mirror of
https://github.com/yt-dlp/yt-dlp
synced 2025-12-16 22:25:40 +07:00
Compare commits
192 Commits
2025.06.25
...
2025.08.27
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
487a90c8ef | ||
|
|
8cd37b85d4 | ||
|
|
5c7ad68ff1 | ||
|
|
1ddbd033f0 | ||
|
|
fec30c56f0 | ||
|
|
d6950c27af | ||
|
|
3bd9154412 | ||
|
|
8f4a908300 | ||
|
|
f1ba9f4ddb | ||
|
|
5c8bcfdbc6 | ||
|
|
895e762a83 | ||
|
|
39b7b8ddc7 | ||
|
|
526410b4af | ||
|
|
f29acc4a6e | ||
|
|
4dbe96459d | ||
|
|
a03c37b44e | ||
|
|
fcea3edb5c | ||
|
|
415b6d9ca8 | ||
|
|
575753b9f3 | ||
|
|
c2fc4f3e7f | ||
|
|
07247d6c20 | ||
|
|
f63a7e41d1 | ||
|
|
7b8a8abb98 | ||
|
|
a97f4cb57e | ||
|
|
d154dc3dcf | ||
|
|
438d3f06b3 | ||
|
|
74b4b3b005 | ||
|
|
36e873822b | ||
|
|
d3d1ac8eb2 | ||
|
|
86d74e5cf0 | ||
|
|
6ca9165648 | ||
|
|
82a1390204 | ||
|
|
7540aa1da1 | ||
|
|
35da8df4f8 | ||
|
|
8df121ba59 | ||
|
|
471a2b60e0 | ||
|
|
df0553153e | ||
|
|
7bc53ae799 | ||
|
|
d8200ff0a4 | ||
|
|
0f6b915822 | ||
|
|
374ea049f5 | ||
|
|
6f4c1bb593 | ||
|
|
c22660aed5 | ||
|
|
404bd889d0 | ||
|
|
edf55e8184 | ||
|
|
8a8861d538 | ||
|
|
70f5669951 | ||
|
|
6ae3543d5a | ||
|
|
770119bdd1 | ||
|
|
8e3f8065af | ||
|
|
aea85d525e | ||
|
|
f2919bd28e | ||
|
|
681ed2153d | ||
|
|
bdeb3eb3f2 | ||
|
|
b7de89c910 | ||
|
|
5e4ceb35cf | ||
|
|
e98695549e | ||
|
|
bf366517ef | ||
|
|
c76ce28e06 | ||
|
|
e8d49b1c7f | ||
|
|
a6df5e8a58 | ||
|
|
e8d2807296 | ||
|
|
fe53ebe5b6 | ||
|
|
662af5bb83 | ||
|
|
8175f3738f | ||
|
|
1e0c77ddcc | ||
|
|
e651a53a2f | ||
|
|
f799a4b472 | ||
|
|
38c2bf4026 | ||
|
|
6ff135c319 | ||
|
|
cd31c319e3 | ||
|
|
6539ee1947 | ||
|
|
43dedbe639 | ||
|
|
05e553e9d1 | ||
|
|
1c6068af99 | ||
|
|
71f30921a2 | ||
|
|
121647705a | ||
|
|
70d7687487 | ||
|
|
42ca3d601e | ||
|
|
62e2a9c0d5 | ||
|
|
28b68f6875 | ||
|
|
682334e4b3 | ||
|
|
b831406a1d | ||
|
|
23c658b9cb | ||
|
|
cc5a5caac5 | ||
|
|
66aa21dc5a | ||
|
|
57186f958f | ||
|
|
daa1859be1 | ||
|
|
e8c2bf798b | ||
|
|
1fe83b0111 | ||
|
|
30302df22b | ||
|
|
3e609b2ced | ||
|
|
d399505fdf | ||
|
|
61d4cd0bc0 | ||
|
|
4385480795 | ||
|
|
485de69dbf | ||
|
|
0adeb1e54b | ||
|
|
afaf60d9fd | ||
|
|
7e3f48d64d | ||
|
|
59765ecbc0 | ||
|
|
c59ad2b066 | ||
|
|
eed94c7306 | ||
|
|
3e918d825d | ||
|
|
035b1ece8f | ||
|
|
9951fdd0d0 | ||
|
|
959ac99e98 | ||
|
|
d88b304d44 | ||
|
|
b15aa8d772 | ||
|
|
d3edc5d52a | ||
|
|
060c6a4501 | ||
|
|
6be26626f7 | ||
|
|
ef103b2d11 | ||
|
|
3e49bc8a1b | ||
|
|
2ac3eb9837 | ||
|
|
8820101aa3 | ||
|
|
a4561c7a66 | ||
|
|
32809eb2da | ||
|
|
f9dff95cb1 | ||
|
|
790c286ce3 | ||
|
|
87e3dc8c7f | ||
|
|
1a8474c3ca | ||
|
|
09982bc33e | ||
|
|
c8329fc572 | ||
|
|
1f27a9f8ba | ||
|
|
4919051e44 | ||
|
|
5f951ce929 | ||
|
|
28bf46b7da | ||
|
|
b8abd255e4 | ||
|
|
c1ac543c81 | ||
|
|
dcc4cba39e | ||
|
|
3a84be9d16 | ||
|
|
d42a6ff0c4 | ||
|
|
ade876efb3 | ||
|
|
7e0af2b1f0 | ||
|
|
d57a0b5aa7 | ||
|
|
6fb3947c0d | ||
|
|
9f54ea3898 | ||
|
|
07d1d85f63 | ||
|
|
5d693446e8 | ||
|
|
23e9389f93 | ||
|
|
6d39c420f7 | ||
|
|
85c3fa1925 | ||
|
|
b4b4486eff | ||
|
|
630f3389c3 | ||
|
|
a6db1d297a | ||
|
|
0f33950c77 | ||
|
|
b5fea53f20 | ||
|
|
5245231e4a | ||
|
|
3ae61e0f31 | ||
|
|
a5d697f62d | ||
|
|
6e5bee418b | ||
|
|
5b57b72c1a | ||
|
|
2aaf1aa71d | ||
|
|
7b4c96e089 | ||
|
|
0b359b184d | ||
|
|
805519bfaa | ||
|
|
aa9f1f4d57 | ||
|
|
fd36b8f31b | ||
|
|
99093e96fd | ||
|
|
7c49a93788 | ||
|
|
884f35d54a | ||
|
|
c23d837b65 | ||
|
|
a7113722ec | ||
|
|
0e68332bcb | ||
|
|
422cc8cb2f | ||
|
|
fca94ac5d6 | ||
|
|
b342d27f3f | ||
|
|
b6328ca050 | ||
|
|
0b41746964 | ||
|
|
c316416b97 | ||
|
|
e99c0b838a | ||
|
|
c2ff2dbaec | ||
|
|
ca5cce5b07 | ||
|
|
f3008bc5f8 | ||
|
|
30fa54280b | ||
|
|
b018784498 | ||
|
|
11b9416e10 | ||
|
|
35fc33fbc5 | ||
|
|
b16722ede8 | ||
|
|
500761e41a | ||
|
|
2ba5391cd6 | ||
|
|
e9f157669e | ||
|
|
958153a226 | ||
|
|
1b88384634 | ||
|
|
7b81634fb1 | ||
|
|
7e2504f941 | ||
|
|
4bd9a7ade7 | ||
|
|
b5bd057fe8 | ||
|
|
5e292baad6 | ||
|
|
0a6b104489 | ||
|
|
06c1a8cdff | ||
|
|
99b85ac102 |
202
.github/workflows/build.yml
vendored
202
.github/workflows/build.yml
vendored
@@ -21,15 +21,9 @@ on:
|
||||
macos:
|
||||
default: true
|
||||
type: boolean
|
||||
macos_legacy:
|
||||
default: true
|
||||
type: boolean
|
||||
windows:
|
||||
default: true
|
||||
type: boolean
|
||||
windows32:
|
||||
default: true
|
||||
type: boolean
|
||||
origin:
|
||||
required: false
|
||||
default: ''
|
||||
@@ -67,16 +61,8 @@ on:
|
||||
description: yt-dlp_macos, yt-dlp_macos.zip
|
||||
default: true
|
||||
type: boolean
|
||||
macos_legacy:
|
||||
description: yt-dlp_macos_legacy
|
||||
default: true
|
||||
type: boolean
|
||||
windows:
|
||||
description: yt-dlp.exe, yt-dlp_win.zip
|
||||
default: true
|
||||
type: boolean
|
||||
windows32:
|
||||
description: yt-dlp_x86.exe
|
||||
description: yt-dlp.exe, yt-dlp_win.zip, yt-dlp_x86.exe, yt-dlp_win_x86.zip, yt-dlp_arm64.exe, yt-dlp_win_arm64.zip
|
||||
default: true
|
||||
type: boolean
|
||||
origin:
|
||||
@@ -208,7 +194,7 @@ jobs:
|
||||
python3.9 -m pip install -U pip wheel 'setuptools>=71.0.2'
|
||||
# XXX: Keep this in sync with pyproject.toml (it can't be accessed at this stage) and exclude secretstorage
|
||||
python3.9 -m pip install -U Pyinstaller mutagen pycryptodomex brotli certifi cffi \
|
||||
'requests>=2.32.2,<3' 'urllib3>=1.26.17,<3' 'websockets>=13.0'
|
||||
'requests>=2.32.2,<3' 'urllib3>=2.0.2,<3' 'websockets>=13.0'
|
||||
|
||||
run: |
|
||||
cd repo
|
||||
@@ -242,7 +228,7 @@ jobs:
|
||||
permissions:
|
||||
contents: read
|
||||
actions: write # For cleaning up cache
|
||||
runs-on: macos-13
|
||||
runs-on: macos-14
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
@@ -261,6 +247,8 @@ jobs:
|
||||
- name: Install Requirements
|
||||
run: |
|
||||
brew install coreutils
|
||||
# We need to use system Python in order to roll our own universal2 curl_cffi wheel
|
||||
brew uninstall --ignore-dependencies python3
|
||||
python3 -m venv ~/yt-dlp-build-venv
|
||||
source ~/yt-dlp-build-venv/bin/activate
|
||||
python3 devscripts/install_deps.py -o --include build
|
||||
@@ -342,91 +330,76 @@ jobs:
|
||||
~/yt-dlp-build-venv
|
||||
key: cache-reqs-${{ github.job }}-${{ github.ref }}
|
||||
|
||||
macos_legacy:
|
||||
needs: process
|
||||
if: inputs.macos_legacy
|
||||
runs-on: macos-13
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Install Python
|
||||
# We need the official Python, because the GA ones only support newer macOS versions
|
||||
env:
|
||||
PYTHON_VERSION: 3.10.5
|
||||
MACOSX_DEPLOYMENT_TARGET: 10.9 # Used up by the Python build tools
|
||||
run: |
|
||||
# Hack to get the latest patch version. Uncomment if needed
|
||||
#brew install python@3.10
|
||||
#export PYTHON_VERSION=$( $(brew --prefix)/opt/python@3.10/bin/python3 --version | cut -d ' ' -f 2 )
|
||||
curl "https://www.python.org/ftp/python/${PYTHON_VERSION}/python-${PYTHON_VERSION}-macos11.pkg" -o "python.pkg"
|
||||
sudo installer -pkg python.pkg -target /
|
||||
python3 --version
|
||||
- name: Install Requirements
|
||||
run: |
|
||||
brew install coreutils
|
||||
python3 devscripts/install_deps.py --user -o --include build
|
||||
python3 devscripts/install_deps.py --user --include pyinstaller
|
||||
|
||||
- name: Prepare
|
||||
run: |
|
||||
python3 devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
|
||||
python3 devscripts/make_lazy_extractors.py
|
||||
- name: Build
|
||||
run: |
|
||||
python3 -m bundle.pyinstaller
|
||||
mv dist/yt-dlp_macos dist/yt-dlp_macos_legacy
|
||||
|
||||
- name: Verify --update-to
|
||||
if: vars.UPDATE_TO_VERIFICATION
|
||||
run: |
|
||||
chmod +x ./dist/yt-dlp_macos_legacy
|
||||
cp ./dist/yt-dlp_macos_legacy ./dist/yt-dlp_macos_legacy_downgraded
|
||||
version="$(./dist/yt-dlp_macos_legacy --version)"
|
||||
./dist/yt-dlp_macos_legacy_downgraded -v --update-to yt-dlp/yt-dlp@2023.03.04
|
||||
downgraded_version="$(./dist/yt-dlp_macos_legacy_downgraded --version)"
|
||||
[[ "$version" != "$downgraded_version" ]]
|
||||
|
||||
- name: Upload artifacts
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: build-bin-${{ github.job }}
|
||||
path: |
|
||||
dist/yt-dlp_macos_legacy
|
||||
compression-level: 0
|
||||
|
||||
windows:
|
||||
needs: process
|
||||
if: inputs.windows
|
||||
runs-on: windows-latest
|
||||
permissions:
|
||||
contents: read
|
||||
actions: write # For cleaning up cache
|
||||
runs-on: ${{ matrix.runner }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- arch: 'x64'
|
||||
runner: windows-2025
|
||||
python_version: '3.10'
|
||||
suffix: ''
|
||||
- arch: 'x86'
|
||||
runner: windows-2025
|
||||
python_version: '3.10'
|
||||
suffix: '_x86'
|
||||
- arch: 'arm64'
|
||||
runner: windows-11-arm
|
||||
python_version: '3.13' # arm64 only has Python >= 3.11 available
|
||||
suffix: '_arm64'
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.10"
|
||||
python-version: ${{ matrix.python_version }}
|
||||
architecture: ${{ matrix.arch }}
|
||||
|
||||
- name: Restore cached requirements
|
||||
id: restore-cache
|
||||
if: matrix.arch == 'arm64'
|
||||
uses: actions/cache/restore@v4
|
||||
env:
|
||||
SEGMENT_DOWNLOAD_TIMEOUT_MINS: 1
|
||||
with:
|
||||
path: |
|
||||
/yt-dlp-build-venv
|
||||
key: cache-reqs-${{ github.job }}_${{ matrix.arch }}-${{ matrix.python_version }}-${{ github.ref }}
|
||||
|
||||
- name: Install Requirements
|
||||
run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
|
||||
run: |
|
||||
python -m venv /yt-dlp-build-venv
|
||||
/yt-dlp-build-venv/Scripts/Activate.ps1
|
||||
python devscripts/install_deps.py -o --include build
|
||||
python devscripts/install_deps.py --include curl-cffi
|
||||
python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.13.0-py3-none-any.whl"
|
||||
python devscripts/install_deps.py ${{ (matrix.arch != 'x86' && '--include curl-cffi') || '' }}
|
||||
# Use custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
|
||||
python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/${{ matrix.arch }}/pyinstaller-6.15.0-py3-none-any.whl"
|
||||
|
||||
- name: Prepare
|
||||
run: |
|
||||
python devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
|
||||
python devscripts/make_lazy_extractors.py
|
||||
|
||||
- name: Build
|
||||
run: |
|
||||
/yt-dlp-build-venv/Scripts/Activate.ps1
|
||||
python -m bundle.pyinstaller
|
||||
python -m bundle.pyinstaller --onedir
|
||||
Compress-Archive -Path ./dist/yt-dlp/* -DestinationPath ./dist/yt-dlp_win.zip
|
||||
Compress-Archive -Path ./dist/yt-dlp${{ matrix.suffix }}/* -DestinationPath ./dist/yt-dlp_win${{ matrix.suffix }}.zip
|
||||
|
||||
- name: Verify --update-to
|
||||
if: vars.UPDATE_TO_VERIFICATION
|
||||
run: |
|
||||
foreach ($name in @("yt-dlp")) {
|
||||
foreach ($name in @("yt-dlp${{ matrix.suffix }}")) {
|
||||
Copy-Item "./dist/${name}.exe" "./dist/${name}_downgraded.exe"
|
||||
$version = & "./dist/${name}.exe" --version
|
||||
& "./dist/${name}_downgraded.exe" -v --update-to yt-dlp/yt-dlp@2023.03.04
|
||||
& "./dist/${name}_downgraded.exe" -v --update-to yt-dlp/yt-dlp@2025.08.20
|
||||
$downgraded_version = & "./dist/${name}_downgraded.exe" --version
|
||||
if ($version -eq $downgraded_version) {
|
||||
exit 1
|
||||
@@ -436,57 +409,28 @@ jobs:
|
||||
- name: Upload artifacts
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: build-bin-${{ github.job }}
|
||||
name: build-bin-${{ github.job }}-${{ matrix.arch }}
|
||||
path: |
|
||||
dist/yt-dlp.exe
|
||||
dist/yt-dlp_win.zip
|
||||
dist/yt-dlp${{ matrix.suffix }}.exe
|
||||
dist/yt-dlp_win${{ matrix.suffix }}.zip
|
||||
compression-level: 0
|
||||
|
||||
windows32:
|
||||
needs: process
|
||||
if: inputs.windows32
|
||||
runs-on: windows-latest
|
||||
- name: Cleanup cache
|
||||
if: |
|
||||
matrix.arch == 'arm64' && steps.restore-cache.outputs.cache-hit == 'true'
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
cache_key: cache-reqs-${{ github.job }}_${{ matrix.arch }}-${{ matrix.python_version }}-${{ github.ref }}
|
||||
run: |
|
||||
gh cache delete "${cache_key}"
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
- name: Cache requirements
|
||||
if: matrix.arch == 'arm64'
|
||||
uses: actions/cache/save@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
architecture: "x86"
|
||||
- name: Install Requirements
|
||||
run: |
|
||||
python devscripts/install_deps.py -o --include build
|
||||
python devscripts/install_deps.py
|
||||
python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.13.0-py3-none-any.whl"
|
||||
|
||||
- name: Prepare
|
||||
run: |
|
||||
python devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
|
||||
python devscripts/make_lazy_extractors.py
|
||||
- name: Build
|
||||
run: |
|
||||
python -m bundle.pyinstaller
|
||||
|
||||
- name: Verify --update-to
|
||||
if: vars.UPDATE_TO_VERIFICATION
|
||||
run: |
|
||||
foreach ($name in @("yt-dlp_x86")) {
|
||||
Copy-Item "./dist/${name}.exe" "./dist/${name}_downgraded.exe"
|
||||
$version = & "./dist/${name}.exe" --version
|
||||
& "./dist/${name}_downgraded.exe" -v --update-to yt-dlp/yt-dlp@2023.03.04
|
||||
$downgraded_version = & "./dist/${name}_downgraded.exe" --version
|
||||
if ($version -eq $downgraded_version) {
|
||||
exit 1
|
||||
}
|
||||
}
|
||||
|
||||
- name: Upload artifacts
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: build-bin-${{ github.job }}
|
||||
path: |
|
||||
dist/yt-dlp_x86.exe
|
||||
compression-level: 0
|
||||
/yt-dlp-build-venv
|
||||
key: cache-reqs-${{ github.job }}_${{ matrix.arch }}-${{ matrix.python_version }}-${{ github.ref }}
|
||||
|
||||
meta_files:
|
||||
if: always() && !cancelled()
|
||||
@@ -496,9 +440,7 @@ jobs:
|
||||
- linux_static
|
||||
- linux_arm
|
||||
- macos
|
||||
- macos_legacy
|
||||
- windows
|
||||
- windows32
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Download artifacts
|
||||
@@ -528,27 +470,31 @@ jobs:
|
||||
lock 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lock 2024.10.22 py2exe .+
|
||||
lock 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lock 2024.10.22 (?!\w+_exe).+ Python 3\.8
|
||||
lock 2024.10.22 zip Python 3\.8
|
||||
lock 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lock 2025.08.11 darwin_legacy_exe .+
|
||||
lockV2 yt-dlp/yt-dlp 2022.08.18.36 .+ Python 3\.6
|
||||
lockV2 yt-dlp/yt-dlp 2023.11.16 (?!win_x86_exe).+ Python 3\.7
|
||||
lockV2 yt-dlp/yt-dlp 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp 2025.08.11 darwin_legacy_exe .+
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 (?!win_x86_exe).+ Python 3\.7
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2025.08.12.233030 darwin_legacy_exe .+
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 (?!win_x86_exe).+ Python 3\.7
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.045052 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2025.08.12.232447 darwin_legacy_exe .+
|
||||
EOF
|
||||
|
||||
- name: Sign checksum files
|
||||
|
||||
4
.github/workflows/core.yml
vendored
4
.github/workflows/core.yml
vendored
@@ -37,7 +37,7 @@ jobs:
|
||||
matrix:
|
||||
os: [ubuntu-latest]
|
||||
# CPython 3.9 is in quick-test
|
||||
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.10]
|
||||
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
|
||||
include:
|
||||
# atleast one of each CPython/PyPy tests must be in windows
|
||||
- os: windows-latest
|
||||
@@ -49,7 +49,7 @@ jobs:
|
||||
- os: windows-latest
|
||||
python-version: '3.13'
|
||||
- os: windows-latest
|
||||
python-version: pypy-3.10
|
||||
python-version: pypy-3.11
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
|
||||
4
.github/workflows/download.yml
vendored
4
.github/workflows/download.yml
vendored
@@ -28,13 +28,13 @@ jobs:
|
||||
fail-fast: true
|
||||
matrix:
|
||||
os: [ubuntu-latest]
|
||||
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.10]
|
||||
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
|
||||
include:
|
||||
# atleast one of each CPython/PyPy tests must be in windows
|
||||
- os: windows-latest
|
||||
python-version: '3.9'
|
||||
- os: windows-latest
|
||||
python-version: pypy-3.10
|
||||
python-version: pypy-3.11
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
|
||||
41
.github/workflows/signature-tests.yml
vendored
Normal file
41
.github/workflows/signature-tests.yml
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
name: Signature Tests
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- .github/workflows/signature-tests.yml
|
||||
- test/test_youtube_signature.py
|
||||
- yt_dlp/jsinterp.py
|
||||
pull_request:
|
||||
paths:
|
||||
- .github/workflows/signature-tests.yml
|
||||
- test/test_youtube_signature.py
|
||||
- yt_dlp/jsinterp.py
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: signature-tests-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
||||
|
||||
jobs:
|
||||
tests:
|
||||
name: Signature Tests
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [ubuntu-latest, windows-latest]
|
||||
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', pypy-3.11]
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install test requirements
|
||||
run: python3 ./devscripts/install_deps.py --only-optional --include test
|
||||
- name: Run tests
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
python3 -m yt_dlp -v || true # Print debug head
|
||||
python3 ./devscripts/run_tests.py test/test_youtube_signature.py
|
||||
@@ -126,7 +126,7 @@ ### Are you willing to share account details if needed?
|
||||
While these steps won't necessarily ensure that no misuse of the account takes place, these are still some good practices to follow.
|
||||
|
||||
- Look for people with `Member` (maintainers of the project) or `Contributor` (people who have previously contributed code) tag on their messages.
|
||||
- Change the password before sharing the account to something random (use [this](https://passwordsgenerator.net/) if you don't have a random password generator).
|
||||
- Change the password before sharing the account to something random.
|
||||
- Change the password after receiving the account back.
|
||||
|
||||
### Is the website primarily used for piracy?
|
||||
@@ -272,7 +272,7 @@ ## Adding support for a new site
|
||||
|
||||
You can use `hatch fmt` to automatically fix problems. Rules that the linter/formatter enforces should not be disabled with `# noqa` unless a maintainer requests it. The only exception allowed is for old/printf-style string formatting in GraphQL query templates (use `# noqa: UP031`).
|
||||
|
||||
1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython >=3.9 and PyPy >=3.10. Backward compatibility is not required for even older versions of Python.
|
||||
1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython >=3.9 and PyPy >=3.11. Backward compatibility is not required for even older versions of Python.
|
||||
1. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files, [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
|
||||
|
||||
```shell
|
||||
|
||||
27
CONTRIBUTORS
27
CONTRIBUTORS
@@ -4,6 +4,7 @@ coletdjnz/colethedj (collaborator)
|
||||
Ashish0804 (collaborator)
|
||||
bashonly (collaborator)
|
||||
Grub4K (collaborator)
|
||||
seproDev (collaborator)
|
||||
h-h-h-h
|
||||
pauldubois98
|
||||
nixxo
|
||||
@@ -403,7 +404,6 @@ rebane2001
|
||||
road-master
|
||||
rohieb
|
||||
sdht0
|
||||
seproDev
|
||||
Hill-98
|
||||
LXYan2333
|
||||
mushbite
|
||||
@@ -781,3 +781,28 @@ maxbin123
|
||||
nullpos
|
||||
anlar
|
||||
eason1478
|
||||
ceandreasen
|
||||
chauhantirth
|
||||
helpimnotdrowning
|
||||
adamralph
|
||||
averageFOSSenjoyer
|
||||
bubo
|
||||
flanter21
|
||||
Georift
|
||||
moonshinerd
|
||||
R0hanW
|
||||
ShockedPlot7560
|
||||
swayll
|
||||
atsushi2965
|
||||
barryvan
|
||||
injust
|
||||
iribeirocampos
|
||||
rolandcrosby
|
||||
Sojiroh
|
||||
tchebb
|
||||
AzartX47
|
||||
e2dk4r
|
||||
junyilou
|
||||
PierreMesure
|
||||
Randalix
|
||||
runarmod
|
||||
|
||||
268
Changelog.md
268
Changelog.md
@@ -4,6 +4,274 @@ # Changelog
|
||||
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
|
||||
-->
|
||||
|
||||
### 2025.08.27
|
||||
|
||||
#### Extractor changes
|
||||
- **generic**
|
||||
- [Simplify invalid URL error message](https://github.com/yt-dlp/yt-dlp/commit/1ddbd033f0fd65917526b1271cea66913ac8647f) ([#14167](https://github.com/yt-dlp/yt-dlp/issues/14167)) by [seproDev](https://github.com/seproDev)
|
||||
- [Use https as fallback protocol](https://github.com/yt-dlp/yt-dlp/commit/fec30c56f0e97e573ace659104ff0d72c4cc9809) ([#14160](https://github.com/yt-dlp/yt-dlp/issues/14160)) by [seproDev](https://github.com/seproDev)
|
||||
- **skeb**: [Support wav files](https://github.com/yt-dlp/yt-dlp/commit/d6950c27af31908363c5c815e3b7eb4f9ff41643) ([#14147](https://github.com/yt-dlp/yt-dlp/issues/14147)) by [seproDev](https://github.com/seproDev)
|
||||
- **youtube**
|
||||
- [Add `tcc` player JS variant](https://github.com/yt-dlp/yt-dlp/commit/8f4a908300f55054bc96814bceeaa1034fdf4110) ([#14134](https://github.com/yt-dlp/yt-dlp/issues/14134)) by [bashonly](https://github.com/bashonly)
|
||||
- [Deprioritize `web_safari` m3u8 formats](https://github.com/yt-dlp/yt-dlp/commit/5c7ad68ff1643ad80d18cef8be9db8fcab05ee6c) ([#14168](https://github.com/yt-dlp/yt-dlp/issues/14168)) by [bashonly](https://github.com/bashonly)
|
||||
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/3bd91544122142a87863d79e54e995c26cfd7f92) ([#14135](https://github.com/yt-dlp/yt-dlp/issues/14135)) by [bashonly](https://github.com/bashonly)
|
||||
- [Use alternative `tv` user-agent when authenticated](https://github.com/yt-dlp/yt-dlp/commit/8cd37b85d492edb56a4f7506ea05527b85a6b02b) ([#14169](https://github.com/yt-dlp/yt-dlp/issues/14169)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
### 2025.08.22
|
||||
|
||||
#### Core changes
|
||||
- **cookies**: [Fix `--cookies-from-browser` with Firefox 142+](https://github.com/yt-dlp/yt-dlp/commit/f29acc4a6e73a9dc091686d40951288acae5a46d) ([#14114](https://github.com/yt-dlp/yt-dlp/issues/14114)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K) (With fixes in [526410b](https://github.com/yt-dlp/yt-dlp/commit/526410b4af9c1ca73aa3503cdaf4d32e42308fd6) by [bashonly](https://github.com/bashonly))
|
||||
|
||||
#### Extractor changes
|
||||
- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4dbe96459d7e632d397826d0bb323f3f0ac8b057) ([#13975](https://github.com/yt-dlp/yt-dlp/issues/13975)) by [zhallgato](https://github.com/zhallgato)
|
||||
- **steam**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/fcea3edb5c5648638357f27431500c0aaf08b147) ([#14093](https://github.com/yt-dlp/yt-dlp/issues/14093)) by [doe1080](https://github.com/doe1080)
|
||||
- **youtube**
|
||||
- [Improve `tv` client context](https://github.com/yt-dlp/yt-dlp/commit/39b7b8ddc7a4d0669e0cf39105c3bb84cb2736cc) ([#14122](https://github.com/yt-dlp/yt-dlp/issues/14122)) by [bashonly](https://github.com/bashonly)
|
||||
- [Optimize playback wait times](https://github.com/yt-dlp/yt-dlp/commit/5c8bcfdbc638dfde13e93157637d8521413ed774) ([#14124](https://github.com/yt-dlp/yt-dlp/issues/14124)) by [bashonly](https://github.com/bashonly)
|
||||
- [Replace `ios` with `tv_simply` in default clients](https://github.com/yt-dlp/yt-dlp/commit/895e762a834bbd729ab822c7d17329fdf815aaf2) ([#14123](https://github.com/yt-dlp/yt-dlp/issues/14123)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Update `tv` client config](https://github.com/yt-dlp/yt-dlp/commit/a03c37b44ec8f50fd472c409115096f92410346d) ([#14101](https://github.com/yt-dlp/yt-dlp/issues/14101)) by [seproDev](https://github.com/seproDev)
|
||||
|
||||
#### Misc. changes
|
||||
- **build**: [Post-release workflow cleanup](https://github.com/yt-dlp/yt-dlp/commit/415b6d9ca868032a45b30b9139a50c5c06be2feb) ([#14090](https://github.com/yt-dlp/yt-dlp/issues/14090)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
### 2025.08.20
|
||||
|
||||
#### Core changes
|
||||
- [Warn against using `-f mp4`](https://github.com/yt-dlp/yt-dlp/commit/70f56699515e0854a4853d214dce11b61d432387) ([#13915](https://github.com/yt-dlp/yt-dlp/issues/13915)) by [seproDev](https://github.com/seproDev)
|
||||
- **utils**: [Add improved `jwt_encode` function](https://github.com/yt-dlp/yt-dlp/commit/35da8df4f843cb8f0656a301e5bebbf47d64d69a) ([#14071](https://github.com/yt-dlp/yt-dlp/issues/14071)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Extractor changes
|
||||
- [Extract avif storyboard formats from MPD manifests](https://github.com/yt-dlp/yt-dlp/commit/770119bdd15c525ba4338503f0eb68ea4baedf10) ([#14016](https://github.com/yt-dlp/yt-dlp/issues/14016)) by [doe1080](https://github.com/doe1080)
|
||||
- `_rta_search`: [Do not assume `age_limit` is `0`](https://github.com/yt-dlp/yt-dlp/commit/6ae3543d5a1feea0c546571fd2782b024c108eac) ([#13985](https://github.com/yt-dlp/yt-dlp/issues/13985)) by [doe1080](https://github.com/doe1080)
|
||||
- **adobetv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/c22660aed5fadb4ac29bdf25db4e8016414153cc) ([#13917](https://github.com/yt-dlp/yt-dlp/issues/13917)) by [doe1080](https://github.com/doe1080)
|
||||
- **bilibili**: [Handle Bangumi redirection](https://github.com/yt-dlp/yt-dlp/commit/6ca9165648ac9a07c012de639faf50a97cbe0991) ([#14038](https://github.com/yt-dlp/yt-dlp/issues/14038)) by [grqz](https://github.com/grqz), [junyilou](https://github.com/junyilou)
|
||||
- **faulio**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/74b4b3b00516e92a60250e0626272a6826459057) ([#13907](https://github.com/yt-dlp/yt-dlp/issues/13907)) by [CasperMcFadden95](https://github.com/CasperMcFadden95)
|
||||
- **francetv**: site: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7b8a8abb98165a53c026e2a3f52faee608df1f20) ([#14082](https://github.com/yt-dlp/yt-dlp/issues/14082)) by [bashonly](https://github.com/bashonly)
|
||||
- **medialaan**: [Rework extractors](https://github.com/yt-dlp/yt-dlp/commit/86d74e5cf0e06c53c931ccdbdd497e3f2c4d2fe2) ([#14015](https://github.com/yt-dlp/yt-dlp/issues/14015)) by [doe1080](https://github.com/doe1080)
|
||||
- **mtv**: [Overhaul extractors](https://github.com/yt-dlp/yt-dlp/commit/8df121ba59208979aa713822781891347abd03d1) ([#14052](https://github.com/yt-dlp/yt-dlp/issues/14052)) by [bashonly](https://github.com/bashonly), [doe1080](https://github.com/doe1080), [Randalix](https://github.com/Randalix), [seproDev](https://github.com/seproDev)
|
||||
- **niconico**: live: [Support age-restricted streams](https://github.com/yt-dlp/yt-dlp/commit/374ea049f531959bcccf8a1e6bc5659d228a780e) ([#13549](https://github.com/yt-dlp/yt-dlp/issues/13549)) by [doe1080](https://github.com/doe1080)
|
||||
- **nrktvepisode**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7540aa1da1800769af40381f423825a1a8826377) ([#14065](https://github.com/yt-dlp/yt-dlp/issues/14065)) by [runarmod](https://github.com/runarmod)
|
||||
- **puhutv**: [Fix playlists extraction](https://github.com/yt-dlp/yt-dlp/commit/36e873822bdb2c5aba3780dd3ae32cbae564c6cd) ([#11955](https://github.com/yt-dlp/yt-dlp/issues/11955)) by [e2dk4r](https://github.com/e2dk4r)
|
||||
- **steam**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d3d1ac8eb2f9e96f3d75292e0effe2b1bccece3b) ([#14008](https://github.com/yt-dlp/yt-dlp/issues/14008)) by [AzartX47](https://github.com/AzartX47)
|
||||
- **svt**: [Extract forced subs under separate lang code](https://github.com/yt-dlp/yt-dlp/commit/82a139020417a501f261d9fe02cefca01b1e12e4) ([#14062](https://github.com/yt-dlp/yt-dlp/issues/14062)) by [PierreMesure](https://github.com/PierreMesure)
|
||||
- **tiktok**: user: [Avoid infinite loop during extraction](https://github.com/yt-dlp/yt-dlp/commit/edf55e81842fcfa6c302528d7f33ccd5081b37ef) ([#14032](https://github.com/yt-dlp/yt-dlp/issues/14032)) by [bashonly](https://github.com/bashonly) (With fixes in [471a2b6](https://github.com/yt-dlp/yt-dlp/commit/471a2b60e0a3e056960d9ceb1ebf57908428f752))
|
||||
- **vimeo**
|
||||
- album: [Support embed-only and non-numeric albums](https://github.com/yt-dlp/yt-dlp/commit/d8200ff0a4699e06c9f7daca8f8531f8b98e68f2) ([#14021](https://github.com/yt-dlp/yt-dlp/issues/14021)) by [bashonly](https://github.com/bashonly)
|
||||
- event: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0f6b915822fb64bd944126fdacd401975c9f06ed) ([#14064](https://github.com/yt-dlp/yt-dlp/issues/14064)) by [bashonly](https://github.com/bashonly)
|
||||
- **weibo**
|
||||
- [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/8e3f8065af1415caeff788c5c430703dd0d8f576) ([#14012](https://github.com/yt-dlp/yt-dlp/issues/14012)) by [AzartX47](https://github.com/AzartX47), [bashonly](https://github.com/bashonly)
|
||||
- [Support more URLs and --no-playlist](https://github.com/yt-dlp/yt-dlp/commit/404bd889d0e0b62ad72b7281e3fefdc0497080b3) ([#14035](https://github.com/yt-dlp/yt-dlp/issues/14035)) by [bashonly](https://github.com/bashonly)
|
||||
- **youtube**
|
||||
- [Add `es5` and `es6` player JS variants](https://github.com/yt-dlp/yt-dlp/commit/f2919bd28eac905f1267c62b83738a02bb5b4e04) ([#14005](https://github.com/yt-dlp/yt-dlp/issues/14005)) by [bashonly](https://github.com/bashonly)
|
||||
- [Add `playback_wait` extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/f63a7e41d120ef84f0f2274b0962438e3272d2fa) by [bashonly](https://github.com/bashonly)
|
||||
- [Default to `main` player JS variant](https://github.com/yt-dlp/yt-dlp/commit/df0553153e41f81e3b30aa5bb1d119c61bd449ac) ([#14079](https://github.com/yt-dlp/yt-dlp/issues/14079)) by [bashonly](https://github.com/bashonly)
|
||||
- [Extract title and description from initial data](https://github.com/yt-dlp/yt-dlp/commit/7bc53ae79930b36f4f947679545c75f36e9f0ddd) ([#14078](https://github.com/yt-dlp/yt-dlp/issues/14078)) by [bashonly](https://github.com/bashonly)
|
||||
- [Handle required preroll waiting period](https://github.com/yt-dlp/yt-dlp/commit/a97f4cb57e61e19be61a7d5ac19665d4b567c960) ([#14081](https://github.com/yt-dlp/yt-dlp/issues/14081)) by [bashonly](https://github.com/bashonly)
|
||||
- [Remove default player params](https://github.com/yt-dlp/yt-dlp/commit/d154dc3dcf0c7c75dbabb6cd1aca66fdd806f858) ([#14081](https://github.com/yt-dlp/yt-dlp/issues/14081)) by [bashonly](https://github.com/bashonly)
|
||||
- tab: [Fix playlists tab extraction](https://github.com/yt-dlp/yt-dlp/commit/8a8861d53864c8a38e924bc0657ead5180f17268) ([#14030](https://github.com/yt-dlp/yt-dlp/issues/14030)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Downloader changes
|
||||
- [Support `available_at` format field](https://github.com/yt-dlp/yt-dlp/commit/438d3f06b3c41bdef8112d40b75d342186e91a16) ([#13980](https://github.com/yt-dlp/yt-dlp/issues/13980)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Postprocessor changes
|
||||
- **xattrmetadata**: [Only set "Where From" attribute on macOS](https://github.com/yt-dlp/yt-dlp/commit/bdeb3eb3f29eebbe8237fbc5186e51e7293eea4a) ([#13999](https://github.com/yt-dlp/yt-dlp/issues/13999)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Misc. changes
|
||||
- **build**
|
||||
- [Add Windows ARM64 builds](https://github.com/yt-dlp/yt-dlp/commit/07247d6c20fef1ad13b6f71f6355a44d308cf010) ([#14003](https://github.com/yt-dlp/yt-dlp/issues/14003)) by [bashonly](https://github.com/bashonly)
|
||||
- [Bump PyInstaller version to 6.15.0 for Windows](https://github.com/yt-dlp/yt-dlp/commit/681ed2153de754c2c885fdad09ab71fffa8114f9) ([#14002](https://github.com/yt-dlp/yt-dlp/issues/14002)) by [bashonly](https://github.com/bashonly)
|
||||
- [Discontinue `darwin_legacy_exe` support](https://github.com/yt-dlp/yt-dlp/commit/aea85d525e1007bb64baec0e170c054292d0858a) ([#13860](https://github.com/yt-dlp/yt-dlp/issues/13860)) by [bashonly](https://github.com/bashonly)
|
||||
- **cleanup**
|
||||
- [Remove dead extractors](https://github.com/yt-dlp/yt-dlp/commit/6f4c1bb593da92f0ce68229d0c813cdbaf1314da) ([#13996](https://github.com/yt-dlp/yt-dlp/issues/13996)) by [doe1080](https://github.com/doe1080)
|
||||
- Miscellaneous: [c2fc4f3](https://github.com/yt-dlp/yt-dlp/commit/c2fc4f3e7f6d757250183b177130c64beee50520) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
### 2025.08.11
|
||||
|
||||
#### Important changes
|
||||
- **The minimum *recommended* Python version has been raised to 3.10**
|
||||
Since Python 3.9 will reach end-of-life in October 2025, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13858)
|
||||
- **darwin_legacy_exe builds are being discontinued**
|
||||
This release's `yt-dlp_macos_legacy` binary will likely be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13856)
|
||||
- **linux_armv7l_exe builds are being discontinued**
|
||||
This release's `yt-dlp_linux_armv7l` binary could be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13976)
|
||||
|
||||
#### Core changes
|
||||
- [Deprecate `darwin_legacy_exe` support](https://github.com/yt-dlp/yt-dlp/commit/cc5a5caac5fbc0d605b52bde0778d6fd5f97b5ab) ([#13857](https://github.com/yt-dlp/yt-dlp/issues/13857)) by [bashonly](https://github.com/bashonly)
|
||||
- [Deprecate `linux_armv7l_exe` support](https://github.com/yt-dlp/yt-dlp/commit/c76ce28e06c816eb5b261dfb6aff6e69dd9b7382) ([#13978](https://github.com/yt-dlp/yt-dlp/issues/13978)) by [bashonly](https://github.com/bashonly)
|
||||
- [Raise minimum recommended Python version to 3.10](https://github.com/yt-dlp/yt-dlp/commit/23c658b9cbe34a151f8f921ab1320bb5d4e40a4d) ([#13859](https://github.com/yt-dlp/yt-dlp/issues/13859)) by [bashonly](https://github.com/bashonly)
|
||||
- [Warn when yt-dlp is severely outdated](https://github.com/yt-dlp/yt-dlp/commit/662af5bb8307ec3ff8ab0857f1159922d64792f0) ([#13937](https://github.com/yt-dlp/yt-dlp/issues/13937)) by [seproDev](https://github.com/seproDev)
|
||||
- **cookies**: [Load cookies with float `expires` timestamps](https://github.com/yt-dlp/yt-dlp/commit/28b68f687561468e0c664dcb430707458970019f) ([#13873](https://github.com/yt-dlp/yt-dlp/issues/13873)) by [bashonly](https://github.com/bashonly)
|
||||
- **utils**
|
||||
- [Add `WINDOWS_VT_MODE` to globals](https://github.com/yt-dlp/yt-dlp/commit/eed94c7306d4ecdba53ad8783b1463a9af5c97f1) ([#12460](https://github.com/yt-dlp/yt-dlp/issues/12460)) by [Grub4K](https://github.com/Grub4K)
|
||||
- `parse_resolution`: [Support width-only pattern](https://github.com/yt-dlp/yt-dlp/commit/4385480795acda35667be008d0bf26b46e9d65b4) ([#13802](https://github.com/yt-dlp/yt-dlp/issues/13802)) by [doe1080](https://github.com/doe1080)
|
||||
- `random_user_agent`: [Bump versions](https://github.com/yt-dlp/yt-dlp/commit/c59ad2b066bbccd3cc4eed580842f961bce7dd4a) ([#13543](https://github.com/yt-dlp/yt-dlp/issues/13543)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Extractor changes
|
||||
- **archive.org**: [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/42ca3d601ee10cef89d698f72e2b5d44fab4f013) ([#13880](https://github.com/yt-dlp/yt-dlp/issues/13880)) by [bashonly](https://github.com/bashonly)
|
||||
- **digitalconcerthall**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/e8d2807296ccc603e031f5982623a8311f2a5119) ([#13948](https://github.com/yt-dlp/yt-dlp/issues/13948)) by [bashonly](https://github.com/bashonly)
|
||||
- **eagleplatform**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/1fe83b0111277a6f214c5ec1819cfbf943508baf) ([#13469](https://github.com/yt-dlp/yt-dlp/issues/13469)) by [doe1080](https://github.com/doe1080)
|
||||
- **fauliolive**
|
||||
- [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3e609b2cedd285739bf82c7af7853735092070a4) ([#13421](https://github.com/yt-dlp/yt-dlp/issues/13421)) by [CasperMcFadden95](https://github.com/CasperMcFadden95), [seproDev](https://github.com/seproDev)
|
||||
- [Support Bahry TV](https://github.com/yt-dlp/yt-dlp/commit/daa1859be1b0e7d123da8b4e0988f2eb7bd47d15) ([#13850](https://github.com/yt-dlp/yt-dlp/issues/13850)) by [CasperMcFadden95](https://github.com/CasperMcFadden95)
|
||||
- **fc2**: [Fix old video support](https://github.com/yt-dlp/yt-dlp/commit/cd31c319e3142622ec43c49485d196ed2835df05) ([#12633](https://github.com/yt-dlp/yt-dlp/issues/12633)) by [JChris246](https://github.com/JChris246), [seproDev](https://github.com/seproDev)
|
||||
- **motherless**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e8d49b1c7f11c7e282319395ca9c2a201304be41) ([#13960](https://github.com/yt-dlp/yt-dlp/issues/13960)) by [Grub4K](https://github.com/Grub4K)
|
||||
- **n1info**: article: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6539ee1947d7885d3606da6365fd858308435a63) ([#13865](https://github.com/yt-dlp/yt-dlp/issues/13865)) by [u-spec-png](https://github.com/u-spec-png)
|
||||
- **neteasemusic**: [Support XFF](https://github.com/yt-dlp/yt-dlp/commit/e8c2bf798b6707d27fecde66161172da69c7cd72) ([#11044](https://github.com/yt-dlp/yt-dlp/issues/11044)) by [c-basalt](https://github.com/c-basalt)
|
||||
- **niconico**: [Fix error handling & improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/05e553e9d1f57655d65c9811d05df38261601b85) ([#13240](https://github.com/yt-dlp/yt-dlp/issues/13240)) by [doe1080](https://github.com/doe1080)
|
||||
- **parlview**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/485de69dbfeb7de7bcf9f7fe16d6c6ba9e81e1a0) ([#13788](https://github.com/yt-dlp/yt-dlp/issues/13788)) by [barryvan](https://github.com/barryvan)
|
||||
- **plyrembed**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/61d4cd0bc01be6ebe11fd53c2d3805d1a2058990) ([#13836](https://github.com/yt-dlp/yt-dlp/issues/13836)) by [seproDev](https://github.com/seproDev)
|
||||
- **royalive**: [Support `en` URLs](https://github.com/yt-dlp/yt-dlp/commit/43dedbe6394bdd489193b15ee9690a62d1b82d94) ([#13908](https://github.com/yt-dlp/yt-dlp/issues/13908)) by [CasperMcFadden95](https://github.com/CasperMcFadden95)
|
||||
- **rtve.es**: program: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b831406a1d3be34c159835079d12bae624c43610) ([#12955](https://github.com/yt-dlp/yt-dlp/issues/12955)) by [meGAmeS1](https://github.com/meGAmeS1), [seproDev](https://github.com/seproDev)
|
||||
- **shiey**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/6ff135c31914ea8b5545f8d187c60e852cfde9bc) ([#13354](https://github.com/yt-dlp/yt-dlp/issues/13354)) by [iribeirocampos](https://github.com/iribeirocampos)
|
||||
- **sportdeuschland**: [Support embedded player URLs](https://github.com/yt-dlp/yt-dlp/commit/30302df22b7b431ce920e0f7298cd10be9989967) ([#13833](https://github.com/yt-dlp/yt-dlp/issues/13833)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
|
||||
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/59765ecbc08d18005de7143fbb1d1caf90239471) ([#13813](https://github.com/yt-dlp/yt-dlp/issues/13813)) by [bashonly](https://github.com/bashonly)
|
||||
- **tbs**: [Fix truTV support](https://github.com/yt-dlp/yt-dlp/commit/0adeb1e54b2d7e95cd19999e71013877850f8f41) ([#9683](https://github.com/yt-dlp/yt-dlp/issues/9683)) by [bashonly](https://github.com/bashonly), [ischmidt20](https://github.com/ischmidt20)
|
||||
- **tbsjp**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/71f30921a2023dbb25c53fd1bb1399cac803116d) ([#13485](https://github.com/yt-dlp/yt-dlp/issues/13485)) by [garret1317](https://github.com/garret1317)
|
||||
- **tver**
|
||||
- [Extract Streaks API info](https://github.com/yt-dlp/yt-dlp/commit/70d7687487252a08dbf8b2831743e7833472ba05) ([#13885](https://github.com/yt-dlp/yt-dlp/issues/13885)) by [bashonly](https://github.com/bashonly)
|
||||
- [Support --ignore-no-formats-error when geo-blocked](https://github.com/yt-dlp/yt-dlp/commit/121647705a2fc6b968278723fe61801007e228a4) ([#13598](https://github.com/yt-dlp/yt-dlp/issues/13598)) by [arabcoders](https://github.com/arabcoders)
|
||||
- **tvw**: news: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/682334e4b35112f7a5798decdcb5cb12230ef948) ([#12907](https://github.com/yt-dlp/yt-dlp/issues/12907)) by [fries1234](https://github.com/fries1234)
|
||||
- **vimeo**: [Fix login support and require authentication](https://github.com/yt-dlp/yt-dlp/commit/afaf60d9fd5a0c7a85aeb1374fd97fbc13cd652c) ([#13823](https://github.com/yt-dlp/yt-dlp/issues/13823)) by [bashonly](https://github.com/bashonly)
|
||||
- **yandexdisk**: [Support 360 URLs](https://github.com/yt-dlp/yt-dlp/commit/a6df5e8a58d6743dd230011389c986495ec509da) ([#13935](https://github.com/yt-dlp/yt-dlp/issues/13935)) by [Sojiroh](https://github.com/Sojiroh)
|
||||
- **youtube**
|
||||
- [Add player params to mweb client](https://github.com/yt-dlp/yt-dlp/commit/38c2bf40260f7788efb5a7f5e8eba8e5cb43f741) ([#13914](https://github.com/yt-dlp/yt-dlp/issues/13914)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Update player params](https://github.com/yt-dlp/yt-dlp/commit/bf366517ef0b745490ee9e0f929254fa26b69647) ([#13979](https://github.com/yt-dlp/yt-dlp/issues/13979)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Downloader changes
|
||||
- **dash**: [Re-extract if using --load-info-json with --live-from-start](https://github.com/yt-dlp/yt-dlp/commit/fe53ebe5b66a03c664708a4d6fd87b8c13a1bc7b) ([#13922](https://github.com/yt-dlp/yt-dlp/issues/13922)) by [bashonly](https://github.com/bashonly)
|
||||
- **external**: [Work around ffmpeg's `file:` URL handling](https://github.com/yt-dlp/yt-dlp/commit/d399505fdf8292332bdc91d33859a0b0d08104fd) ([#13844](https://github.com/yt-dlp/yt-dlp/issues/13844)) by [bashonly](https://github.com/bashonly)
|
||||
- **hls**: [Fix `--hls-split-continuity` support](https://github.com/yt-dlp/yt-dlp/commit/57186f958f164daa50203adcbf7ec74d541151cf) ([#13321](https://github.com/yt-dlp/yt-dlp/issues/13321)) by [tchebb](https://github.com/tchebb)
|
||||
|
||||
#### Postprocessor changes
|
||||
- **embedthumbnail**: [Fix ffmpeg args for embedding in mp3](https://github.com/yt-dlp/yt-dlp/commit/7e3f48d64d237281a97b3df1a61980c78a0302fe) ([#13720](https://github.com/yt-dlp/yt-dlp/issues/13720)) by [atsushi2965](https://github.com/atsushi2965)
|
||||
- **xattrmetadata**: [Add macOS "Where from" attribute](https://github.com/yt-dlp/yt-dlp/commit/3e918d825d7ff367812658957b281b8cda8f9ebb) ([#12664](https://github.com/yt-dlp/yt-dlp/issues/12664)) by [rolandcrosby](https://github.com/rolandcrosby) (With fixes in [1e0c77d](https://github.com/yt-dlp/yt-dlp/commit/1e0c77ddcce335a1875ecc17d93ed6ff3fabd975) by [seproDev](https://github.com/seproDev))
|
||||
|
||||
#### Networking changes
|
||||
- **Request Handler**
|
||||
- curl_cffi: [Support `curl_cffi` 0.11.x, 0.12.x, 0.13.x](https://github.com/yt-dlp/yt-dlp/commit/e98695549e2eb8ce4a59abe16b5afa8adc075bbe) ([#13989](https://github.com/yt-dlp/yt-dlp/issues/13989)) by [bashonly](https://github.com/bashonly)
|
||||
- requests: [Bump minimum required version of urllib3 to 2.0.2](https://github.com/yt-dlp/yt-dlp/commit/8175f3738fe4db3bc629d36bb72b927d4286d3f9) ([#13939](https://github.com/yt-dlp/yt-dlp/issues/13939)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Misc. changes
|
||||
- **build**: [Use `macos-14` runner for `macos` builds](https://github.com/yt-dlp/yt-dlp/commit/66aa21dc5a3b79059c38f3ad1d05dc9b29187701) ([#13814](https://github.com/yt-dlp/yt-dlp/issues/13814)) by [bashonly](https://github.com/bashonly)
|
||||
- **ci**: [Bump supported PyPy version to 3.11](https://github.com/yt-dlp/yt-dlp/commit/62e2a9c0d55306906f18da2927e05e1cbc31473c) ([#13877](https://github.com/yt-dlp/yt-dlp/issues/13877)) by [bashonly](https://github.com/bashonly)
|
||||
- **cleanup**
|
||||
- [Move embed tests to dedicated extractors](https://github.com/yt-dlp/yt-dlp/commit/1c6068af997cfc0e28061fc00f4d6091e1de57da) ([#13782](https://github.com/yt-dlp/yt-dlp/issues/13782)) by [doe1080](https://github.com/doe1080)
|
||||
- Miscellaneous: [5e4ceb3](https://github.com/yt-dlp/yt-dlp/commit/5e4ceb35cf997af0dbf100e1de37f4e2bcbaa0b7) by [bashonly](https://github.com/bashonly), [injust](https://github.com/injust), [seproDev](https://github.com/seproDev)
|
||||
|
||||
### 2025.07.21
|
||||
|
||||
#### Important changes
|
||||
- **Default behaviour changed from `--mtime` to `--no-mtime`**
|
||||
yt-dlp no longer applies the server modified time to downloaded files by default. [Read more](https://github.com/yt-dlp/yt-dlp/issues/12780)
|
||||
- Security: [[CVE-2025-54072](https://nvd.nist.gov/vuln/detail/CVE-2025-54072)] [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-45hg-7f49-5h56)
|
||||
- When `--exec` is used on Windows, the filepath expanded from `{}` (or the default placeholder) is now properly escaped
|
||||
|
||||
#### Core changes
|
||||
- [Allow extractors to designate formats/subtitles for impersonation](https://github.com/yt-dlp/yt-dlp/commit/32809eb2da92c649e540a5b714f6235036026161) ([#13778](https://github.com/yt-dlp/yt-dlp/issues/13778)) by [bashonly](https://github.com/bashonly) (With fixes in [3e49bc8](https://github.com/yt-dlp/yt-dlp/commit/3e49bc8a1bdb4109b857f2c361c358e86fa63405), [2ac3eb9](https://github.com/yt-dlp/yt-dlp/commit/2ac3eb98373d1c31341c5e918c83872c7ff409c6))
|
||||
- [Don't let format testing alter the return code](https://github.com/yt-dlp/yt-dlp/commit/4919051e447c7f8ae9df8ba5c4208b6b5c04915a) ([#13767](https://github.com/yt-dlp/yt-dlp/issues/13767)) by [bashonly](https://github.com/bashonly)
|
||||
- [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/commit/959ac99e98c3215437e573c22d64be42d361e863) by [Grub4K](https://github.com/Grub4K)
|
||||
- [No longer enable `--mtime` by default](https://github.com/yt-dlp/yt-dlp/commit/f3008bc5f89d2691f2f8dfc51b406ef4e25281c3) ([#12781](https://github.com/yt-dlp/yt-dlp/issues/12781)) by [seproDev](https://github.com/seproDev)
|
||||
- [Warn when skipping formats](https://github.com/yt-dlp/yt-dlp/commit/1f27a9f8baccb9105f2476154557540efe09a937) ([#13090](https://github.com/yt-dlp/yt-dlp/issues/13090)) by [bashonly](https://github.com/bashonly)
|
||||
- **jsinterp**
|
||||
- [Cache undefined variable names](https://github.com/yt-dlp/yt-dlp/commit/b342d27f3f82d913976509ddf5bff539ad8567ec) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly) (With fixes in [805519b](https://github.com/yt-dlp/yt-dlp/commit/805519bfaa7cb5443912dfe45ac774834ba65a16))
|
||||
- [Fix variable scoping](https://github.com/yt-dlp/yt-dlp/commit/b6328ca05030d815222b25d208cc59a964623bf9) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
|
||||
- **utils**
|
||||
- `mimetype2ext`: [Always parse `flac` from `audio/flac`](https://github.com/yt-dlp/yt-dlp/commit/b8abd255e454acbe0023cdb946f9eb461ced7eeb) ([#13748](https://github.com/yt-dlp/yt-dlp/issues/13748)) by [bashonly](https://github.com/bashonly)
|
||||
- `unified_timestamp`: [Return `int` values](https://github.com/yt-dlp/yt-dlp/commit/6be26626f7cfa71d28e0fac2861eb04758810c5d) ([#13796](https://github.com/yt-dlp/yt-dlp/issues/13796)) by [doe1080](https://github.com/doe1080)
|
||||
- `urlhandle_detect_ext`: [Use `x-amz-meta-file-type` headers](https://github.com/yt-dlp/yt-dlp/commit/28bf46b7dafe2e241137763bf570a2f91ba8a53a) ([#13749](https://github.com/yt-dlp/yt-dlp/issues/13749)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Extractor changes
|
||||
- [Add `_search_nextjs_v13_data` helper](https://github.com/yt-dlp/yt-dlp/commit/5245231e4a39ecd5595d4337d46d85e150e2430a) ([#13398](https://github.com/yt-dlp/yt-dlp/issues/13398)) by [bashonly](https://github.com/bashonly) (With fixes in [b5fea53](https://github.com/yt-dlp/yt-dlp/commit/b5fea53f2099bed41ba1b17ab0ac87c8dba5a5ec))
|
||||
- [Detect invalid m3u8 playlist data](https://github.com/yt-dlp/yt-dlp/commit/e99c0b838a9c5feb40c0dcd291bd7b8620b8d36d) ([#13601](https://github.com/yt-dlp/yt-dlp/issues/13601)) by [Grub4K](https://github.com/Grub4K)
|
||||
- **10play**: [Support new site domain](https://github.com/yt-dlp/yt-dlp/commit/790c286ce3e0b534ca2d8f6648ced220d888f139) ([#13611](https://github.com/yt-dlp/yt-dlp/issues/13611)) by [Georift](https://github.com/Georift)
|
||||
- **9gag**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/0b359b184dee0c7052be482857bf562de67e4928) ([#13678](https://github.com/yt-dlp/yt-dlp/issues/13678)) by [bashonly](https://github.com/bashonly)
|
||||
- **aenetworks**: [Support new URL formats](https://github.com/yt-dlp/yt-dlp/commit/5f951ce929b56a822514f1a02cc06af030855ec7) ([#13747](https://github.com/yt-dlp/yt-dlp/issues/13747)) by [bashonly](https://github.com/bashonly)
|
||||
- **archive.org**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d42a6ff0c4ca8893d722ff4e0c109aecbf4cc7cf) ([#13706](https://github.com/yt-dlp/yt-dlp/issues/13706)) by [rdamas](https://github.com/rdamas)
|
||||
- **bandaichannel**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/23e9389f936ec5236a87815b8576e5ce567b2f77) ([#13152](https://github.com/yt-dlp/yt-dlp/issues/13152)) by [doe1080](https://github.com/doe1080)
|
||||
- **bandcamp**: [Extract tags](https://github.com/yt-dlp/yt-dlp/commit/f9dff95cb1c138913011417b3bba020c0a691bba) ([#13480](https://github.com/yt-dlp/yt-dlp/issues/13480)) by [WouterGordts](https://github.com/WouterGordts)
|
||||
- **bellmedia**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/6fb3947c0dc6d0e3eab5077c5bada8402f47a277) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
|
||||
- **bilibili**: [Pass newer user-agent with API requests](https://github.com/yt-dlp/yt-dlp/commit/d3edc5d52a7159eda2331dbc7e14bf40a6585c81) ([#13736](https://github.com/yt-dlp/yt-dlp/issues/13736)) by [c-basalt](https://github.com/c-basalt)
|
||||
- **bilibilibangumi**
|
||||
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b15aa8d77257b86fa44c9a42a615dfe47ac5b3b7) ([#13800](https://github.com/yt-dlp/yt-dlp/issues/13800)) by [bashonly](https://github.com/bashonly)
|
||||
- [Fix geo-block detection](https://github.com/yt-dlp/yt-dlp/commit/884f35d54a64f1e6e7be49459842f573fc3a2701) ([#13667](https://github.com/yt-dlp/yt-dlp/issues/13667)) by [bashonly](https://github.com/bashonly)
|
||||
- **blackboardcollaborate**: [Support subtitles and authwalled videos](https://github.com/yt-dlp/yt-dlp/commit/dcc4cba39e2a79d3efce16afa28dbe245468489f) ([#12473](https://github.com/yt-dlp/yt-dlp/issues/12473)) by [flanter21](https://github.com/flanter21)
|
||||
- **btvplus**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3ae61e0f313dd03a09060abc7a212775c3717818) ([#13541](https://github.com/yt-dlp/yt-dlp/issues/13541)) by [bubo](https://github.com/bubo)
|
||||
- **ctv**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/9f54ea38984788811773ca2ceaca73864acf0e8a) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
|
||||
- **dangalplay**: [Support other login regions](https://github.com/yt-dlp/yt-dlp/commit/09982bc33e2f1f9a1ff66e6738df44f15b36f6a6) ([#13768](https://github.com/yt-dlp/yt-dlp/issues/13768)) by [bashonly](https://github.com/bashonly)
|
||||
- **francetv**: [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/ade876efb31d55d3394185ffc56942fdc8d325cc) ([#13726](https://github.com/yt-dlp/yt-dlp/issues/13726)) by [bashonly](https://github.com/bashonly)
|
||||
- **hotstar**
|
||||
- [Fix support for free accounts](https://github.com/yt-dlp/yt-dlp/commit/07d1d85f6387e4bdb107096f0131c7054f078bb9) ([#13700](https://github.com/yt-dlp/yt-dlp/issues/13700)) by [chauhantirth](https://github.com/chauhantirth)
|
||||
- [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/7e0af2b1f0c3edb688603b022f3a9ca0bfdf75e9) ([#13727](https://github.com/yt-dlp/yt-dlp/issues/13727)) by [bashonly](https://github.com/bashonly) (With fixes in [ef103b2](https://github.com/yt-dlp/yt-dlp/commit/ef103b2d115bd0e880f9cfd2f7dd705f48e4b40d))
|
||||
- **joqrag**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/6d39c420f7774562a106d90253e2ed5b75036321) ([#13152](https://github.com/yt-dlp/yt-dlp/issues/13152)) by [doe1080](https://github.com/doe1080)
|
||||
- **limelight**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/5d693446e882931618c40c99bb593f0b87b30eb9) ([#13267](https://github.com/yt-dlp/yt-dlp/issues/13267)) by [doe1080](https://github.com/doe1080)
|
||||
- **lrtradio**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b4b4486effdcb96bb6b8148171a49ff579b69a4a) ([#13717](https://github.com/yt-dlp/yt-dlp/issues/13717)) by [Pawka](https://github.com/Pawka)
|
||||
- **mir24.tv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/7b4c96e0898db048259ef5fdf12ed14e3605dce3) ([#13651](https://github.com/yt-dlp/yt-dlp/issues/13651)) by [swayll](https://github.com/swayll)
|
||||
- **mixlr**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/0f33950c778331bf4803c76e8b0ba1862df93431) ([#13561](https://github.com/yt-dlp/yt-dlp/issues/13561)) by [seproDev](https://github.com/seproDev), [ShockedPlot7560](https://github.com/ShockedPlot7560)
|
||||
- **mlbtv**: [Make formats downloadable with ffmpeg](https://github.com/yt-dlp/yt-dlp/commit/87e3dc8c7f78929d2ef4f4a44e6a567e04cd8226) ([#13761](https://github.com/yt-dlp/yt-dlp/issues/13761)) by [bashonly](https://github.com/bashonly)
|
||||
- **newspicks**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2aaf1aa71d174700859c9ec1a81109b78e34961c) ([#13612](https://github.com/yt-dlp/yt-dlp/issues/13612)) by [doe1080](https://github.com/doe1080)
|
||||
- **nhkradiru**: [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/7c49a937887756efcfa162abdcf17e48c244cb0c) ([#12708](https://github.com/yt-dlp/yt-dlp/issues/12708)) by [garret1317](https://github.com/garret1317)
|
||||
- **noovo**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/d57a0b5aa78d59324b037d37492fe86aa4fbf58a) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
|
||||
- **patreon**: campaign: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d88b304d44c599d81acfa4231502270c8b9fe2f8) ([#13712](https://github.com/yt-dlp/yt-dlp/issues/13712)) by [bashonly](https://github.com/bashonly)
|
||||
- **playerfm**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1a8474c3ca6dbe51bb153b2b8eef7b9a61fa7dc3) ([#13016](https://github.com/yt-dlp/yt-dlp/issues/13016)) by [R0hanW](https://github.com/R0hanW)
|
||||
- **rai**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/c8329fc572903eeed7edad1642773b2268b71a62) ([#13572](https://github.com/yt-dlp/yt-dlp/issues/13572)) by [moonshinerd](https://github.com/moonshinerd), [seproDev](https://github.com/seproDev)
|
||||
- **raisudtirol**: [Support alternative domain](https://github.com/yt-dlp/yt-dlp/commit/85c3fa1925a9057ef4ae8af682686d5b3eb8e568) ([#13718](https://github.com/yt-dlp/yt-dlp/issues/13718)) by [barsnick](https://github.com/barsnick)
|
||||
- **skeb**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/060c6a4501a0b8a92f1b9c12788f556d902c83c6) ([#13593](https://github.com/yt-dlp/yt-dlp/issues/13593)) by [doe1080](https://github.com/doe1080)
|
||||
- **soundcloud**: [Always extract original format extension](https://github.com/yt-dlp/yt-dlp/commit/c1ac543c8166ff031d62e340b3244ca8556e3fb9) ([#13746](https://github.com/yt-dlp/yt-dlp/issues/13746)) by [bashonly](https://github.com/bashonly)
|
||||
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0b41746964e1d0470ac286ce09408940a3a51147) ([#13610](https://github.com/yt-dlp/yt-dlp/issues/13610)) by [bashonly](https://github.com/bashonly)
|
||||
- **thehighwire**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3a84be9d1660ef798ea28f929a20391bef6afda4) ([#13505](https://github.com/yt-dlp/yt-dlp/issues/13505)) by [swayll](https://github.com/swayll)
|
||||
- **twitch**: [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/422cc8cb2ff2bd3b4c2bc64e23507b7e6f522c35) ([#13618](https://github.com/yt-dlp/yt-dlp/issues/13618)) by [bashonly](https://github.com/bashonly)
|
||||
- **unitednationswebtv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/630f3389c33f0f7f6ec97e8917d20aeb4e4078da) ([#13538](https://github.com/yt-dlp/yt-dlp/issues/13538)) by [averageFOSSenjoyer](https://github.com/averageFOSSenjoyer)
|
||||
- **vimeo**
|
||||
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a5d697f62d8be78ffd472acb2f52c8bc32833003) ([#13692](https://github.com/yt-dlp/yt-dlp/issues/13692)) by [bashonly](https://github.com/bashonly)
|
||||
- [Handle age-restricted videos](https://github.com/yt-dlp/yt-dlp/commit/a6db1d297ab40cc346de24aacbeab93112b2f4e1) ([#13719](https://github.com/yt-dlp/yt-dlp/issues/13719)) by [bashonly](https://github.com/bashonly)
|
||||
- **youtube**
|
||||
- [Do not require PO Token for premium accounts](https://github.com/yt-dlp/yt-dlp/commit/5b57b72c1a7c6bd249ffcebdf5630761ec664c10) ([#13640](https://github.com/yt-dlp/yt-dlp/issues/13640)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Ensure context params are consistent for web clients](https://github.com/yt-dlp/yt-dlp/commit/6e5bee418bc108565108153fd745c8e7a59f16dd) ([#13701](https://github.com/yt-dlp/yt-dlp/issues/13701)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Extract global nsig helper functions](https://github.com/yt-dlp/yt-dlp/commit/fca94ac5d63ed6578b5cd9c8129d97a8a713c39a) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
|
||||
- [Fix subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/0e68332bcb9fba87c42805b7a051eeb2bed36206) ([#13659](https://github.com/yt-dlp/yt-dlp/issues/13659)) by [bashonly](https://github.com/bashonly)
|
||||
- [Log bad playability statuses of player responses](https://github.com/yt-dlp/yt-dlp/commit/aa9f1f4d577e99897ac16cd19d4e217d688ea75d) ([#13647](https://github.com/yt-dlp/yt-dlp/issues/13647)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Use impersonation for downloading subtitles](https://github.com/yt-dlp/yt-dlp/commit/8820101aa3152e5f4811541c645f8b5de231ba8c) ([#13786](https://github.com/yt-dlp/yt-dlp/issues/13786)) by [bashonly](https://github.com/bashonly)
|
||||
- tab: [Fix subscriptions feed extraction](https://github.com/yt-dlp/yt-dlp/commit/c23d837b6524d1e7a4595948871ba1708cba4dfa) ([#13665](https://github.com/yt-dlp/yt-dlp/issues/13665)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Downloader changes
|
||||
- **hls**: [Do not fall back to ffmpeg when native is required](https://github.com/yt-dlp/yt-dlp/commit/a7113722ec33f30fc898caee9242af2b82188a53) ([#13655](https://github.com/yt-dlp/yt-dlp/issues/13655)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Networking changes
|
||||
- **Request Handler**
|
||||
- requests
|
||||
- [Refactor default headers](https://github.com/yt-dlp/yt-dlp/commit/a4561c7a66c39d88efe7ae51e7fa1986faf093fb) ([#13785](https://github.com/yt-dlp/yt-dlp/issues/13785)) by [bashonly](https://github.com/bashonly)
|
||||
- [Work around partial read dropping data](https://github.com/yt-dlp/yt-dlp/commit/c2ff2dbaec7929015373fe002e9bd4849931a4ce) ([#13599](https://github.com/yt-dlp/yt-dlp/issues/13599)) by [Grub4K](https://github.com/Grub4K) (With fixes in [c316416](https://github.com/yt-dlp/yt-dlp/commit/c316416b972d1b05e58fbcc21e80428b900ce102))
|
||||
|
||||
#### Misc. changes
|
||||
- **cleanup**
|
||||
- [Bump ruff to 0.12.x](https://github.com/yt-dlp/yt-dlp/commit/ca5cce5b07d51efe7310b449cdefeca8d873e9df) ([#13596](https://github.com/yt-dlp/yt-dlp/issues/13596)) by [seproDev](https://github.com/seproDev)
|
||||
- Miscellaneous: [9951fdd](https://github.com/yt-dlp/yt-dlp/commit/9951fdd0d08b655cb1af8cd7f32a3fb7e2b1324e) by [adamralph](https://github.com/adamralph), [bashonly](https://github.com/bashonly), [doe1080](https://github.com/doe1080), [hseg](https://github.com/hseg), [InvalidUsernameException](https://github.com/InvalidUsernameException), [seproDev](https://github.com/seproDev)
|
||||
- **devscripts**: [Fix filename/directory Bash completions](https://github.com/yt-dlp/yt-dlp/commit/99093e96fd6a26dea9d6e4bd1e4b16283b6ad1ee) ([#13620](https://github.com/yt-dlp/yt-dlp/issues/13620)) by [barsnick](https://github.com/barsnick)
|
||||
- **test**: download: [Support `playlist_maxcount`](https://github.com/yt-dlp/yt-dlp/commit/fd36b8f31bafbd8096bdb92a446a0c9c6081209c) ([#13433](https://github.com/yt-dlp/yt-dlp/issues/13433)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
|
||||
|
||||
### 2025.06.30
|
||||
|
||||
#### Core changes
|
||||
- **jsinterp**: [Fix `extract_object`](https://github.com/yt-dlp/yt-dlp/commit/958153a226214c86879e36211ac191bf78289578) ([#13580](https://github.com/yt-dlp/yt-dlp/issues/13580)) by [seproDev](https://github.com/seproDev)
|
||||
|
||||
#### Extractor changes
|
||||
- **bilibilispacevideo**: [Extract hidden-mode collections as playlists](https://github.com/yt-dlp/yt-dlp/commit/99b85ac102047446e6adf5b62bfc3c8d80b53778) ([#13533](https://github.com/yt-dlp/yt-dlp/issues/13533)) by [c-basalt](https://github.com/c-basalt)
|
||||
- **hotstar**
|
||||
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b5bd057fe86550f3aa67f2fc8790d1c6a251c57b) ([#13530](https://github.com/yt-dlp/yt-dlp/issues/13530)) by [bashonly](https://github.com/bashonly), [chauhantirth](https://github.com/chauhantirth) (With fixes in [e9f1576](https://github.com/yt-dlp/yt-dlp/commit/e9f157669e24953a88d15ce22053649db7a8e81e) by [bashonly](https://github.com/bashonly))
|
||||
- [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0a6b1044899f452cd10b6c7a6b00fa985a9a8b97) ([#13560](https://github.com/yt-dlp/yt-dlp/issues/13560)) by [bashonly](https://github.com/bashonly)
|
||||
- [Raise for login required](https://github.com/yt-dlp/yt-dlp/commit/5e292baad62c749b6c340621ab2d0f904165ddfb) ([#10405](https://github.com/yt-dlp/yt-dlp/issues/10405)) by [bashonly](https://github.com/bashonly)
|
||||
- series: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4bd9a7ade7e0508b9795b3e72a69eeb40788b62b) ([#13564](https://github.com/yt-dlp/yt-dlp/issues/13564)) by [bashonly](https://github.com/bashonly)
|
||||
- **jiocinema**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/7e2504f941a11ea2b0dba00de3f0295cdc253e79) ([#13565](https://github.com/yt-dlp/yt-dlp/issues/13565)) by [bashonly](https://github.com/bashonly)
|
||||
- **kick**: [Support subscriber-only content](https://github.com/yt-dlp/yt-dlp/commit/b16722ede83377f77ea8352dcd0a6ca8e83b8f0f) ([#13550](https://github.com/yt-dlp/yt-dlp/issues/13550)) by [helpimnotdrowning](https://github.com/helpimnotdrowning)
|
||||
- **niconico**: live: [Fix extractor and downloader](https://github.com/yt-dlp/yt-dlp/commit/06c1a8cdffe14050206683253726875144192ef5) ([#13158](https://github.com/yt-dlp/yt-dlp/issues/13158)) by [doe1080](https://github.com/doe1080)
|
||||
- **sauceplus**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/35fc33fbc51c7f5392fb2300f65abf6cf107ef90) ([#13567](https://github.com/yt-dlp/yt-dlp/issues/13567)) by [bashonly](https://github.com/bashonly), [ceandreasen](https://github.com/ceandreasen)
|
||||
- **sproutvideo**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/11b9416e10cff7513167d76d6c47774fcdd3e26a) ([#13589](https://github.com/yt-dlp/yt-dlp/issues/13589)) by [bashonly](https://github.com/bashonly)
|
||||
- **youtube**: [Fix premium formats extraction](https://github.com/yt-dlp/yt-dlp/commit/2ba5391cd68ed4f2415c827d2cecbcbc75ace10b) ([#13586](https://github.com/yt-dlp/yt-dlp/issues/13586)) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
#### Misc. changes
|
||||
- **ci**: [Add signature tests](https://github.com/yt-dlp/yt-dlp/commit/1b883846347addeab12663fd74317fd544341a1c) ([#13582](https://github.com/yt-dlp/yt-dlp/issues/13582)) by [bashonly](https://github.com/bashonly)
|
||||
- **cleanup**: Miscellaneous: [b018784](https://github.com/yt-dlp/yt-dlp/commit/b0187844988e557c7e1e6bb1aabd4c1176768d86) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
### 2025.06.25
|
||||
|
||||
#### Extractor changes
|
||||
|
||||
39
README.md
39
README.md
@@ -106,12 +106,14 @@ #### Alternatives
|
||||
File|Description
|
||||
:---|:---
|
||||
[yt-dlp_x86.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_x86.exe)|Windows (Win8+) standalone x86 (32-bit) binary
|
||||
[yt-dlp_arm64.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_arm64.exe)|Windows (Win10+) standalone arm64 (64-bit) binary
|
||||
[yt-dlp_linux](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux)|Linux standalone x64 binary
|
||||
[yt-dlp_linux_armv7l](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux_armv7l)|Linux standalone armv7l (32-bit) binary
|
||||
[yt-dlp_linux_aarch64](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux_aarch64)|Linux standalone aarch64 (64-bit) binary
|
||||
[yt-dlp_win.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win.zip)|Unpackaged Windows executable (no auto-update)
|
||||
[yt-dlp_win.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win.zip)|Unpackaged Windows (Win8+) x64 executable (no auto-update)
|
||||
[yt-dlp_win_x86.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win_x86.zip)|Unpackaged Windows (Win8+) x86 executable (no auto-update)
|
||||
[yt-dlp_win_arm64.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win_arm64.zip)|Unpackaged Windows (Win10+) arm64 executable (no auto-update)
|
||||
[yt-dlp_macos.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos.zip)|Unpackaged MacOS (10.15+) executable (no auto-update)
|
||||
[yt-dlp_macos_legacy](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos_legacy)|MacOS (10.9+) standalone x64 executable
|
||||
|
||||
#### Misc
|
||||
|
||||
@@ -171,8 +173,11 @@ # To install nightly with pip:
|
||||
python3 -m pip install -U --pre "yt-dlp[default]"
|
||||
```
|
||||
|
||||
When running a yt-dlp version that is older than 90 days, you will see a warning message suggesting to update to the latest version.
|
||||
You can suppress this warning by adding `--no-update` to your command or configuration file.
|
||||
|
||||
## DEPENDENCIES
|
||||
Python versions 3.9+ (CPython) and 3.10+ (PyPy) are supported. Other versions and implementations may or may not work correctly.
|
||||
Python versions 3.9+ (CPython) and 3.11+ (PyPy) are supported. Other versions and implementations may or may not work correctly.
|
||||
|
||||
<!-- Python 3.5+ uses VC++14 and it is already embedded in the binary created
|
||||
<!x-- https://www.microsoft.com/en-us/download/details.aspx?id=26999 --x>
|
||||
@@ -208,7 +213,7 @@ ### Metadata
|
||||
|
||||
* [**mutagen**](https://github.com/quodlibet/mutagen)\* - For `--embed-thumbnail` in certain formats. Licensed under [GPLv2+](https://github.com/quodlibet/mutagen/blob/master/COPYING)
|
||||
* [**AtomicParsley**](https://github.com/wez/atomicparsley) - For `--embed-thumbnail` in `mp4`/`m4a` files when `mutagen`/`ffmpeg` cannot. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING)
|
||||
* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattr`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
|
||||
* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattrs`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
|
||||
|
||||
### Misc
|
||||
|
||||
@@ -277,7 +282,7 @@ # USAGE AND OPTIONS
|
||||
<!-- MANPAGE: BEGIN EXCLUDED SECTION -->
|
||||
yt-dlp [OPTIONS] [--] URL [URL...]
|
||||
|
||||
`Ctrl+F` is your friend :D
|
||||
Tip: Use `CTRL`+`F` (or `Command`+`F`) to search by keywords
|
||||
<!-- MANPAGE: END EXCLUDED SECTION -->
|
||||
|
||||
<!-- Auto generated -->
|
||||
@@ -639,9 +644,9 @@ ## Filesystem Options:
|
||||
--no-part Do not use .part files - write directly into
|
||||
output file
|
||||
--mtime Use the Last-modified header to set the file
|
||||
modification time (default)
|
||||
modification time
|
||||
--no-mtime Do not use the Last-modified header to set
|
||||
the file modification time
|
||||
the file modification time (default)
|
||||
--write-description Write video description to a .description file
|
||||
--no-write-description Do not write video description (default)
|
||||
--write-info-json Write video metadata to a .info.json file
|
||||
@@ -1156,15 +1161,15 @@ # CONFIGURATION
|
||||
* `/etc/yt-dlp/config`
|
||||
* `/etc/yt-dlp/config.txt`
|
||||
|
||||
E.g. with the following configuration file, yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
|
||||
E.g. with the following configuration file, yt-dlp will always extract the audio, copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
|
||||
```
|
||||
# Lines starting with # are comments
|
||||
|
||||
# Always extract audio
|
||||
-x
|
||||
|
||||
# Do not copy the mtime
|
||||
--no-mtime
|
||||
# Copy the mtime
|
||||
--mtime
|
||||
|
||||
# Use this proxy
|
||||
--proxy 127.0.0.1:3128
|
||||
@@ -1797,10 +1802,11 @@ # EXTRACTOR ARGUMENTS
|
||||
#### youtube
|
||||
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube/_base.py](https://github.com/yt-dlp/yt-dlp/blob/415b4c9f955b1a0391204bd24a7132590e7b3bdb/yt_dlp/extractor/youtube/_base.py#L402-L409) for the list of supported content language codes
|
||||
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
|
||||
* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
|
||||
* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv_simply,tv,web` is used, but `tv,web_safari,web` is used when authenticating with cookies and `tv,web_creator,web` is used with premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
|
||||
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
|
||||
* `webpage_skip`: Skip extraction of embedded webpage data. One or both of `player_response`, `initial_data`. These options are for testing purposes and don't skip any network requests
|
||||
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
|
||||
* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`
|
||||
* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. The default is `main`, and the others are for debugging purposes. You can use `actual` to go with what is prescribed by the site
|
||||
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
|
||||
* `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all`
|
||||
* E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
|
||||
@@ -1813,6 +1819,7 @@ #### youtube
|
||||
* `po_token`: Proof of Origin (PO) Token(s) to use. Comma seperated list of PO Tokens in the format `CLIENT.CONTEXT+PO_TOKEN`, e.g. `youtube:po_token=web.gvs+XXX,web.player=XXX,web_safari.gvs+YYY`. Context can be any of `gvs` (Google Video Server URLs), `player` (Innertube player request) or `subs` (Subtitles)
|
||||
* `pot_trace`: Enable debug logging for PO Token fetching. Either `true` or `false` (default)
|
||||
* `fetch_pot`: Policy to use for fetching a PO Token from providers. One of `always` (always try fetch a PO Token regardless if the client requires one for the given context), `never` (never fetch a PO Token), or `auto` (default; only fetch a PO Token if the client requires one for the given context)
|
||||
* `playback_wait`: Duration (in seconds) to wait inbetween the extraction and download stages in order to ensure the formats are available. The default is `6` seconds
|
||||
|
||||
#### youtubepot-webpo
|
||||
* `bind_to_visitor_id`: Whether to use the Visitor ID instead of Visitor Data for caching WebPO tokens. Either `true` (default) or `false`
|
||||
@@ -1900,6 +1907,10 @@ #### sonylivseries
|
||||
#### tver
|
||||
* `backend`: Backend API to use for extraction - one of `streaks` (default) or `brightcove` (deprecated)
|
||||
|
||||
#### vimeo
|
||||
* `client`: Client to extract video data from. The currently available clients are `android`, `ios`, and `web`. Only one client can be used. The `web` client is used by default. The `web` client only works with account cookies or login credentials. The `android` and `ios` clients only work with previously cached OAuth tokens
|
||||
* `original_format_policy`: Policy for when to try extracting original formats. One of `always`, `never`, or `auto`. The default `auto` policy tries to avoid exceeding the web client's API rate-limit by only making an extra request when Vimeo publicizes the video's downloadability
|
||||
|
||||
**Note**: These options may be changed/removed in the future without concern for backward compatibility
|
||||
|
||||
<!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
|
||||
@@ -2262,6 +2273,7 @@ ### Differences in default behavior
|
||||
* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
|
||||
* The sub-modules `swfinterp`, `casefold` are removed.
|
||||
* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
|
||||
* yt-dlp no longer applies the server modified time to downloaded files by default. Use `--mtime` or `--compat-options mtime-by-default` to revert this.
|
||||
|
||||
For ease of use, a few more compat options are available:
|
||||
|
||||
@@ -2271,7 +2283,7 @@ ### Differences in default behavior
|
||||
* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization`
|
||||
* `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
|
||||
* `--compat-options 2023`: Same as `--compat-options 2024,prefer-vp9-sort`
|
||||
* `--compat-options 2024`: Currently does nothing. Use this to enable all future compat options
|
||||
* `--compat-options 2024`: Same as `--compat-options mtime-by-default`. Use this to enable all future compat options
|
||||
|
||||
The following compat options restore vulnerable behavior from before security patches:
|
||||
|
||||
@@ -2361,7 +2373,6 @@ #### Old aliases
|
||||
--dump-headers --print-traffic
|
||||
--dump-intermediate-pages --dump-pages
|
||||
--force-write-download-archive --force-write-archive
|
||||
--load-info --load-info-json
|
||||
--no-clean-infojson --no-clean-info-json
|
||||
--no-split-tracks --no-split-chapters
|
||||
--no-write-srt --no-write-subs
|
||||
|
||||
@@ -62,16 +62,22 @@ def parse_options():
|
||||
|
||||
def exe(onedir):
|
||||
"""@returns (name, path)"""
|
||||
platform_name, machine, extension = {
|
||||
'win32': (None, MACHINE, '.exe'),
|
||||
'darwin': ('macos', None, None),
|
||||
}.get(OS_NAME, (OS_NAME, MACHINE, None))
|
||||
|
||||
name = '_'.join(filter(None, (
|
||||
'yt-dlp',
|
||||
{'win32': '', 'darwin': 'macos'}.get(OS_NAME, OS_NAME),
|
||||
MACHINE,
|
||||
platform_name,
|
||||
machine,
|
||||
)))
|
||||
|
||||
return name, ''.join(filter(None, (
|
||||
'dist/',
|
||||
onedir and f'{name}/',
|
||||
name,
|
||||
OS_NAME == 'win32' and '.exe',
|
||||
extension,
|
||||
)))
|
||||
|
||||
|
||||
|
||||
@@ -6,13 +6,17 @@ __yt_dlp()
|
||||
prev="${COMP_WORDS[COMP_CWORD-1]}"
|
||||
opts="{{flags}}"
|
||||
keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
|
||||
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
|
||||
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info-json"
|
||||
diropts="--cache-dir"
|
||||
|
||||
if [[ ${prev} =~ ${fileopts} ]]; then
|
||||
local IFS=$'\n'
|
||||
type compopt &>/dev/null && compopt -o filenames
|
||||
COMPREPLY=( $(compgen -f -- ${cur}) )
|
||||
return 0
|
||||
elif [[ ${prev} =~ ${diropts} ]]; then
|
||||
local IFS=$'\n'
|
||||
type compopt &>/dev/null && compopt -o dirnames
|
||||
COMPREPLY=( $(compgen -d -- ${cur}) )
|
||||
return 0
|
||||
fi
|
||||
|
||||
@@ -254,5 +254,44 @@
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "d596824c2f8428362c072518856065070616e348"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "7b81634fb1d15999757e7a9883daa6ef09ea785b"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "500761e41acb96953a5064e951d41d190c287e46"
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "f3008bc5f89d2691f2f8dfc51b406ef4e25281c3",
|
||||
"short": "[priority] **Default behaviour changed from `--mtime` to `--no-mtime`**\nyt-dlp no longer applies the server modified time to downloaded files by default. [Read more](https://github.com/yt-dlp/yt-dlp/issues/12780)"
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "959ac99e98c3215437e573c22d64be42d361e863",
|
||||
"short": "[priority] Security: [[CVE-2025-54072](https://nvd.nist.gov/vuln/detail/CVE-2025-54072)] [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-45hg-7f49-5h56)\n - When `--exec` is used on Windows, the filepath expanded from `{}` (or the default placeholder) is now properly escaped"
|
||||
},
|
||||
{
|
||||
"action": "change",
|
||||
"when": "b831406a1d3be34c159835079d12bae624c43610",
|
||||
"short": "[ie/rtve.es:program] Add extractor (#12955)",
|
||||
"authors": ["meGAmeS1", "seproDev"]
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "23c658b9cbe34a151f8f921ab1320bb5d4e40a4d",
|
||||
"short": "[priority] **The minimum *recommended* Python version has been raised to 3.10**\nSince Python 3.9 will reach end-of-life in October 2025, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13858)"
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "cc5a5caac5fbc0d605b52bde0778d6fd5f97b5ab",
|
||||
"short": "[priority] **darwin_legacy_exe builds are being discontinued**\nThis release's `yt-dlp_macos_legacy` binary will likely be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13856)"
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "c76ce28e06c816eb5b261dfb6aff6e69dd9b7382",
|
||||
"short": "[priority] **linux_armv7l_exe builds are being discontinued**\nThis release's `yt-dlp_linux_armv7l` binary could be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13976)"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -20,6 +20,7 @@ def parse_patched_options(opts):
|
||||
'fragment_retries': 0,
|
||||
'extract_flat': False,
|
||||
'concat_playlist': 'never',
|
||||
'update_self': False,
|
||||
})
|
||||
yt_dlp.options.create_parser = lambda: patched_parser
|
||||
try:
|
||||
|
||||
@@ -15,11 +15,11 @@ description = "A feature-rich command-line audio/video downloader"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.9"
|
||||
keywords = [
|
||||
"cli",
|
||||
"downloader",
|
||||
"youtube-dl",
|
||||
"video-downloader",
|
||||
"youtube-downloader",
|
||||
"sponsorblock",
|
||||
"youtube-dlc",
|
||||
"yt-dlp",
|
||||
]
|
||||
license = {file = "LICENSE"}
|
||||
@@ -51,11 +51,11 @@ default = [
|
||||
"mutagen",
|
||||
"pycryptodomex",
|
||||
"requests>=2.32.2,<3",
|
||||
"urllib3>=1.26.17,<3",
|
||||
"urllib3>=2.0.2,<3",
|
||||
"websockets>=13.0",
|
||||
]
|
||||
curl-cffi = [
|
||||
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.11; implementation_name=='cpython'",
|
||||
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.14; implementation_name=='cpython'",
|
||||
]
|
||||
secretstorage = [
|
||||
"cffi",
|
||||
@@ -75,7 +75,7 @@ dev = [
|
||||
]
|
||||
static-analysis = [
|
||||
"autopep8~=2.0",
|
||||
"ruff~=0.11.0",
|
||||
"ruff~=0.12.0",
|
||||
]
|
||||
test = [
|
||||
"pytest~=8.1",
|
||||
@@ -210,10 +210,12 @@ ignore = [
|
||||
"TD001", # invalid-todo-tag
|
||||
"TD002", # missing-todo-author
|
||||
"TD003", # missing-todo-link
|
||||
"PLC0415", # import-outside-top-level
|
||||
"PLE0604", # invalid-all-object (false positives)
|
||||
"PLE0643", # potential-index-error (false positives)
|
||||
"PLW0603", # global-statement
|
||||
"PLW1510", # subprocess-run-without-check
|
||||
"PLW1641", # eq-without-hash
|
||||
"PLW2901", # redefined-loop-name
|
||||
"RUF001", # ambiguous-unicode-character-string
|
||||
"RUF012", # mutable-class-default
|
||||
@@ -313,6 +315,7 @@ banned-from = [
|
||||
"yt_dlp.utils.error_to_compat_str".msg = "Use `str` instead."
|
||||
"yt_dlp.utils.bytes_to_intlist".msg = "Use `list` instead."
|
||||
"yt_dlp.utils.intlist_to_bytes".msg = "Use `bytes` instead."
|
||||
"yt_dlp.utils.jwt_encode_hs256".msg = "Use `yt_dlp.utils.jwt_encode` instead."
|
||||
"yt_dlp.utils.decodeArgument".msg = "Do not use"
|
||||
"yt_dlp.utils.decodeFilename".msg = "Do not use"
|
||||
"yt_dlp.utils.encodeFilename".msg = "Do not use"
|
||||
|
||||
@@ -16,7 +16,7 @@ remove-unused-variables = true
|
||||
|
||||
[tox:tox]
|
||||
skipsdist = true
|
||||
envlist = py{39,310,311,312,313},pypy310
|
||||
envlist = py{39,310,311,312,313},pypy311
|
||||
skip_missing_interpreters = true
|
||||
|
||||
[testenv] # tox
|
||||
|
||||
@@ -12,7 +12,7 @@ # Supported sites
|
||||
- **17live:vod**
|
||||
- **1News**: 1news.co.nz article videos
|
||||
- **1tv**: Первый канал
|
||||
- **20min**
|
||||
- **20min**: (**Currently broken**)
|
||||
- **23video**
|
||||
- **247sports**: (**Currently broken**)
|
||||
- **24tv.ua**
|
||||
@@ -45,10 +45,6 @@ # Supported sites
|
||||
- **ADNSeason**: [*animationdigitalnetwork*](## "netrc machine") Animation Digital Network
|
||||
- **AdobeConnect**
|
||||
- **adobetv**
|
||||
- **adobetv:channel**
|
||||
- **adobetv:embed**
|
||||
- **adobetv:show**
|
||||
- **adobetv:video**
|
||||
- **AdultSwim**
|
||||
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
|
||||
- **aenetworks:collection**
|
||||
@@ -100,7 +96,6 @@ # Supported sites
|
||||
- **ARD**
|
||||
- **ARDMediathek**
|
||||
- **ARDMediathekCollection**
|
||||
- **Arkena**
|
||||
- **Art19**
|
||||
- **Art19Show**
|
||||
- **arte.sky.it**
|
||||
@@ -133,7 +128,6 @@ # Supported sites
|
||||
- **BaiduVideo**: 百度视频
|
||||
- **BanBye**
|
||||
- **BanByeChannel**
|
||||
- **bandaichannel**
|
||||
- **Bandcamp**
|
||||
- **Bandcamp:album**
|
||||
- **Bandcamp:user**
|
||||
@@ -156,10 +150,8 @@ # Supported sites
|
||||
- **Beatport**
|
||||
- **Beeg**
|
||||
- **BehindKink**: (**Currently broken**)
|
||||
- **Bellator**
|
||||
- **BellMedia**
|
||||
- **BerufeTV**
|
||||
- **Bet**: (**Currently broken**)
|
||||
- **Bet**
|
||||
- **bfi:player**: (**Currently broken**)
|
||||
- **bfmtv**
|
||||
- **bfmtv:article**
|
||||
@@ -197,6 +189,7 @@ # Supported sites
|
||||
- **BitChute**
|
||||
- **BitChuteChannel**
|
||||
- **BlackboardCollaborate**
|
||||
- **BlackboardCollaborateLaunch**
|
||||
- **BleacherReport**: (**Currently broken**)
|
||||
- **BleacherReportCMS**: (**Currently broken**)
|
||||
- **blerp**
|
||||
@@ -225,6 +218,7 @@ # Supported sites
|
||||
- **Brilliantpala:Elearn**: [*brilliantpala*](## "netrc machine") VoD on elearn.brilliantpala.org
|
||||
- **bt:article**: Bergens Tidende Articles
|
||||
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
|
||||
- **BTVPlus**
|
||||
- **Bundesliga**
|
||||
- **Bundestag**
|
||||
- **BunnyCdn**
|
||||
@@ -285,18 +279,15 @@ # Supported sites
|
||||
- **Clipchamp**
|
||||
- **Clippit**
|
||||
- **ClipRs**: (**Currently broken**)
|
||||
- **ClipYouEmbed**
|
||||
- **CloserToTruth**: (**Currently broken**)
|
||||
- **CloudflareStream**
|
||||
- **CloudyCDN**
|
||||
- **Clubic**: (**Currently broken**)
|
||||
- **Clyp**
|
||||
- **cmt.com**: (**Currently broken**)
|
||||
- **CNBCVideo**
|
||||
- **CNN**
|
||||
- **CNNIndonesia**
|
||||
- **ComedyCentral**
|
||||
- **ComedyCentralTV**
|
||||
- **ConanClassic**: (**Currently broken**)
|
||||
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
|
||||
- **CONtv**
|
||||
@@ -317,7 +308,6 @@ # Supported sites
|
||||
- **CSpan**: C-SPAN
|
||||
- **CSpanCongress**
|
||||
- **CtsNews**: 華視新聞
|
||||
- **CTV**
|
||||
- **CTVNews**
|
||||
- **cu.ntv.co.jp**: 日テレ無料TADA!
|
||||
- **CultureUnplugged**
|
||||
@@ -397,7 +387,6 @@ # Supported sites
|
||||
- **dw:article**: (**Currently broken**)
|
||||
- **dzen.ru**: Дзен (dzen) formerly Яндекс.Дзен (Yandex Zen)
|
||||
- **dzen.ru:channel**
|
||||
- **EaglePlatform**
|
||||
- **EbaumsWorld**
|
||||
- **Ebay**
|
||||
- **egghead:course**: egghead.io course
|
||||
@@ -448,6 +437,8 @@ # Supported sites
|
||||
- **fancode:live**: [*fancode*](## "netrc machine") (**Currently broken**)
|
||||
- **fancode:vod**: [*fancode*](## "netrc machine") (**Currently broken**)
|
||||
- **Fathom**
|
||||
- **Faulio**
|
||||
- **FaulioLive**
|
||||
- **faz.net**
|
||||
- **fc2**: [*fc2*](## "netrc machine")
|
||||
- **fc2:embed**
|
||||
@@ -575,9 +566,7 @@ # Supported sites
|
||||
- **HollywoodReporterPlaylist**
|
||||
- **Holodex**
|
||||
- **HotNewHipHop**: (**Currently broken**)
|
||||
- **hotstar**
|
||||
- **hotstar:playlist**
|
||||
- **hotstar:season**
|
||||
- **hotstar**: JioHotstar
|
||||
- **hotstar:series**
|
||||
- **hrfernsehen**
|
||||
- **HRTi**: [*hrti*](## "netrc machine")
|
||||
@@ -647,8 +636,6 @@ # Supported sites
|
||||
- **Jamendo**
|
||||
- **JamendoAlbum**
|
||||
- **JeuxVideo**: (**Currently broken**)
|
||||
- **jiocinema**: [*jiocinema*](## "netrc machine")
|
||||
- **jiocinema:series**: [*jiocinema*](## "netrc machine")
|
||||
- **jiosaavn:album**
|
||||
- **jiosaavn:artist**
|
||||
- **jiosaavn:playlist**
|
||||
@@ -656,7 +643,6 @@ # Supported sites
|
||||
- **jiosaavn:show:playlist**
|
||||
- **jiosaavn:song**
|
||||
- **Joj**
|
||||
- **JoqrAg**: 超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)
|
||||
- **Jove**
|
||||
- **JStream**
|
||||
- **JTBC**: jtbc.co.kr
|
||||
@@ -707,8 +693,8 @@ # Supported sites
|
||||
- **lbry:channel**: odysee.com channels
|
||||
- **lbry:playlist**: odysee.com playlists
|
||||
- **LCI**
|
||||
- **Lcp**
|
||||
- **LcpPlay**
|
||||
- **Lcp**: (**Currently broken**)
|
||||
- **LcpPlay**: (**Currently broken**)
|
||||
- **Le**: 乐视网
|
||||
- **LearningOnScreen**
|
||||
- **Lecture2Go**: (**Currently broken**)
|
||||
@@ -727,9 +713,6 @@ # Supported sites
|
||||
- **life:embed**
|
||||
- **likee**
|
||||
- **likee:user**
|
||||
- **limelight**
|
||||
- **limelight:channel**
|
||||
- **limelight:channel_list**
|
||||
- **LinkedIn**: [*linkedin*](## "netrc machine")
|
||||
- **linkedin:events**: [*linkedin*](## "netrc machine")
|
||||
- **linkedin:learning**: [*linkedin*](## "netrc machine")
|
||||
@@ -737,7 +720,7 @@ # Supported sites
|
||||
- **Liputan6**
|
||||
- **ListenNotes**
|
||||
- **LiTV**
|
||||
- **LiveJournal**
|
||||
- **LiveJournal**: (**Currently broken**)
|
||||
- **livestream**
|
||||
- **livestream:original**
|
||||
- **Livestreamfails**
|
||||
@@ -811,6 +794,7 @@ # Supported sites
|
||||
- **minds:channel**
|
||||
- **minds:group**
|
||||
- **Minoto**
|
||||
- **mir24.tv**
|
||||
- **mirrativ**
|
||||
- **mirrativ:user**
|
||||
- **MirrorCoUK**
|
||||
@@ -821,6 +805,8 @@ # Supported sites
|
||||
- **mixcloud**
|
||||
- **mixcloud:playlist**
|
||||
- **mixcloud:user**
|
||||
- **Mixlr**
|
||||
- **MixlrRecoring**
|
||||
- **MLB**
|
||||
- **MLBArticle**
|
||||
- **MLBTV**: [*mlb*](## "netrc machine")
|
||||
@@ -847,12 +833,6 @@ # Supported sites
|
||||
- **MSN**
|
||||
- **mtg**: MTG services
|
||||
- **mtv**
|
||||
- **mtv.de**: (**Currently broken**)
|
||||
- **mtv.it**
|
||||
- **mtv.it:programma**
|
||||
- **mtv:video**
|
||||
- **mtvjapan**
|
||||
- **mtvservices:embedded**
|
||||
- **MTVUutisetArticle**: (**Currently broken**)
|
||||
- **MuenchenTV**: münchen.tv (**Currently broken**)
|
||||
- **MujRozhlas**
|
||||
@@ -952,9 +932,6 @@ # Supported sites
|
||||
- **NhkVodProgram**
|
||||
- **nhl.com**
|
||||
- **nick.com**
|
||||
- **nick.de**
|
||||
- **nickelodeon:br**
|
||||
- **nickelodeonru**
|
||||
- **niconico**: [*niconico*](## "netrc machine") ニコニコ動画
|
||||
- **niconico:history**: NicoNico user history or likes. Requires cookies.
|
||||
- **niconico:live**: [*niconico*](## "netrc machine") ニコニコ生放送
|
||||
@@ -977,7 +954,6 @@ # Supported sites
|
||||
- **NoicePodcast**
|
||||
- **NonkTube**
|
||||
- **NoodleMagazine**
|
||||
- **Noovo**
|
||||
- **NOSNLArticle**
|
||||
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
|
||||
- **NovaEmbed**
|
||||
@@ -1057,13 +1033,12 @@ # Supported sites
|
||||
- **Panopto**
|
||||
- **PanoptoList**
|
||||
- **PanoptoPlaylist**
|
||||
- **ParamountNetwork**
|
||||
- **ParamountPlus**
|
||||
- **ParamountPlusSeries**
|
||||
- **ParamountPressExpress**
|
||||
- **Parler**: Posts on parler.com
|
||||
- **parliamentlive.tv**: UK parliament videos
|
||||
- **Parlview**: (**Currently broken**)
|
||||
- **Parlview**
|
||||
- **parti:livestream**
|
||||
- **parti:video**
|
||||
- **patreon**
|
||||
@@ -1096,11 +1071,11 @@ # Supported sites
|
||||
- **PiramideTVChannel**
|
||||
- **pixiv:sketch**
|
||||
- **pixiv:sketch:user**
|
||||
- **Pladform**
|
||||
- **PlanetMarathi**
|
||||
- **Platzi**: [*platzi*](## "netrc machine")
|
||||
- **PlatziCourse**: [*platzi*](## "netrc machine")
|
||||
- **player.sky.it**
|
||||
- **PlayerFm**
|
||||
- **playeur**
|
||||
- **PlayPlusTV**: [*playplustv*](## "netrc machine")
|
||||
- **PlaySuisse**: [*playsuisse*](## "netrc machine")
|
||||
@@ -1111,6 +1086,7 @@ # Supported sites
|
||||
- **pluralsight:course**
|
||||
- **PlutoTV**: (**Currently broken**)
|
||||
- **PlVideo**: Платформа
|
||||
- **PlyrEmbed**
|
||||
- **PodbayFM**
|
||||
- **PodbayFMChannel**
|
||||
- **Podchaser**
|
||||
@@ -1264,6 +1240,7 @@ # Supported sites
|
||||
- **rtve.es:alacarta**: RTVE a la carta and Play
|
||||
- **rtve.es:audio**: RTVE audio
|
||||
- **rtve.es:live**: RTVE.es live streams
|
||||
- **rtve.es:program**: RTVE.es programs
|
||||
- **rtve.es:television**
|
||||
- **rtvslo.si**
|
||||
- **rtvslo.si:show**
|
||||
@@ -1281,7 +1258,7 @@ # Supported sites
|
||||
- **rutube:playlist**: Rutube playlists
|
||||
- **rutube:tags**: Rutube tags
|
||||
- **RUTV**: RUTV.RU
|
||||
- **Ruutu**
|
||||
- **Ruutu**: (**Currently broken**)
|
||||
- **Ruv**
|
||||
- **ruv.is:spila**
|
||||
- **S4C**
|
||||
@@ -1299,6 +1276,7 @@ # Supported sites
|
||||
- **SampleFocus**
|
||||
- **Sangiin**: 参議院インターネット審議中継 (archive)
|
||||
- **Sapo**: SAPO Vídeos
|
||||
- **SaucePlus**: Sauce+
|
||||
- **SBS**: sbs.com.au
|
||||
- **sbs.co.kr**
|
||||
- **sbs.co.kr:allvod_program**
|
||||
@@ -1331,6 +1309,7 @@ # Supported sites
|
||||
- **SharePoint**
|
||||
- **ShareVideosEmbed**
|
||||
- **ShemarooMe**
|
||||
- **Shiey**
|
||||
- **ShowRoomLive**
|
||||
- **ShugiinItvLive**: 衆議院インターネット審議中継
|
||||
- **ShugiinItvLiveRoom**: 衆議院インターネット審議中継 (中継)
|
||||
@@ -1380,15 +1359,16 @@ # Supported sites
|
||||
- **southpark.cc.com:español**
|
||||
- **southpark.de**
|
||||
- **southpark.lat**
|
||||
- **southpark.nl**
|
||||
- **southparkstudios.dk**
|
||||
- **southparkstudios.co.uk**
|
||||
- **southparkstudios.com.br**
|
||||
- **southparkstudios.nu**
|
||||
- **SovietsCloset**
|
||||
- **SovietsClosetPlaylist**
|
||||
- **SpankBang**
|
||||
- **SpankBangPlaylist**
|
||||
- **Spiegel**
|
||||
- **Sport5**
|
||||
- **SportBox**
|
||||
- **SportBox**: (**Currently broken**)
|
||||
- **SportDeutschland**
|
||||
- **spotify**: Spotify episodes (**Currently broken**)
|
||||
- **spotify:show**: Spotify shows (**Currently broken**)
|
||||
@@ -1406,6 +1386,7 @@ # Supported sites
|
||||
- **startrek**: STAR TREK
|
||||
- **startv**
|
||||
- **Steam**
|
||||
- **SteamCommunity**
|
||||
- **SteamCommunityBroadcast**
|
||||
- **Stitcher**
|
||||
- **StitcherShow**
|
||||
@@ -1475,11 +1456,12 @@ # Supported sites
|
||||
- **Tempo**
|
||||
- **TennisTV**: [*tennistv*](## "netrc machine")
|
||||
- **TF1**
|
||||
- **TFO**
|
||||
- **TFO**: (**Currently broken**)
|
||||
- **theatercomplextown:ppv**: [*theatercomplextown*](## "netrc machine")
|
||||
- **theatercomplextown:vod**: [*theatercomplextown*](## "netrc machine")
|
||||
- **TheGuardianPodcast**
|
||||
- **TheGuardianPodcastPlaylist**
|
||||
- **TheHighWire**
|
||||
- **TheHoleTv**
|
||||
- **TheIntercept**
|
||||
- **ThePlatform**
|
||||
@@ -1528,7 +1510,6 @@ # Supported sites
|
||||
- **TrueID**
|
||||
- **TruNews**
|
||||
- **Truth**
|
||||
- **TruTV**
|
||||
- **Tube8**: (**Currently broken**)
|
||||
- **TubeTuGraz**: [*tubetugraz*](## "netrc machine") tube.tugraz.at
|
||||
- **TubeTuGrazSeries**: [*tubetugraz*](## "netrc machine")
|
||||
@@ -1547,8 +1528,8 @@ # Supported sites
|
||||
- **tv2playseries.hu**
|
||||
- **TV4**: tv4.se and tv4play.se
|
||||
- **TV5MONDE**
|
||||
- **tv5unis**
|
||||
- **tv5unis:video**
|
||||
- **tv5unis**: (**Currently broken**)
|
||||
- **tv5unis:video**: (**Currently broken**)
|
||||
- **tv8.it**
|
||||
- **tv8.it:live**: TV8 Live
|
||||
- **tv8.it:playlist**: TV8 Playlist
|
||||
@@ -1560,7 +1541,6 @@ # Supported sites
|
||||
- **TVer**
|
||||
- **tvigle**: Интернет-телевидение Tvigle.ru
|
||||
- **TVIPlayer**
|
||||
- **tvland.com**
|
||||
- **TVN24**: (**Currently broken**)
|
||||
- **TVNoe**: (**Currently broken**)
|
||||
- **tvopengr:embed**: tvopen.gr embedded videos
|
||||
@@ -1573,6 +1553,7 @@ # Supported sites
|
||||
- **TVPlayer**
|
||||
- **TVPlayHome**
|
||||
- **tvw**
|
||||
- **tvw:news**
|
||||
- **tvw:tvchannels**
|
||||
- **Tweakers**
|
||||
- **TwitCasting**
|
||||
@@ -1603,6 +1584,7 @@ # Supported sites
|
||||
- **UlizaPortal**: ulizaportal.jp
|
||||
- **umg:de**: Universal Music Deutschland
|
||||
- **Unistra**
|
||||
- **UnitedNationsWebTv**
|
||||
- **Unity**: (**Currently broken**)
|
||||
- **uol.com.br**
|
||||
- **uplynk**
|
||||
@@ -1619,15 +1601,13 @@ # Supported sites
|
||||
- **Vbox7**
|
||||
- **Veo**
|
||||
- **Vesti**: Вести.Ru (**Currently broken**)
|
||||
- **Vevo**
|
||||
- **VevoPlaylist**
|
||||
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
|
||||
- **vh1.com**
|
||||
- **vhx:embed**: [*vimeo*](## "netrc machine")
|
||||
- **vice**: (**Currently broken**)
|
||||
- **vice:article**: (**Currently broken**)
|
||||
- **vice:show**: (**Currently broken**)
|
||||
- **Viddler**
|
||||
- **Viddler**: (**Currently broken**)
|
||||
- **Videa**
|
||||
- **video.arnes.si**: Arnes Video
|
||||
- **video.google:search**: Google Video search; "gvsearch:" prefix
|
||||
@@ -1699,7 +1679,7 @@ # Supported sites
|
||||
- **vrsquare:section**
|
||||
- **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
|
||||
- **vrtmax**: [*vrtnu*](## "netrc machine") VRT MAX (formerly VRT NU)
|
||||
- **VTM**: (**Currently broken**)
|
||||
- **VTM**
|
||||
- **VTV**
|
||||
- **VTVGo**
|
||||
- **VTXTV**: [*vtxtv*](## "netrc machine")
|
||||
|
||||
@@ -36,6 +36,18 @@ def do_GET(self):
|
||||
self.send_header('Content-Type', 'text/html; charset=utf-8')
|
||||
self.end_headers()
|
||||
self.wfile.write(TEAPOT_RESPONSE_BODY.encode())
|
||||
elif self.path == '/fake.m3u8':
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Length', '1024')
|
||||
self.end_headers()
|
||||
self.wfile.write(1024 * b'\x00')
|
||||
elif self.path == '/bipbop.m3u8':
|
||||
with open('test/testdata/m3u8/bipbop_16x9.m3u8', 'rb') as f:
|
||||
data = f.read()
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Length', str(len(data)))
|
||||
self.end_headers()
|
||||
self.wfile.write(data)
|
||||
else:
|
||||
assert False
|
||||
|
||||
@@ -1947,6 +1959,37 @@ def test_search_nextjs_data(self):
|
||||
with self.assertWarns(DeprecationWarning):
|
||||
self.assertEqual(self.ie._search_nextjs_data('', None, default='{}'), {})
|
||||
|
||||
def test_search_nextjs_v13_data(self):
|
||||
HTML = R'''
|
||||
<script>(self.__next_f=self.__next_f||[]).push([0])</script>
|
||||
<script>self.__next_f.push([2,"0:[\"$\",\"$L0\",null,{\"do_not_add_this\":\"fail\"}]\n"])</script>
|
||||
<script>self.__next_f.push([1,"1:I[46975,[],\"HTTPAccessFallbackBoundary\"]\n2:I[32630,[\"8183\",\"static/chunks/8183-768193f6a9e33cdd.js\"]]\n"])</script>
|
||||
<script nonce="abc123">self.__next_f.push([1,"e:[false,[\"$\",\"div\",null,{\"children\":[\"$\",\"$L18\",null,{\"foo\":\"bar\"}]}],false]\n "])</script>
|
||||
<script>self.__next_f.push([1,"2a:[[\"$\",\"div\",null,{\"className\":\"flex flex-col\",\"children\":[]}],[\"$\",\"$L16\",null,{\"meta\":{\"dateCreated\":1730489700,\"uuid\":\"40cac41d-8d29-4ef5-aa11-75047b9f0907\"}}]]\n"])</script>
|
||||
<script>self.__next_f.push([1,"df:[\"$undefined\",[\"$\",\"div\",null,{\"children\":[\"$\",\"$L17\",null,{}],\"do_not_include_this_field\":\"fail\"}],[\"$\",\"div\",null,{\"children\":[[\"$\",\"$L19\",null,{\"duplicated_field_name\":{\"x\":1}}],[\"$\",\"$L20\",null,{\"duplicated_field_name\":{\"y\":2}}]]}],\"$undefined\"]\n"])</script>
|
||||
<script>self.__next_f.push([3,"MzM6WyIkIiwiJEwzMiIsbnVsbCx7ImRlY29kZWQiOiJzdWNjZXNzIn1d"])</script>
|
||||
'''
|
||||
EXPECTED = {
|
||||
'18': {
|
||||
'foo': 'bar',
|
||||
},
|
||||
'16': {
|
||||
'meta': {
|
||||
'dateCreated': 1730489700,
|
||||
'uuid': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
|
||||
},
|
||||
},
|
||||
'19': {
|
||||
'duplicated_field_name': {'x': 1},
|
||||
},
|
||||
'20': {
|
||||
'duplicated_field_name': {'y': 2},
|
||||
},
|
||||
}
|
||||
self.assertEqual(self.ie._search_nextjs_v13_data(HTML, None), EXPECTED)
|
||||
self.assertEqual(self.ie._search_nextjs_v13_data('', None, fatal=False), {})
|
||||
self.assertEqual(self.ie._search_nextjs_v13_data(None, None, fatal=False), {})
|
||||
|
||||
def test_search_nuxt_json(self):
|
||||
HTML_TMPL = '<script data-ssr="true" id="__NUXT_DATA__" type="application/json">[{}]</script>'
|
||||
VALID_DATA = '''
|
||||
@@ -2079,5 +2122,45 @@ def test_search_nuxt_json(self):
|
||||
self.ie._search_nuxt_json(HTML_TMPL.format(data), None, default=DEFAULT), DEFAULT)
|
||||
|
||||
|
||||
class TestInfoExtractorNetwork(unittest.TestCase):
|
||||
def setUp(self, /):
|
||||
self.httpd = http.server.HTTPServer(
|
||||
('127.0.0.1', 0), InfoExtractorTestRequestHandler)
|
||||
self.port = http_server_port(self.httpd)
|
||||
|
||||
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
|
||||
self.server_thread.daemon = True
|
||||
self.server_thread.start()
|
||||
|
||||
self.called = False
|
||||
|
||||
def require_warning(*args, **kwargs):
|
||||
self.called = True
|
||||
|
||||
self.ydl = FakeYDL()
|
||||
self.ydl.report_warning = require_warning
|
||||
self.ie = DummyIE(self.ydl)
|
||||
|
||||
def tearDown(self, /):
|
||||
self.ydl.close()
|
||||
self.httpd.shutdown()
|
||||
self.httpd.server_close()
|
||||
self.server_thread.join(1)
|
||||
|
||||
def test_extract_m3u8_formats(self):
|
||||
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
|
||||
f'http://127.0.0.1:{self.port}/bipbop.m3u8', None, fatal=False)
|
||||
self.assertFalse(self.called)
|
||||
self.assertTrue(formats)
|
||||
self.assertTrue(subtitles)
|
||||
|
||||
def test_extract_m3u8_formats_warning(self):
|
||||
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
|
||||
f'http://127.0.0.1:{self.port}/fake.m3u8', None, fatal=False)
|
||||
self.assertTrue(self.called, 'Warning was not issued for binary m3u8 file')
|
||||
self.assertFalse(formats)
|
||||
self.assertFalse(subtitles)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@@ -21,9 +21,6 @@ def test_compat_passthrough(self):
|
||||
with self.assertWarns(DeprecationWarning):
|
||||
_ = compat.compat_basestring
|
||||
|
||||
with self.assertWarns(DeprecationWarning):
|
||||
_ = compat.WINDOWS_VT_MODE
|
||||
|
||||
self.assertEqual(urllib.request.getproxies, getproxies)
|
||||
|
||||
with self.assertWarns(DeprecationWarning):
|
||||
|
||||
@@ -14,6 +14,7 @@
|
||||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_info_dict,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
@@ -65,10 +66,6 @@ def _file_md5(fn):
|
||||
|
||||
@is_download_test
|
||||
class TestDownload(unittest.TestCase):
|
||||
# Parallel testing in nosetests. See
|
||||
# http://nose.readthedocs.org/en/latest/doc_tests/test_multiprocess/multiprocess.html
|
||||
_multiprocess_shared_ = True
|
||||
|
||||
maxDiff = None
|
||||
|
||||
COMPLETED_TESTS = {}
|
||||
@@ -121,10 +118,13 @@ def print_skipping(reason):
|
||||
params = get_params(test_case.get('params', {}))
|
||||
params['outtmpl'] = tname + '_' + params['outtmpl']
|
||||
if is_playlist and 'playlist' not in test_case:
|
||||
params.setdefault('extract_flat', 'in_playlist')
|
||||
params.setdefault('playlistend', test_case.get(
|
||||
'playlist_mincount', test_case.get('playlist_count', -2) + 1))
|
||||
params.setdefault('playlistend', max(
|
||||
test_case.get('playlist_mincount', -1),
|
||||
test_case.get('playlist_count', -2) + 1,
|
||||
test_case.get('playlist_maxcount', -2) + 1))
|
||||
params.setdefault('skip_download', True)
|
||||
if 'playlist_duration_sum' not in test_case:
|
||||
params.setdefault('extract_flat', 'in_playlist')
|
||||
|
||||
ydl = YoutubeDL(params, auto_init=False)
|
||||
ydl.add_default_info_extractors()
|
||||
@@ -159,6 +159,7 @@ def try_rm_tcs_files(tcs=None):
|
||||
try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
|
||||
try_rm_tcs_files()
|
||||
try:
|
||||
test_url = test_case['url']
|
||||
try_num = 1
|
||||
while True:
|
||||
try:
|
||||
@@ -166,7 +167,7 @@ def try_rm_tcs_files(tcs=None):
|
||||
# for outside error handling, and returns the exit code
|
||||
# instead of the result dict.
|
||||
res_dict = ydl.extract_info(
|
||||
test_case['url'],
|
||||
test_url,
|
||||
force_generic_extractor=params.get('force_generic_extractor', False))
|
||||
except (DownloadError, ExtractorError) as err:
|
||||
# Check if the exception is not a network related one
|
||||
@@ -194,23 +195,23 @@ def try_rm_tcs_files(tcs=None):
|
||||
self.assertTrue('entries' in res_dict)
|
||||
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
|
||||
|
||||
num_entries = len(res_dict.get('entries', []))
|
||||
if 'playlist_mincount' in test_case:
|
||||
mincount = test_case['playlist_mincount']
|
||||
assertGreaterEqual(
|
||||
self,
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_mincount'],
|
||||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
self, num_entries, mincount,
|
||||
f'Expected at least {mincount} entries in playlist {test_url}, but got only {num_entries}')
|
||||
if 'playlist_count' in test_case:
|
||||
count = test_case['playlist_count']
|
||||
got = num_entries if num_entries <= count else 'more'
|
||||
self.assertEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_count'],
|
||||
'Expected %d entries in playlist %s, but got %d.' % (
|
||||
test_case['playlist_count'],
|
||||
test_case['url'],
|
||||
len(res_dict['entries']),
|
||||
))
|
||||
num_entries, count,
|
||||
f'Expected exactly {count} entries in playlist {test_url}, but got {got}')
|
||||
if 'playlist_maxcount' in test_case:
|
||||
maxcount = test_case['playlist_maxcount']
|
||||
assertLessEqual(
|
||||
self, num_entries, maxcount,
|
||||
f'Expected at most {maxcount} entries in playlist {test_url}, but got more')
|
||||
if 'playlist_duration_sum' in test_case:
|
||||
got_duration = sum(e['duration'] for e in res_dict['entries'])
|
||||
self.assertEqual(
|
||||
|
||||
@@ -478,6 +478,10 @@ def test_extract_function_with_global_stack(self):
|
||||
func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
|
||||
self.assertEqual(func([1]), 1111)
|
||||
|
||||
def test_extract_object(self):
|
||||
jsi = JSInterpreter('var a={};a.xy={};var xy;var zxy={};xy={z:function(){return "abc"}};')
|
||||
self.assertTrue('z' in jsi.extract_object('xy', None))
|
||||
|
||||
def test_increment_decrement(self):
|
||||
self._test('function f() { var x = 1; return ++x; }', 2)
|
||||
self._test('function f() { var x = 1; return x++; }', 1)
|
||||
@@ -486,6 +490,57 @@ def test_increment_decrement(self):
|
||||
self._test('function f() { var a = "test--"; return a; }', 'test--')
|
||||
self._test('function f() { var b = 1; var a = "b--"; return a; }', 'b--')
|
||||
|
||||
def test_nested_function_scoping(self):
|
||||
self._test(R'''
|
||||
function f() {
|
||||
var g = function() {
|
||||
var P = 2;
|
||||
return P;
|
||||
};
|
||||
var P = 1;
|
||||
g();
|
||||
return P;
|
||||
}
|
||||
''', 1)
|
||||
self._test(R'''
|
||||
function f() {
|
||||
var x = function() {
|
||||
for (var w = 1, M = []; w < 2; w++) switch (w) {
|
||||
case 1:
|
||||
M.push("a");
|
||||
case 2:
|
||||
M.push("b");
|
||||
}
|
||||
return M
|
||||
};
|
||||
var w = "c";
|
||||
var M = "d";
|
||||
var y = x();
|
||||
y.push(w);
|
||||
y.push(M);
|
||||
return y;
|
||||
}
|
||||
''', ['a', 'b', 'c', 'd'])
|
||||
self._test(R'''
|
||||
function f() {
|
||||
var P, Q;
|
||||
var z = 100;
|
||||
var g = function() {
|
||||
var P, Q; P = 2; Q = 15;
|
||||
z = 0;
|
||||
return P+Q;
|
||||
};
|
||||
P = 1; Q = 10;
|
||||
var x = g(), y = 3;
|
||||
return P+Q+x+y+z;
|
||||
}
|
||||
''', 31)
|
||||
|
||||
def test_undefined_varnames(self):
|
||||
jsi = JSInterpreter('function f(){ var a; return [a, b]; }')
|
||||
self._test(jsi, [JS_Undefined, JS_Undefined])
|
||||
self.assertEqual(jsi._undefined_varnames, {'b'})
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@@ -22,7 +22,6 @@
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
import warnings
|
||||
import zlib
|
||||
@@ -223,10 +222,7 @@ def do_GET(self):
|
||||
if encoding == 'br' and brotli:
|
||||
payload = brotli.compress(payload)
|
||||
elif encoding == 'gzip':
|
||||
buf = io.BytesIO()
|
||||
with gzip.GzipFile(fileobj=buf, mode='wb') as f:
|
||||
f.write(payload)
|
||||
payload = buf.getvalue()
|
||||
payload = gzip.compress(payload, mtime=0)
|
||||
elif encoding == 'deflate':
|
||||
payload = zlib.compress(payload)
|
||||
elif encoding == 'unsupported':
|
||||
@@ -729,6 +725,17 @@ def test_keep_header_casing(self, handler):
|
||||
|
||||
assert 'X-test-heaDer: test' in res
|
||||
|
||||
def test_partial_read_then_full_read(self, handler):
|
||||
with handler() as rh:
|
||||
for encoding in ('', 'gzip', 'deflate'):
|
||||
res = validate_and_send(rh, Request(
|
||||
f'http://127.0.0.1:{self.http_port}/content-encoding',
|
||||
headers={'ytdl-encoding': encoding}))
|
||||
assert res.headers.get('Content-Encoding') == encoding
|
||||
assert res.read(6) == b'<html>'
|
||||
assert res.read(0) == b''
|
||||
assert res.read() == b'<video src="/vid.mp4" /></html>'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
|
||||
class TestClientCertificate:
|
||||
|
||||
@@ -14,7 +14,6 @@
|
||||
NRKTVIE,
|
||||
PBSIE,
|
||||
CeskaTelevizeIE,
|
||||
ComedyCentralIE,
|
||||
DailymotionIE,
|
||||
DemocracynowIE,
|
||||
LyndaIE,
|
||||
@@ -279,23 +278,6 @@ def test_allsubtitles(self):
|
||||
self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
|
||||
|
||||
|
||||
@is_download_test
|
||||
@unittest.skip('IE broken')
|
||||
class TestMTVSubtitles(BaseTestSubtitles):
|
||||
url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
|
||||
IE = ComedyCentralIE
|
||||
|
||||
def getInfoDict(self):
|
||||
return super().getInfoDict()['entries'][0]
|
||||
|
||||
def test_allsubtitles(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(set(subtitles.keys()), {'en'})
|
||||
self.assertEqual(md5(subtitles['en']), '78206b8d8a0cfa9da64dc026eea48961')
|
||||
|
||||
|
||||
@is_download_test
|
||||
class TestNRKSubtitles(BaseTestSubtitles):
|
||||
url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
|
||||
|
||||
@@ -84,8 +84,9 @@
|
||||
lock 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lock 2024.10.22 py2exe .+
|
||||
lock 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lock 2024.10.22 (?!\w+_exe).+ Python 3\.8
|
||||
lock 2024.10.22 zip Python 3\.8
|
||||
lock 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lock 2025.08.11 darwin_legacy_exe .+
|
||||
'''
|
||||
|
||||
TEST_LOCKFILE_V2_TMPL = r'''%s
|
||||
@@ -94,20 +95,23 @@
|
||||
lockV2 yt-dlp/yt-dlp 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp 2025.08.11 darwin_legacy_exe .+
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 (?!win_x86_exe).+ Python 3\.7
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp-nightly-builds 2025.08.12.233030 darwin_legacy_exe .+
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 (?!win_x86_exe).+ Python 3\.7
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 win_x86_exe .+ Windows-(?:Vista|2008Server)
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.045052 py2exe .+
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 (?!\w+_exe).+ Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 zip Python 3\.8
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
|
||||
lockV2 yt-dlp/yt-dlp-master-builds 2025.08.12.232447 darwin_legacy_exe .+
|
||||
'''
|
||||
|
||||
TEST_LOCKFILE_V2 = TEST_LOCKFILE_V2_TMPL % TEST_LOCKFILE_COMMENT
|
||||
@@ -217,6 +221,10 @@ def test(lockfile, identifier, input_tag, expect_tag, exact=False, repo='yt-dlp/
|
||||
test( # linux_aarch64_exe w/glibc2.3 should only update to glibc<2.31 lock
|
||||
lockfile, 'linux_aarch64_exe Python 3.8.0 (CPython aarch64 64bit) - Linux-6.5.0-1025-azure-aarch64-with-glibc2.3 (OpenSSL',
|
||||
'2025.01.01', '2024.10.22')
|
||||
test(lockfile, 'darwin_legacy_exe Python 3.10.5', '2025.08.11', '2025.08.11')
|
||||
test(lockfile, 'darwin_legacy_exe Python 3.10.5', '2025.08.11', '2025.08.11', exact=True)
|
||||
test(lockfile, 'darwin_legacy_exe Python 3.10.5', '2025.08.12', '2025.08.11')
|
||||
test(lockfile, 'darwin_legacy_exe Python 3.10.5', '2025.08.12', None, exact=True)
|
||||
|
||||
# Forks can block updates to non-numeric tags rather than lock
|
||||
test(TEST_LOCKFILE_FORK, 'zip Python 3.6.3', 'pr0000', None, repo='fork/yt-dlp')
|
||||
|
||||
@@ -71,6 +71,8 @@
|
||||
iri_to_uri,
|
||||
is_html,
|
||||
js_to_json,
|
||||
jwt_decode_hs256,
|
||||
jwt_encode,
|
||||
limit_length,
|
||||
locked_file,
|
||||
lowercase_escape,
|
||||
@@ -1373,6 +1375,7 @@ def test_parse_resolution(self):
|
||||
self.assertEqual(parse_resolution('pre_1920x1080_post'), {'width': 1920, 'height': 1080})
|
||||
self.assertEqual(parse_resolution('ep1x2'), {})
|
||||
self.assertEqual(parse_resolution('1920, 1080'), {'width': 1920, 'height': 1080})
|
||||
self.assertEqual(parse_resolution('1920w', lenient=True), {'width': 1920})
|
||||
|
||||
def test_parse_bitrate(self):
|
||||
self.assertEqual(parse_bitrate(None), None)
|
||||
@@ -2179,6 +2182,41 @@ def test_partial_application(self):
|
||||
assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
|
||||
assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
|
||||
|
||||
_JWT_KEY = '12345678'
|
||||
_JWT_HEADERS_1 = {'a': 'b'}
|
||||
_JWT_HEADERS_2 = {'typ': 'JWT', 'alg': 'HS256'}
|
||||
_JWT_HEADERS_3 = {'typ': 'JWT', 'alg': 'RS256'}
|
||||
_JWT_HEADERS_4 = {'c': 'd', 'alg': 'ES256'}
|
||||
_JWT_DECODED = {
|
||||
'foo': 'bar',
|
||||
'qux': 'baz',
|
||||
}
|
||||
_JWT_SIMPLE = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJmb28iOiJiYXIiLCJxdXgiOiJiYXoifQ.fKojvTWqnjNTbsdoDTmYNc4tgYAG3h_SWRzM77iLH0U'
|
||||
_JWT_WITH_EXTRA_HEADERS = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCIsImEiOiJiIn0.eyJmb28iOiJiYXIiLCJxdXgiOiJiYXoifQ.Ia91-B77yasfYM7jsB6iVKLew-3rO6ITjNmjWUVXCvQ'
|
||||
_JWT_WITH_REORDERED_HEADERS = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJmb28iOiJiYXIiLCJxdXgiOiJiYXoifQ.slg-7COta5VOfB36p3tqV4MGPV6TTA_ouGnD48UEVq4'
|
||||
_JWT_WITH_REORDERED_HEADERS_AND_RS256_ALG = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJmb28iOiJiYXIiLCJxdXgiOiJiYXoifQ.XWp496oVgQnoits0OOocutdjxoaQwn4GUWWxUsKENPM'
|
||||
_JWT_WITH_EXTRA_HEADERS_AND_ES256_ALG = 'eyJhbGciOiJFUzI1NiIsInR5cCI6IkpXVCIsImMiOiJkIn0.eyJmb28iOiJiYXIiLCJxdXgiOiJiYXoifQ.oM_tc7IkfrwkoRh43rFFE1wOi3J3mQGwx7_lMyKQqDg'
|
||||
|
||||
def test_jwt_encode(self):
|
||||
def test(expected, headers={}):
|
||||
self.assertEqual(jwt_encode(self._JWT_DECODED, self._JWT_KEY, headers=headers), expected)
|
||||
|
||||
test(self._JWT_SIMPLE)
|
||||
test(self._JWT_WITH_EXTRA_HEADERS, headers=self._JWT_HEADERS_1)
|
||||
test(self._JWT_WITH_REORDERED_HEADERS, headers=self._JWT_HEADERS_2)
|
||||
test(self._JWT_WITH_REORDERED_HEADERS_AND_RS256_ALG, headers=self._JWT_HEADERS_3)
|
||||
test(self._JWT_WITH_EXTRA_HEADERS_AND_ES256_ALG, headers=self._JWT_HEADERS_4)
|
||||
|
||||
def test_jwt_decode_hs256(self):
|
||||
def test(inp):
|
||||
self.assertEqual(jwt_decode_hs256(inp), self._JWT_DECODED)
|
||||
|
||||
test(self._JWT_SIMPLE)
|
||||
test(self._JWT_WITH_EXTRA_HEADERS)
|
||||
test(self._JWT_WITH_REORDERED_HEADERS)
|
||||
test(self._JWT_WITH_REORDERED_HEADERS_AND_RS256_ALG)
|
||||
test(self._JWT_WITH_EXTRA_HEADERS_AND_ES256_ALG)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@@ -133,6 +133,26 @@
|
||||
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||
'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/e12fbea4/player_ias.vflset/en_US/base.js',
|
||||
'gN7a-hudCuAuPH6fByOk1_GNXN0yNMHShjZXS2VOgsEItAJz0tipeavEOmNdYN-wUtcEqD3bCXjc0iyKfAyZxCBGgIARwsSdQfJ2CJtt',
|
||||
'JC2JfQdSswRAIgGBCxZyAfKyi0cjXCb3DqEctUw-NYdNmOEvaepit0zJAtIEsgOV2SXZjhSHMNy0NXNG_1kOyBf6HPuAuCduh-a',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/010fbc8d/player_es5.vflset/en_US/base.js',
|
||||
'gN7a-hudCuAuPH6fByOk1_GNXN0yNMHShjZXS2VOgsEItAJz0tipeavEOmNdYN-wUtcEqD3bCXjc0iyKfAyZxCBGgIARwsSdQfJ2CJtt',
|
||||
'ttJC2JfQdSswRAIgGBCxZyAfKyi0cjXCb3DqEctUw-NYdNmOEvaepit2zJAsIEggOVaSXZjhSHMNy0NXNG_1kOyBf6HPuAuCduh-',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/010fbc8d/player_es6.vflset/en_US/base.js',
|
||||
'gN7a-hudCuAuPH6fByOk1_GNXN0yNMHShjZXS2VOgsEItAJz0tipeavEOmNdYN-wUtcEqD3bCXjc0iyKfAyZxCBGgIARwsSdQfJ2CJtt',
|
||||
'ttJC2JfQdSswRAIgGBCxZyAfKyi0cjXCb3DqEctUw-NYdNmOEvaepit2zJAsIEggOVaSXZjhSHMNy0NXNG_1kOyBf6HPuAuCduh-',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/5ec65609/player_ias_tcc.vflset/en_US/base.js',
|
||||
'AAJAJfQdSswRAIgNSN0GDUcHnCIXkKcF61yLBgDHiX1sUhOJdY4_GxunRYCIDeYNYP_16mQTPm5f1OVq3oV1ijUNYPjP4iUSMAjO9bZ',
|
||||
'AJfQdSswRAIgNSN0GDUcHnCIXkKcF61ZLBgDHiX1sUhOJdY4_GxunRYCIDyYNYP_16mQTPm5f1OVq3oV1ijUNYPjP4iUSMAjO9be',
|
||||
),
|
||||
]
|
||||
|
||||
_NSIG_TESTS = [
|
||||
@@ -328,6 +348,62 @@
|
||||
'https://www.youtube.com/s/player/fc2a56a5/tv-player-ias.vflset/tv-player-ias.js',
|
||||
'qTKWg_Il804jd2kAC', 'OtUAm2W6gyzJjB9u',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/a74bf670/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', 'hQP7k1hA22OrNTnq',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/6275f73c/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '-I03XF0iyf6I_X0A',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/20c72c18/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '-I03XF0iyf6I_X0A',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/9fe2e06e/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '6r5ekNIiEMPutZy',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/680f8c75/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '0ml9caTwpa55Jf',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/14397202/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', 'ozZFAN21okDdJTa',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/5dcb2c1f/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', 'p7iTbRZDYAF',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/a10d7fcc/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '9Zue7DDHJSD',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/8e20cb06/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', '5-4tTneTROTpMzba',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/e12fbea4/player_ias_tce.vflset/en_US/base.js',
|
||||
'kM5r52fugSZRAKHfo3', 'XkeRfXIPOkSwfg',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/ef259203/player_ias_tce.vflset/en_US/base.js',
|
||||
'rPqBC01nJpqhhi2iA2U', 'hY7dbiKFT51UIA',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/010fbc8d/player_es5.vflset/en_US/base.js',
|
||||
'0hlOAlqjFszVvF4Z', 'R-H23bZGAsRFTg',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/010fbc8d/player_es6.vflset/en_US/base.js',
|
||||
'0hlOAlqjFszVvF4Z', 'R-H23bZGAsRFTg',
|
||||
),
|
||||
(
|
||||
'https://www.youtube.com/s/player/5ec65609/player_ias_tcc.vflset/en_US/base.js',
|
||||
'6l5CTNx4AzIqH4MXM', 'NupToduxHBew1g',
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
|
||||
@@ -36,6 +36,7 @@
|
||||
from .globals import (
|
||||
IN_CLI,
|
||||
LAZY_EXTRACTORS,
|
||||
WINDOWS_VT_MODE,
|
||||
plugin_ies,
|
||||
plugin_ies_overrides,
|
||||
plugin_pps,
|
||||
@@ -52,7 +53,7 @@
|
||||
SSLError,
|
||||
network_exceptions,
|
||||
)
|
||||
from .networking.impersonate import ImpersonateRequestHandler
|
||||
from .networking.impersonate import ImpersonateRequestHandler, ImpersonateTarget
|
||||
from .plugins import directories as plugin_directories, load_all_plugins
|
||||
from .postprocessor import (
|
||||
EmbedThumbnailPP,
|
||||
@@ -72,6 +73,7 @@
|
||||
from .update import (
|
||||
REPOSITORY,
|
||||
_get_system_deprecation,
|
||||
_get_outdated_warning,
|
||||
_make_label,
|
||||
current_git_head,
|
||||
detect_variant,
|
||||
@@ -482,7 +484,8 @@ class YoutubeDL:
|
||||
The following options do not work when used through the API:
|
||||
filename, abort-on-error, multistreams, no-live-chat,
|
||||
format-sort, no-clean-infojson, no-playlist-metafiles,
|
||||
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort.
|
||||
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort,
|
||||
mtime-by-default.
|
||||
Refer __init__.py for their implementation
|
||||
progress_template: Dictionary of templates for progress outputs.
|
||||
Allowed keys are 'download', 'postprocess',
|
||||
@@ -502,6 +505,7 @@ class YoutubeDL:
|
||||
force_keyframes_at_cuts: Re-encode the video when downloading ranges to get precise cuts
|
||||
noprogress: Do not print the progress bar
|
||||
live_from_start: Whether to download livestreams videos from the start
|
||||
warn_when_outdated: Emit a warning if the yt-dlp version is older than 90 days
|
||||
|
||||
The following parameters are not used by YoutubeDL itself, they are used by
|
||||
the downloader (see yt_dlp/downloader/common.py):
|
||||
@@ -528,6 +532,7 @@ class YoutubeDL:
|
||||
discontinuities such as ad breaks (default: False)
|
||||
extractor_args: A dictionary of arguments to be passed to the extractors.
|
||||
See "EXTRACTOR ARGUMENTS" for details.
|
||||
Argument values must always be a list of string(s).
|
||||
E.g. {'youtube': {'skip': ['dash', 'hls']}}
|
||||
mark_watched: Mark videos watched (even with --simulate). Only for YouTube
|
||||
|
||||
@@ -594,7 +599,7 @@ class YoutubeDL:
|
||||
_NUMERIC_FIELDS = {
|
||||
'width', 'height', 'asr', 'audio_channels', 'fps',
|
||||
'tbr', 'abr', 'vbr', 'filesize', 'filesize_approx',
|
||||
'timestamp', 'release_timestamp',
|
||||
'timestamp', 'release_timestamp', 'available_at',
|
||||
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
|
||||
'average_rating', 'comment_count', 'age_limit',
|
||||
'start_time', 'end_time',
|
||||
@@ -604,13 +609,13 @@ class YoutubeDL:
|
||||
|
||||
_format_fields = {
|
||||
# NB: Keep in sync with the docstring of extractor/common.py
|
||||
'url', 'manifest_url', 'manifest_stream_number', 'ext', 'format', 'format_id', 'format_note',
|
||||
'url', 'manifest_url', 'manifest_stream_number', 'ext', 'format', 'format_id', 'format_note', 'available_at',
|
||||
'width', 'height', 'aspect_ratio', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr', 'audio_channels',
|
||||
'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns', 'hls_media_playlist_data',
|
||||
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
|
||||
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
|
||||
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'extra_param_to_key_url',
|
||||
'hls_aes', 'downloader_options', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
|
||||
'hls_aes', 'downloader_options', 'impersonate', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
|
||||
'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time',
|
||||
}
|
||||
_deprecated_multivalue_fields = {
|
||||
@@ -700,6 +705,9 @@ def process_color_policy(stream):
|
||||
system_deprecation = _get_system_deprecation()
|
||||
if system_deprecation:
|
||||
self.deprecated_feature(system_deprecation.replace('\n', '\n '))
|
||||
elif self.params.get('warn_when_outdated'):
|
||||
if outdated_warning := _get_outdated_warning():
|
||||
self.report_warning(outdated_warning)
|
||||
|
||||
if self.params.get('allow_unplayable_formats'):
|
||||
self.report_warning(
|
||||
@@ -746,8 +754,6 @@ def check_deprecated(param, option, suggestion):
|
||||
if self.params.get('geo_verification_proxy') is None:
|
||||
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
|
||||
|
||||
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
|
||||
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
|
||||
check_deprecated('useid', '--id', '-o "%(id)s.%(ext)s"')
|
||||
|
||||
for msg in self.params.get('_warnings', []):
|
||||
@@ -2194,7 +2200,7 @@ def _filter(f):
|
||||
return op(actual_value, comparison_value)
|
||||
return _filter
|
||||
|
||||
def _check_formats(self, formats):
|
||||
def _check_formats(self, formats, warning=True):
|
||||
for f in formats:
|
||||
working = f.get('__working')
|
||||
if working is not None:
|
||||
@@ -2207,6 +2213,9 @@ def _check_formats(self, formats):
|
||||
continue
|
||||
temp_file = tempfile.NamedTemporaryFile(suffix='.tmp', delete=False, dir=path or None)
|
||||
temp_file.close()
|
||||
# If FragmentFD fails when testing a fragment, it will wrongly set a non-zero return code.
|
||||
# Save the actual return code for later. See https://github.com/yt-dlp/yt-dlp/issues/13750
|
||||
original_retcode = self._download_retcode
|
||||
try:
|
||||
success, _ = self.dl(temp_file.name, f, test=True)
|
||||
except (DownloadError, OSError, ValueError, *network_exceptions):
|
||||
@@ -2217,12 +2226,18 @@ def _check_formats(self, formats):
|
||||
os.remove(temp_file.name)
|
||||
except OSError:
|
||||
self.report_warning(f'Unable to delete temporary file "{temp_file.name}"')
|
||||
# Restore the actual return code
|
||||
self._download_retcode = original_retcode
|
||||
f['__working'] = success
|
||||
if success:
|
||||
f.pop('__needs_testing', None)
|
||||
yield f
|
||||
else:
|
||||
self.to_screen('[info] Unable to download format {}. Skipping...'.format(f['format_id']))
|
||||
msg = f'Unable to download format {f["format_id"]}. Skipping...'
|
||||
if warning:
|
||||
self.report_warning(msg)
|
||||
else:
|
||||
self.to_screen(f'[info] {msg}')
|
||||
|
||||
def _select_formats(self, formats, selector):
|
||||
return list(selector({
|
||||
@@ -2948,7 +2963,7 @@ def is_wellformed(f):
|
||||
)
|
||||
|
||||
if self.params.get('check_formats') is True:
|
||||
formats = LazyList(self._check_formats(formats[::-1]), reverse=True)
|
||||
formats = LazyList(self._check_formats(formats[::-1], warning=False), reverse=True)
|
||||
|
||||
if not formats or formats[0] is not info_dict:
|
||||
# only set the 'formats' fields if the original info_dict list them
|
||||
@@ -3221,6 +3236,7 @@ def dl(self, name, info, subtitle=False, test=False):
|
||||
}
|
||||
else:
|
||||
params = self.params
|
||||
|
||||
fd = get_suitable_downloader(info, params, to_stdout=(name == '-'))(self, params)
|
||||
if not test:
|
||||
for ph in self._progress_hooks:
|
||||
@@ -3696,6 +3712,8 @@ def filter_fn(obj):
|
||||
return {k: filter_fn(v) for k, v in obj.items() if not reject(k, v)}
|
||||
elif isinstance(obj, (list, tuple, set, LazyList)):
|
||||
return list(map(filter_fn, obj))
|
||||
elif isinstance(obj, ImpersonateTarget):
|
||||
return str(obj)
|
||||
elif obj is None or isinstance(obj, (str, int, float, bool)):
|
||||
return obj
|
||||
else:
|
||||
@@ -4026,8 +4044,7 @@ def get_encoding(stream):
|
||||
if os.environ.get('TERM', '').lower() == 'dumb':
|
||||
additional_info.append('dumb')
|
||||
if not supports_terminal_sequences(stream):
|
||||
from .utils import WINDOWS_VT_MODE # Must be imported locally
|
||||
additional_info.append('No VT' if WINDOWS_VT_MODE is False else 'No ANSI')
|
||||
additional_info.append('No VT' if WINDOWS_VT_MODE.value is False else 'No ANSI')
|
||||
if additional_info:
|
||||
ret = f'{ret} ({",".join(additional_info)})'
|
||||
return ret
|
||||
@@ -4173,6 +4190,31 @@ def _impersonate_target_available(self, target):
|
||||
for rh in self._request_director.handlers.values()
|
||||
if isinstance(rh, ImpersonateRequestHandler))
|
||||
|
||||
def _parse_impersonate_targets(self, impersonate):
|
||||
if impersonate in (True, ''):
|
||||
impersonate = ImpersonateTarget()
|
||||
|
||||
requested_targets = [
|
||||
t if isinstance(t, ImpersonateTarget) else ImpersonateTarget.from_str(t)
|
||||
for t in variadic(impersonate)
|
||||
] if impersonate else []
|
||||
|
||||
available_target = next(filter(self._impersonate_target_available, requested_targets), None)
|
||||
|
||||
return available_target, requested_targets
|
||||
|
||||
@staticmethod
|
||||
def _unavailable_targets_message(requested_targets, note=None, is_error=False):
|
||||
note = note or 'The extractor specified to use impersonation for this download'
|
||||
specific_targets = ', '.join(filter(None, map(str, requested_targets)))
|
||||
message = (
|
||||
'no impersonate target is available' if not specific_targets
|
||||
else f'none of these impersonate targets are available: {specific_targets}')
|
||||
return (
|
||||
f'{note}, but {message}. {"See" if is_error else "If you encounter errors, then see"}'
|
||||
f' https://github.com/yt-dlp/yt-dlp#impersonation '
|
||||
f'for information on installing the required dependencies')
|
||||
|
||||
def urlopen(self, req):
|
||||
""" Start an HTTP download """
|
||||
if isinstance(req, str):
|
||||
|
||||
@@ -159,6 +159,12 @@ def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
|
||||
elif 'prefer-vp9-sort' in opts.compat_opts:
|
||||
opts.format_sort.extend(FormatSorter._prefer_vp9_sort)
|
||||
|
||||
if 'mtime-by-default' in opts.compat_opts:
|
||||
if opts.updatetime is None:
|
||||
opts.updatetime = True
|
||||
else:
|
||||
_unused_compat_opt('mtime-by-default')
|
||||
|
||||
_video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
|
||||
_audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
|
||||
if _video_multistreams_set is False and _audio_multistreams_set is False:
|
||||
@@ -494,6 +500,14 @@ def metadataparser_actions(f):
|
||||
'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
|
||||
'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
|
||||
|
||||
# Common mistake: -f mp4
|
||||
if opts.format == 'mp4':
|
||||
warnings.append('.\n '.join((
|
||||
'"-f mp4" selects the best pre-merged mp4 format which is often not what\'s intended',
|
||||
'Pre-merged mp4 formats are not available from all sites, or may only be available in lower quality',
|
||||
'To prioritize the best h264 video and aac audio in an mp4 container, use "-t mp4" instead',
|
||||
'If you know what you are doing and want a pre-merged mp4 format, use "-f b[ext=mp4]" instead to suppress this warning')))
|
||||
|
||||
# --(postprocessor/downloader)-args without name
|
||||
def report_args_compat(name, value, key1, key2=None, where=None):
|
||||
if key1 in value and key2 not in value:
|
||||
@@ -965,6 +979,7 @@ def parse_options(argv=None):
|
||||
'geo_bypass': opts.geo_bypass,
|
||||
'geo_bypass_country': opts.geo_bypass_country,
|
||||
'geo_bypass_ip_block': opts.geo_bypass_ip_block,
|
||||
'warn_when_outdated': opts.update_self is None,
|
||||
'_warnings': warnings,
|
||||
'_deprecation_warnings': deprecation_warnings,
|
||||
'compat_opts': opts.compat_opts,
|
||||
@@ -1024,6 +1039,7 @@ def _real_main(argv=None):
|
||||
(ImpersonateTarget('safari'), 'curl_cffi'),
|
||||
(ImpersonateTarget('firefox'), 'curl_cffi>=0.10'),
|
||||
(ImpersonateTarget('edge'), 'curl_cffi'),
|
||||
(ImpersonateTarget('tor'), 'curl_cffi>=0.11'),
|
||||
]
|
||||
|
||||
available_targets = ydl._get_available_impersonate_targets()
|
||||
|
||||
@@ -435,7 +435,7 @@ def sub_bytes_inv(data):
|
||||
|
||||
|
||||
def rotate(data):
|
||||
return data[1:] + [data[0]]
|
||||
return [*data[1:], data[0]]
|
||||
|
||||
|
||||
def key_schedule_core(data, rcon_iteration):
|
||||
|
||||
@@ -37,7 +37,7 @@
|
||||
from ..dependencies.Cryptodome import AES as compat_pycrypto_AES # noqa: F401
|
||||
from ..networking.exceptions import HTTPError as compat_HTTPError
|
||||
|
||||
passthrough_module(__name__, '...utils', ('WINDOWS_VT_MODE', 'windows_enable_vt_mode'))
|
||||
passthrough_module(__name__, '...utils', ('windows_enable_vt_mode',))
|
||||
|
||||
|
||||
# compat_ctypes_WINFUNCTYPE = ctypes.WINFUNCTYPE
|
||||
|
||||
@@ -125,6 +125,8 @@ def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(),
|
||||
|
||||
|
||||
def _extract_firefox_cookies(profile, container, logger):
|
||||
MAX_SUPPORTED_DB_SCHEMA_VERSION = 16
|
||||
|
||||
logger.info('Extracting cookies from firefox')
|
||||
if not sqlite3:
|
||||
logger.warning('Cannot extract cookies from firefox without sqlite3 support. '
|
||||
@@ -159,9 +161,11 @@ def _extract_firefox_cookies(profile, container, logger):
|
||||
raise ValueError(f'could not find firefox container "{container}" in containers.json')
|
||||
|
||||
with tempfile.TemporaryDirectory(prefix='yt_dlp') as tmpdir:
|
||||
cursor = None
|
||||
try:
|
||||
cursor = _open_database_copy(cookie_database_path, tmpdir)
|
||||
cursor = _open_database_copy(cookie_database_path, tmpdir)
|
||||
with contextlib.closing(cursor.connection):
|
||||
db_schema_version = cursor.execute('PRAGMA user_version;').fetchone()[0]
|
||||
if db_schema_version > MAX_SUPPORTED_DB_SCHEMA_VERSION:
|
||||
logger.warning(f'Possibly unsupported firefox cookies database version: {db_schema_version}')
|
||||
if isinstance(container_id, int):
|
||||
logger.debug(
|
||||
f'Only loading cookies from firefox container "{container}", ID {container_id}')
|
||||
@@ -180,6 +184,10 @@ def _extract_firefox_cookies(profile, container, logger):
|
||||
total_cookie_count = len(table)
|
||||
for i, (host, name, value, path, expiry, is_secure) in enumerate(table):
|
||||
progress_bar.print(f'Loading cookie {i: 6d}/{total_cookie_count: 6d}')
|
||||
# FF142 upgraded cookies DB to schema version 16 and started using milliseconds for cookie expiry
|
||||
# Ref: https://github.com/mozilla-firefox/firefox/commit/5869af852cd20425165837f6c2d9971f3efba83d
|
||||
if db_schema_version >= 16 and expiry is not None:
|
||||
expiry /= 1000
|
||||
cookie = http.cookiejar.Cookie(
|
||||
version=0, name=name, value=value, port=None, port_specified=False,
|
||||
domain=host, domain_specified=bool(host), domain_initial_dot=host.startswith('.'),
|
||||
@@ -188,9 +196,6 @@ def _extract_firefox_cookies(profile, container, logger):
|
||||
jar.set_cookie(cookie)
|
||||
logger.info(f'Extracted {len(jar)} cookies from firefox')
|
||||
return jar
|
||||
finally:
|
||||
if cursor is not None:
|
||||
cursor.connection.close()
|
||||
|
||||
|
||||
def _firefox_browser_dirs():
|
||||
@@ -1335,7 +1340,7 @@ def prepare_line(line):
|
||||
if len(cookie_list) != self._ENTRY_LEN:
|
||||
raise http.cookiejar.LoadError(f'invalid length {len(cookie_list)}')
|
||||
cookie = self._CookieFileEntry(*cookie_list)
|
||||
if cookie.expires_at and not cookie.expires_at.isdigit():
|
||||
if cookie.expires_at and not re.fullmatch(r'[0-9]+(?:\.[0-9]+)?', cookie.expires_at):
|
||||
raise http.cookiejar.LoadError(f'invalid expires at {cookie.expires_at}')
|
||||
return line
|
||||
|
||||
|
||||
@@ -99,7 +99,7 @@ def _get_suitable_downloader(info_dict, protocol, params, default):
|
||||
if external_downloader is None:
|
||||
if info_dict['to_stdout'] and FFmpegFD.can_merge_formats(info_dict, params):
|
||||
return FFmpegFD
|
||||
elif external_downloader.lower() != 'native':
|
||||
elif external_downloader.lower() != 'native' and info_dict.get('impersonate') is None:
|
||||
ed = get_external_downloader(external_downloader)
|
||||
if ed.can_download(info_dict, external_downloader):
|
||||
return ed
|
||||
|
||||
@@ -455,14 +455,26 @@ def download(self, filename, info_dict, subtitle=False):
|
||||
self._finish_multiline_status()
|
||||
return True, False
|
||||
|
||||
sleep_note = ''
|
||||
if subtitle:
|
||||
sleep_interval = self.params.get('sleep_interval_subtitles') or 0
|
||||
else:
|
||||
min_sleep_interval = self.params.get('sleep_interval') or 0
|
||||
max_sleep_interval = self.params.get('max_sleep_interval') or 0
|
||||
|
||||
if available_at := info_dict.get('available_at'):
|
||||
forced_sleep_interval = available_at - int(time.time())
|
||||
if forced_sleep_interval > min_sleep_interval:
|
||||
sleep_note = 'as required by the site'
|
||||
min_sleep_interval = forced_sleep_interval
|
||||
if forced_sleep_interval > max_sleep_interval:
|
||||
max_sleep_interval = forced_sleep_interval
|
||||
|
||||
sleep_interval = random.uniform(
|
||||
min_sleep_interval, self.params.get('max_sleep_interval') or min_sleep_interval)
|
||||
min_sleep_interval, max_sleep_interval or min_sleep_interval)
|
||||
|
||||
if sleep_interval > 0:
|
||||
self.to_screen(f'[download] Sleeping {sleep_interval:.2f} seconds ...')
|
||||
self.to_screen(f'[download] Sleeping {sleep_interval:.2f} seconds {sleep_note}...')
|
||||
time.sleep(sleep_interval)
|
||||
|
||||
ret = self.real_download(filename, info_dict)
|
||||
@@ -495,3 +507,14 @@ def _debug_cmd(self, args, exe=None):
|
||||
exe = os.path.basename(args[0])
|
||||
|
||||
self.write_debug(f'{exe} command line: {shell_quote(args)}')
|
||||
|
||||
def _get_impersonate_target(self, info_dict):
|
||||
impersonate = info_dict.get('impersonate')
|
||||
if impersonate is None:
|
||||
return None
|
||||
available_target, requested_targets = self.ydl._parse_impersonate_targets(impersonate)
|
||||
if available_target:
|
||||
return available_target
|
||||
elif requested_targets:
|
||||
self.report_warning(self.ydl._unavailable_targets_message(requested_targets))
|
||||
return None
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
from . import get_suitable_downloader
|
||||
from .fragment import FragmentFD
|
||||
from ..utils import update_url_query, urljoin
|
||||
from ..utils import ReExtractInfo, update_url_query, urljoin
|
||||
|
||||
|
||||
class DashSegmentsFD(FragmentFD):
|
||||
@@ -28,6 +28,11 @@ def real_download(self, filename, info_dict):
|
||||
requested_formats = [{**info_dict, **fmt} for fmt in info_dict.get('requested_formats', [])]
|
||||
args = []
|
||||
for fmt in requested_formats or [info_dict]:
|
||||
# Re-extract if --load-info-json is used and 'fragments' was originally a generator
|
||||
# See https://github.com/yt-dlp/yt-dlp/issues/13906
|
||||
if isinstance(fmt['fragments'], str):
|
||||
raise ReExtractInfo('the stream needs to be re-extracted', expected=True)
|
||||
|
||||
try:
|
||||
fragment_count = 1 if self.params.get('test') else len(fmt['fragments'])
|
||||
except TypeError:
|
||||
|
||||
@@ -572,7 +572,21 @@ def _call_downloader(self, tmpfilename, info_dict):
|
||||
if end_time:
|
||||
args += ['-t', str(end_time - start_time)]
|
||||
|
||||
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', fmt['url']]
|
||||
url = fmt['url']
|
||||
if self.params.get('enable_file_urls') and url.startswith('file:'):
|
||||
# The default protocol_whitelist is 'file,crypto,data' when reading local m3u8 URLs,
|
||||
# so only local segments can be read unless we also include 'http,https,tcp,tls'
|
||||
args += ['-protocol_whitelist', 'file,crypto,data,http,https,tcp,tls']
|
||||
# ffmpeg incorrectly handles 'file:' URLs by only removing the
|
||||
# 'file:' prefix and treating the rest as if it's a normal filepath.
|
||||
# FFmpegPostProcessor also depends on this behavior, so we need to fixup the URLs:
|
||||
# - On Windows/Cygwin, replace 'file:///' and 'file://localhost/' with 'file:'
|
||||
# - On *nix, replace 'file://localhost/' with 'file:/'
|
||||
# Ref: https://github.com/yt-dlp/yt-dlp/issues/13781
|
||||
# https://trac.ffmpeg.org/ticket/2702
|
||||
url = re.sub(r'^file://(?:localhost)?/', 'file:' if os.name == 'nt' else 'file:/', url)
|
||||
|
||||
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', url]
|
||||
|
||||
if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):
|
||||
args += ['-c', 'copy']
|
||||
|
||||
@@ -302,7 +302,7 @@ def _finish_frag_download(self, ctx, info_dict):
|
||||
elif to_file:
|
||||
self.try_rename(ctx['tmpfilename'], ctx['filename'])
|
||||
filetime = ctx.get('fragment_filetime')
|
||||
if self.params.get('updatetime', True) and filetime:
|
||||
if self.params.get('updatetime') and filetime:
|
||||
with contextlib.suppress(Exception):
|
||||
os.utime(ctx['filename'], (time.time(), filetime))
|
||||
|
||||
|
||||
@@ -94,12 +94,19 @@ def real_download(self, filename, info_dict):
|
||||
can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None
|
||||
if can_download:
|
||||
has_ffmpeg = FFmpegFD.available()
|
||||
no_crypto = not Cryptodome.AES and '#EXT-X-KEY:METHOD=AES-128' in s
|
||||
if no_crypto and has_ffmpeg:
|
||||
can_download, message = False, 'The stream has AES-128 encryption and pycryptodomex is not available'
|
||||
elif no_crypto:
|
||||
message = ('The stream has AES-128 encryption and neither ffmpeg nor pycryptodomex are available; '
|
||||
'Decryption will be performed natively, but will be extremely slow')
|
||||
if not Cryptodome.AES and '#EXT-X-KEY:METHOD=AES-128' in s:
|
||||
# Even if pycryptodomex isn't available, force HlsFD for m3u8s that won't work with ffmpeg
|
||||
ffmpeg_can_dl = not traverse_obj(info_dict, ((
|
||||
'extra_param_to_segment_url', 'extra_param_to_key_url',
|
||||
'hls_media_playlist_data', ('hls_aes', ('uri', 'key', 'iv')),
|
||||
), any))
|
||||
message = 'The stream has AES-128 encryption and {} available'.format(
|
||||
'neither ffmpeg nor pycryptodomex are' if ffmpeg_can_dl and not has_ffmpeg else
|
||||
'pycryptodomex is not')
|
||||
if has_ffmpeg and ffmpeg_can_dl:
|
||||
can_download = False
|
||||
else:
|
||||
message += '; decryption will be performed natively, but will be extremely slow'
|
||||
elif info_dict.get('extractor_key') == 'Generic' and re.search(r'(?m)#EXT-X-MEDIA-SEQUENCE:(?!0$)', s):
|
||||
install_ffmpeg = '' if has_ffmpeg else 'install ffmpeg and '
|
||||
message = ('Live HLS streams are not supported by the native downloader. If this is a livestream, '
|
||||
@@ -198,7 +205,7 @@ def is_ad_fragment_end(s):
|
||||
line = line.strip()
|
||||
if line:
|
||||
if not line.startswith('#'):
|
||||
if format_index and discontinuity_count != format_index:
|
||||
if format_index is not None and discontinuity_count != format_index:
|
||||
continue
|
||||
if ad_frag_next:
|
||||
continue
|
||||
@@ -224,7 +231,7 @@ def is_ad_fragment_end(s):
|
||||
byte_range = {}
|
||||
|
||||
elif line.startswith('#EXT-X-MAP'):
|
||||
if format_index and discontinuity_count != format_index:
|
||||
if format_index is not None and discontinuity_count != format_index:
|
||||
continue
|
||||
if frag_index > 0:
|
||||
self.report_error(
|
||||
|
||||
@@ -27,6 +27,10 @@ class HttpFD(FileDownloader):
|
||||
def real_download(self, filename, info_dict):
|
||||
url = info_dict['url']
|
||||
request_data = info_dict.get('request_data', None)
|
||||
request_extensions = {}
|
||||
impersonate_target = self._get_impersonate_target(info_dict)
|
||||
if impersonate_target is not None:
|
||||
request_extensions['impersonate'] = impersonate_target
|
||||
|
||||
class DownloadContext(dict):
|
||||
__getattr__ = dict.get
|
||||
@@ -109,7 +113,7 @@ def establish_connection():
|
||||
if try_call(lambda: range_end >= ctx.content_len):
|
||||
range_end = ctx.content_len - 1
|
||||
|
||||
request = Request(url, request_data, headers)
|
||||
request = Request(url, request_data, headers, extensions=request_extensions)
|
||||
has_range = range_start is not None
|
||||
if has_range:
|
||||
request.headers['Range'] = f'bytes={int(range_start)}-{int_or_none(range_end) or ""}'
|
||||
@@ -348,7 +352,7 @@ def retry(e):
|
||||
self.try_rename(ctx.tmpfilename, ctx.filename)
|
||||
|
||||
# Update file modification time
|
||||
if self.params.get('updatetime', True):
|
||||
if self.params.get('updatetime'):
|
||||
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None))
|
||||
|
||||
self._hook_progress({
|
||||
|
||||
@@ -5,47 +5,46 @@
|
||||
from .common import FileDownloader
|
||||
from .external import FFmpegFD
|
||||
from ..networking import Request
|
||||
from ..utils import DownloadError, str_or_none, try_get
|
||||
from ..networking.websocket import WebSocketResponse
|
||||
from ..utils import DownloadError, str_or_none, truncate_string
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class NiconicoLiveFD(FileDownloader):
|
||||
""" Downloads niconico live without being stopped """
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
video_id = info_dict['video_id']
|
||||
ws_url = info_dict['url']
|
||||
ws_extractor = info_dict['ws']
|
||||
ws_origin_host = info_dict['origin']
|
||||
live_quality = info_dict.get('live_quality', 'high')
|
||||
live_latency = info_dict.get('live_latency', 'high')
|
||||
video_id = info_dict['id']
|
||||
opts = info_dict['downloader_options']
|
||||
quality, ws_extractor, ws_url = opts['max_quality'], opts['ws'], opts['ws_url']
|
||||
dl = FFmpegFD(self.ydl, self.params or {})
|
||||
|
||||
new_info_dict = info_dict.copy()
|
||||
new_info_dict.update({
|
||||
'protocol': 'm3u8',
|
||||
})
|
||||
new_info_dict['protocol'] = 'm3u8'
|
||||
|
||||
def communicate_ws(reconnect):
|
||||
if reconnect:
|
||||
ws = self.ydl.urlopen(Request(ws_url, headers={'Origin': f'https://{ws_origin_host}'}))
|
||||
# Support --load-info-json as if it is a reconnect attempt
|
||||
if reconnect or not isinstance(ws_extractor, WebSocketResponse):
|
||||
ws = self.ydl.urlopen(Request(
|
||||
ws_url, headers={'Origin': 'https://live.nicovideo.jp'}))
|
||||
if self.ydl.params.get('verbose', False):
|
||||
self.to_screen('[debug] Sending startWatching request')
|
||||
self.write_debug('Sending startWatching request')
|
||||
ws.send(json.dumps({
|
||||
'type': 'startWatching',
|
||||
'data': {
|
||||
'reconnect': True,
|
||||
'room': {
|
||||
'commentable': True,
|
||||
'protocol': 'webSocket',
|
||||
},
|
||||
'stream': {
|
||||
'quality': live_quality,
|
||||
'protocol': 'hls+fmp4',
|
||||
'latency': live_latency,
|
||||
'accessRightMethod': 'single_cookie',
|
||||
'chasePlay': False,
|
||||
'latency': 'high',
|
||||
'protocol': 'hls',
|
||||
'quality': quality,
|
||||
},
|
||||
'room': {
|
||||
'protocol': 'webSocket',
|
||||
'commentable': True,
|
||||
},
|
||||
'reconnect': True,
|
||||
},
|
||||
'type': 'startWatching',
|
||||
}))
|
||||
else:
|
||||
ws = ws_extractor
|
||||
@@ -58,7 +57,6 @@ def communicate_ws(reconnect):
|
||||
if not data or not isinstance(data, dict):
|
||||
continue
|
||||
if data.get('type') == 'ping':
|
||||
# pong back
|
||||
ws.send(r'{"type":"pong"}')
|
||||
ws.send(r'{"type":"keepSeat"}')
|
||||
elif data.get('type') == 'disconnect':
|
||||
@@ -66,12 +64,10 @@ def communicate_ws(reconnect):
|
||||
return True
|
||||
elif data.get('type') == 'error':
|
||||
self.write_debug(data)
|
||||
message = try_get(data, lambda x: x['body']['code'], str) or recv
|
||||
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
|
||||
return DownloadError(message)
|
||||
elif self.ydl.params.get('verbose', False):
|
||||
if len(recv) > 100:
|
||||
recv = recv[:100] + '...'
|
||||
self.to_screen(f'[debug] Server said: {recv}')
|
||||
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
|
||||
|
||||
def ws_main():
|
||||
reconnect = False
|
||||
@@ -81,7 +77,8 @@ def ws_main():
|
||||
if ret is True:
|
||||
return
|
||||
except BaseException as e:
|
||||
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
|
||||
self.to_screen(
|
||||
f'[niconico:live] {video_id}: Connection error occured, reconnecting after 10 seconds: {e}')
|
||||
time.sleep(10)
|
||||
continue
|
||||
finally:
|
||||
|
||||
@@ -58,13 +58,7 @@
|
||||
ADNSeasonIE,
|
||||
)
|
||||
from .adobeconnect import AdobeConnectIE
|
||||
from .adobetv import (
|
||||
AdobeTVChannelIE,
|
||||
AdobeTVEmbedIE,
|
||||
AdobeTVIE,
|
||||
AdobeTVShowIE,
|
||||
AdobeTVVideoIE,
|
||||
)
|
||||
from .adobetv import AdobeTVVideoIE
|
||||
from .adultswim import AdultSwimIE
|
||||
from .aenetworks import (
|
||||
AENetworksCollectionIE,
|
||||
@@ -152,7 +146,6 @@
|
||||
ARDBetaMediathekIE,
|
||||
ARDMediathekCollectionIE,
|
||||
)
|
||||
from .arkena import ArkenaIE
|
||||
from .arnes import ArnesIE
|
||||
from .art19 import (
|
||||
Art19IE,
|
||||
@@ -201,7 +194,6 @@
|
||||
BanByeChannelIE,
|
||||
BanByeIE,
|
||||
)
|
||||
from .bandaichannel import BandaiChannelIE
|
||||
from .bandcamp import (
|
||||
BandcampAlbumIE,
|
||||
BandcampIE,
|
||||
@@ -229,7 +221,6 @@
|
||||
from .beatport import BeatportIE
|
||||
from .beeg import BeegIE
|
||||
from .behindkink import BehindKinkIE
|
||||
from .bellmedia import BellMediaIE
|
||||
from .berufetv import BerufeTVIE
|
||||
from .bet import BetIE
|
||||
from .bfi import BFIPlayerIE
|
||||
@@ -275,7 +266,10 @@
|
||||
BitChuteChannelIE,
|
||||
BitChuteIE,
|
||||
)
|
||||
from .blackboardcollaborate import BlackboardCollaborateIE
|
||||
from .blackboardcollaborate import (
|
||||
BlackboardCollaborateIE,
|
||||
BlackboardCollaborateLaunchIE,
|
||||
)
|
||||
from .bleacherreport import (
|
||||
BleacherReportCMSIE,
|
||||
BleacherReportIE,
|
||||
@@ -309,6 +303,7 @@
|
||||
BrilliantpalaClassesIE,
|
||||
BrilliantpalaElearnIE,
|
||||
)
|
||||
from .btvplus import BTVPlusIE
|
||||
from .bundesliga import BundesligaIE
|
||||
from .bundestag import BundestagIE
|
||||
from .bunnycdn import BunnyCdnIE
|
||||
@@ -403,16 +398,12 @@
|
||||
from .cloudycdn import CloudyCDNIE
|
||||
from .clubic import ClubicIE
|
||||
from .clyp import ClypIE
|
||||
from .cmt import CMTIE
|
||||
from .cnbc import CNBCVideoIE
|
||||
from .cnn import (
|
||||
CNNIE,
|
||||
CNNIndonesiaIE,
|
||||
)
|
||||
from .comedycentral import (
|
||||
ComedyCentralIE,
|
||||
ComedyCentralTVIE,
|
||||
)
|
||||
from .comedycentral import ComedyCentralIE
|
||||
from .commonmistakes import (
|
||||
BlobIE,
|
||||
CommonMistakesIE,
|
||||
@@ -446,7 +437,6 @@
|
||||
CSpanIE,
|
||||
)
|
||||
from .ctsnews import CtsNewsIE
|
||||
from .ctv import CTVIE
|
||||
from .ctvnews import CTVNewsIE
|
||||
from .cultureunplugged import CultureUnpluggedIE
|
||||
from .curiositystream import (
|
||||
@@ -570,10 +560,6 @@
|
||||
DWIE,
|
||||
DWArticleIE,
|
||||
)
|
||||
from .eagleplatform import (
|
||||
ClipYouEmbedIE,
|
||||
EaglePlatformIE,
|
||||
)
|
||||
from .ebaumsworld import EbaumsWorldIE
|
||||
from .ebay import EbayIE
|
||||
from .egghead import (
|
||||
@@ -639,6 +625,10 @@
|
||||
FancodeVodIE,
|
||||
)
|
||||
from .fathom import FathomIE
|
||||
from .faulio import (
|
||||
FaulioIE,
|
||||
FaulioLiveIE,
|
||||
)
|
||||
from .faz import FazIE
|
||||
from .fc2 import (
|
||||
FC2IE,
|
||||
@@ -805,9 +795,7 @@
|
||||
from .hotnewhiphop import HotNewHipHopIE
|
||||
from .hotstar import (
|
||||
HotStarIE,
|
||||
HotStarPlaylistIE,
|
||||
HotStarPrefixIE,
|
||||
HotStarSeasonIE,
|
||||
HotStarSeriesIE,
|
||||
)
|
||||
from .hrefli import HrefLiRedirectIE
|
||||
@@ -921,10 +909,6 @@
|
||||
ShugiinItvVodIE,
|
||||
)
|
||||
from .jeuxvideo import JeuxVideoIE
|
||||
from .jiocinema import (
|
||||
JioCinemaIE,
|
||||
JioCinemaSeriesIE,
|
||||
)
|
||||
from .jiosaavn import (
|
||||
JioSaavnAlbumIE,
|
||||
JioSaavnArtistIE,
|
||||
@@ -934,7 +918,6 @@
|
||||
JioSaavnSongIE,
|
||||
)
|
||||
from .joj import JojIE
|
||||
from .joqrag import JoqrAgIE
|
||||
from .jove import JoveIE
|
||||
from .jstream import JStreamIE
|
||||
from .jtbc import (
|
||||
@@ -1037,11 +1020,6 @@
|
||||
LikeeIE,
|
||||
LikeeUserIE,
|
||||
)
|
||||
from .limelight import (
|
||||
LimelightChannelIE,
|
||||
LimelightChannelListIE,
|
||||
LimelightMediaIE,
|
||||
)
|
||||
from .linkedin import (
|
||||
LinkedInEventsIE,
|
||||
LinkedInIE,
|
||||
@@ -1153,6 +1131,7 @@
|
||||
MindsIE,
|
||||
)
|
||||
from .minoto import MinotoIE
|
||||
from .mir24tv import Mir24TvIE
|
||||
from .mirrativ import (
|
||||
MirrativIE,
|
||||
MirrativUserIE,
|
||||
@@ -1173,6 +1152,10 @@
|
||||
MixcloudPlaylistIE,
|
||||
MixcloudUserIE,
|
||||
)
|
||||
from .mixlr import (
|
||||
MixlrIE,
|
||||
MixlrRecoringIE,
|
||||
)
|
||||
from .mlb import (
|
||||
MLBIE,
|
||||
MLBTVIE,
|
||||
@@ -1196,15 +1179,7 @@
|
||||
from .moviezine import MoviezineIE
|
||||
from .movingimage import MovingImageIE
|
||||
from .msn import MSNIE
|
||||
from .mtv import (
|
||||
MTVDEIE,
|
||||
MTVIE,
|
||||
MTVItaliaIE,
|
||||
MTVItaliaProgrammaIE,
|
||||
MTVJapanIE,
|
||||
MTVServicesEmbeddedIE,
|
||||
MTVVideoIE,
|
||||
)
|
||||
from .mtv import MTVIE
|
||||
from .muenchentv import MuenchenTVIE
|
||||
from .murrtube import (
|
||||
MurrtubeIE,
|
||||
@@ -1346,12 +1321,7 @@
|
||||
NhkVodProgramIE,
|
||||
)
|
||||
from .nhl import NHLIE
|
||||
from .nick import (
|
||||
NickBrIE,
|
||||
NickDeIE,
|
||||
NickIE,
|
||||
NickRuIE,
|
||||
)
|
||||
from .nick import NickIE
|
||||
from .niconico import (
|
||||
NiconicoHistoryIE,
|
||||
NiconicoIE,
|
||||
@@ -1383,7 +1353,6 @@
|
||||
from .noice import NoicePodcastIE
|
||||
from .nonktube import NonkTubeIE
|
||||
from .noodlemagazine import NoodleMagazineIE
|
||||
from .noovo import NoovoIE
|
||||
from .nosnl import NOSNLArticleIE
|
||||
from .nova import (
|
||||
NovaEmbedIE,
|
||||
@@ -1558,12 +1527,12 @@
|
||||
PixivSketchIE,
|
||||
PixivSketchUserIE,
|
||||
)
|
||||
from .pladform import PladformIE
|
||||
from .planetmarathi import PlanetMarathiIE
|
||||
from .platzi import (
|
||||
PlatziCourseIE,
|
||||
PlatziIE,
|
||||
)
|
||||
from .playerfm import PlayerFmIE
|
||||
from .playplustv import PlayPlusTVIE
|
||||
from .playsuisse import PlaySuisseIE
|
||||
from .playtvak import PlaytvakIE
|
||||
@@ -1574,6 +1543,7 @@
|
||||
)
|
||||
from .plutotv import PlutoTVIE
|
||||
from .plvideo import PlVideoIE
|
||||
from .plyr import PlyrEmbedIE
|
||||
from .podbayfm import (
|
||||
PodbayFMChannelIE,
|
||||
PodbayFMIE,
|
||||
@@ -1789,6 +1759,7 @@
|
||||
RTVEALaCartaIE,
|
||||
RTVEAudioIE,
|
||||
RTVELiveIE,
|
||||
RTVEProgramIE,
|
||||
RTVETelevisionIE,
|
||||
)
|
||||
from .rtvs import RTVSIE
|
||||
@@ -1830,6 +1801,7 @@
|
||||
from .saitosan import SaitosanIE
|
||||
from .samplefocus import SampleFocusIE
|
||||
from .sapo import SapoIE
|
||||
from .sauceplus import SaucePlusIE
|
||||
from .sbs import SBSIE
|
||||
from .sbscokr import (
|
||||
SBSCoKrAllvodProgramIE,
|
||||
@@ -1872,6 +1844,7 @@
|
||||
from .sharepoint import SharePointIE
|
||||
from .sharevideos import ShareVideosEmbedIE
|
||||
from .shemaroome import ShemarooMeIE
|
||||
from .shiey import ShieyIE
|
||||
from .showroomlive import ShowRoomLiveIE
|
||||
from .sibnet import SibnetEmbedIE
|
||||
from .simplecast import (
|
||||
@@ -1936,12 +1909,13 @@
|
||||
SoundgasmProfileIE,
|
||||
)
|
||||
from .southpark import (
|
||||
SouthParkComBrIE,
|
||||
SouthParkCoUkIE,
|
||||
SouthParkDeIE,
|
||||
SouthParkDkIE,
|
||||
SouthParkEsIE,
|
||||
SouthParkIE,
|
||||
SouthParkLatIE,
|
||||
SouthParkNlIE,
|
||||
)
|
||||
from .sovietscloset import (
|
||||
SovietsClosetIE,
|
||||
@@ -1952,10 +1926,6 @@
|
||||
SpankBangPlaylistIE,
|
||||
)
|
||||
from .spiegel import SpiegelIE
|
||||
from .spike import (
|
||||
BellatorIE,
|
||||
ParamountNetworkIE,
|
||||
)
|
||||
from .sport5 import Sport5IE
|
||||
from .sportbox import SportBoxIE
|
||||
from .sportdeutschland import SportDeutschlandIE
|
||||
@@ -1989,6 +1959,7 @@
|
||||
from .startv import StarTVIE
|
||||
from .steam import (
|
||||
SteamCommunityBroadcastIE,
|
||||
SteamCommunityIE,
|
||||
SteamIE,
|
||||
)
|
||||
from .stitcher import (
|
||||
@@ -2101,6 +2072,7 @@
|
||||
TheGuardianPodcastIE,
|
||||
TheGuardianPodcastPlaylistIE,
|
||||
)
|
||||
from .thehighwire import TheHighWireIE
|
||||
from .theholetv import TheHoleTvIE
|
||||
from .theintercept import TheInterceptIE
|
||||
from .theplatform import (
|
||||
@@ -2170,7 +2142,6 @@
|
||||
from .trueid import TrueIDIE
|
||||
from .trunews import TruNewsIE
|
||||
from .truth import TruthIE
|
||||
from .trutv import TruTVIE
|
||||
from .tube8 import Tube8IE
|
||||
from .tubetugraz import (
|
||||
TubeTuGrazIE,
|
||||
@@ -2220,7 +2191,6 @@
|
||||
from .tver import TVerIE
|
||||
from .tvigle import TvigleIE
|
||||
from .tviplayer import TVIPlayerIE
|
||||
from .tvland import TVLandIE
|
||||
from .tvn24 import TVN24IE
|
||||
from .tvnoe import TVNoeIE
|
||||
from .tvopengr import (
|
||||
@@ -2241,6 +2211,7 @@
|
||||
from .tvplayer import TVPlayerIE
|
||||
from .tvw import (
|
||||
TvwIE,
|
||||
TvwNewsIE,
|
||||
TvwTvChannelsIE,
|
||||
)
|
||||
from .tweakers import TweakersIE
|
||||
@@ -2289,6 +2260,7 @@
|
||||
)
|
||||
from .umg import UMGDeIE
|
||||
from .unistra import UnistraIE
|
||||
from .unitednations import UnitedNationsWebTvIE
|
||||
from .unity import UnityIE
|
||||
from .unsupported import (
|
||||
KnownDRMIE,
|
||||
@@ -2316,10 +2288,6 @@
|
||||
from .vbox7 import Vbox7IE
|
||||
from .veo import VeoIE
|
||||
from .vesti import VestiIE
|
||||
from .vevo import (
|
||||
VevoIE,
|
||||
VevoPlaylistIE,
|
||||
)
|
||||
from .vgtv import (
|
||||
VGTVIE,
|
||||
BTArticleIE,
|
||||
|
||||
@@ -48,7 +48,6 @@
|
||||
'username_field': 'user',
|
||||
'password_field': 'passwd',
|
||||
'login_hostname': 'login.xfinity.com',
|
||||
'needs_newer_ua': True,
|
||||
},
|
||||
'TWC': {
|
||||
'name': 'Time Warner Cable | Spectrum',
|
||||
@@ -1379,11 +1378,8 @@ def _download_webpage_handle(self, *args, **kwargs):
|
||||
|
||||
@staticmethod
|
||||
def _get_mso_headers(mso_info):
|
||||
# yt-dlp's default user-agent is usually too old for some MSO's like Comcast_SSO
|
||||
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
|
||||
return {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0',
|
||||
} if mso_info.get('needs_newer_ua') else {}
|
||||
# Not needed currently
|
||||
return {}
|
||||
|
||||
@staticmethod
|
||||
def _get_mvpd_resource(provider_id, title, guid, rating):
|
||||
|
||||
@@ -1,285 +1,100 @@
|
||||
import functools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ISO639Utils,
|
||||
OnDemandPagedList,
|
||||
clean_html,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
parse_duration,
|
||||
str_or_none,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class AdobeTVBaseIE(InfoExtractor):
|
||||
def _call_api(self, path, video_id, query, note=None):
|
||||
return self._download_json(
|
||||
'http://tv.adobe.com/api/v4/' + path,
|
||||
video_id, note, query=query)['data']
|
||||
|
||||
def _parse_subtitles(self, video_data, url_key):
|
||||
subtitles = {}
|
||||
for translation in video_data.get('translations', []):
|
||||
vtt_path = translation.get(url_key)
|
||||
if not vtt_path:
|
||||
continue
|
||||
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'ext': 'vtt',
|
||||
'url': vtt_path,
|
||||
})
|
||||
return subtitles
|
||||
|
||||
def _parse_video_data(self, video_data):
|
||||
video_id = str(video_data['id'])
|
||||
title = video_data['title']
|
||||
|
||||
s3_extracted = False
|
||||
formats = []
|
||||
for source in video_data.get('videos', []):
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
f = {
|
||||
'format_id': source.get('quality_level'),
|
||||
'fps': int_or_none(source.get('frame_rate')),
|
||||
'height': int_or_none(source.get('height')),
|
||||
'tbr': int_or_none(source.get('video_data_rate')),
|
||||
'width': int_or_none(source.get('width')),
|
||||
'url': source_url,
|
||||
}
|
||||
original_filename = source.get('original_filename')
|
||||
if original_filename:
|
||||
if not (f.get('height') and f.get('width')):
|
||||
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
|
||||
if mobj:
|
||||
f.update({
|
||||
'height': int(mobj.group(2)),
|
||||
'width': int(mobj.group(1)),
|
||||
})
|
||||
if original_filename.startswith('s3://') and not s3_extracted:
|
||||
formats.append({
|
||||
'format_id': 'original',
|
||||
'quality': 1,
|
||||
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
|
||||
})
|
||||
s3_extracted = True
|
||||
formats.append(f)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('thumbnail'),
|
||||
'upload_date': unified_strdate(video_data.get('start_date')),
|
||||
'duration': parse_duration(video_data.get('duration')),
|
||||
'view_count': str_to_int(video_data.get('playcount')),
|
||||
'formats': formats,
|
||||
'subtitles': self._parse_subtitles(video_data, 'vtt'),
|
||||
}
|
||||
|
||||
|
||||
class AdobeTVEmbedIE(AdobeTVBaseIE):
|
||||
IE_NAME = 'adobetv:embed'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://tv.adobe.com/embed/22/4153',
|
||||
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
|
||||
'info_dict': {
|
||||
'id': '4153',
|
||||
'ext': 'flv',
|
||||
'title': 'Creating Graphics Optimized for BlackBerry',
|
||||
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
'upload_date': '20091109',
|
||||
'duration': 377,
|
||||
'view_count': int,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video_data = self._call_api(
|
||||
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
|
||||
return self._parse_video_data(video_data)
|
||||
|
||||
|
||||
class AdobeTVIE(AdobeTVBaseIE):
|
||||
class AdobeTVVideoIE(InfoExtractor):
|
||||
IE_NAME = 'adobetv'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
|
||||
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
|
||||
'info_dict': {
|
||||
'id': '10981',
|
||||
'ext': 'mp4',
|
||||
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
|
||||
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
|
||||
'thumbnail': r're:https?://.*\.jpg$',
|
||||
'upload_date': '20110914',
|
||||
'duration': 60,
|
||||
'view_count': int,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, show_urlname, urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
|
||||
video_data = self._call_api(
|
||||
'episode/get', urlname, {
|
||||
'disclosure': 'standard',
|
||||
'language': language,
|
||||
'show_urlname': show_urlname,
|
||||
'urlname': urlname,
|
||||
})[0]
|
||||
return self._parse_video_data(video_data)
|
||||
|
||||
|
||||
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
|
||||
_PAGE_SIZE = 25
|
||||
|
||||
def _fetch_page(self, display_id, query, page):
|
||||
page += 1
|
||||
query['page'] = page
|
||||
for element_data in self._call_api(
|
||||
self._RESOURCE, display_id, query, f'Download Page {page}'):
|
||||
yield self._process_data(element_data)
|
||||
|
||||
def _extract_playlist_entries(self, display_id, query):
|
||||
return OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, display_id, query), self._PAGE_SIZE)
|
||||
|
||||
|
||||
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
|
||||
IE_NAME = 'adobetv:show'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
|
||||
'info_dict': {
|
||||
'id': '36',
|
||||
'title': 'The Complete Picture with Julieanne Kost',
|
||||
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
|
||||
},
|
||||
'playlist_mincount': 136,
|
||||
}
|
||||
_RESOURCE = 'episode'
|
||||
_process_data = AdobeTVBaseIE._parse_video_data
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, show_urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = {
|
||||
'disclosure': 'standard',
|
||||
'language': language,
|
||||
'show_urlname': show_urlname,
|
||||
}
|
||||
|
||||
show_data = self._call_api(
|
||||
'show/get', show_urlname, query)[0]
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(show_urlname, query),
|
||||
str_or_none(show_data.get('id')),
|
||||
show_data.get('show_name'),
|
||||
show_data.get('show_description'))
|
||||
|
||||
|
||||
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
|
||||
IE_NAME = 'adobetv:channel'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/channel/development',
|
||||
'info_dict': {
|
||||
'id': 'development',
|
||||
},
|
||||
'playlist_mincount': 96,
|
||||
}
|
||||
_RESOURCE = 'show'
|
||||
|
||||
def _process_data(self, show_data):
|
||||
return self.url_result(
|
||||
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = {
|
||||
'channel_urlname': channel_urlname,
|
||||
'language': language,
|
||||
}
|
||||
if category_urlname:
|
||||
query['category_urlname'] = category_urlname
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(channel_urlname, query),
|
||||
channel_urlname)
|
||||
|
||||
|
||||
class AdobeTVVideoIE(AdobeTVBaseIE):
|
||||
IE_NAME = 'adobetv:video'
|
||||
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
|
||||
|
||||
_TEST = {
|
||||
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
|
||||
'url': 'https://video.tv.adobe.com/v/2456/',
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+)']
|
||||
_TESTS = [{
|
||||
'url': 'https://video.tv.adobe.com/v/2456',
|
||||
'md5': '43662b577c018ad707a63766462b1e87',
|
||||
'info_dict': {
|
||||
'id': '2456',
|
||||
'ext': 'mp4',
|
||||
'title': 'New experience with Acrobat DC',
|
||||
'description': 'New experience with Acrobat DC',
|
||||
'duration': 248.667,
|
||||
'duration': 248.522,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://video.tv.adobe.com/v/3463980/adobe-acrobat',
|
||||
'info_dict': {
|
||||
'id': '3463980',
|
||||
'ext': 'mp4',
|
||||
'title': 'Adobe Acrobat: How to Customize the Toolbar for Faster PDF Editing',
|
||||
'description': 'md5:94368ab95ae24f9c1bee0cb346e03dc3',
|
||||
'duration': 97.514,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# https://video.tv.adobe.com/v/3442499
|
||||
'url': 'https://business.adobe.com/dx-fragments/summit/2025/marquees/S335/ondemand.live.html',
|
||||
'info_dict': {
|
||||
'id': '3442499',
|
||||
'ext': 'mp4',
|
||||
'title': 'S335 - Beyond Personalization: Creating Intent-Based Experiences at Scale',
|
||||
'description': 'Beyond Personalization: Creating Intent-Based Experiences at Scale',
|
||||
'duration': 2906.8,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_data = self._parse_json(self._search_regex(
|
||||
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
|
||||
title = video_data['title']
|
||||
video_data = self._search_json(
|
||||
r'var\s+bridge\s*=', webpage, 'bridged data', video_id)
|
||||
|
||||
formats = []
|
||||
sources = video_data.get('sources') or []
|
||||
for source in sources:
|
||||
source_src = source.get('src')
|
||||
if not source_src:
|
||||
continue
|
||||
formats.append({
|
||||
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
|
||||
'format_id': join_nonempty(source.get('format'), source.get('label')),
|
||||
'height': int_or_none(source.get('height') or None),
|
||||
'tbr': int_or_none(source.get('bitrate') or None),
|
||||
'width': int_or_none(source.get('width') or None),
|
||||
'url': source_src,
|
||||
})
|
||||
for source in traverse_obj(video_data, (
|
||||
'sources', lambda _, v: v['format'] != 'playlist' and url_or_none(v['src']),
|
||||
)):
|
||||
source_url = self._proto_relative_url(source['src'])
|
||||
if determine_ext(source_url) == 'm3u8':
|
||||
fmts = self._extract_m3u8_formats(
|
||||
source_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
else:
|
||||
fmts = [{'url': source_url}]
|
||||
|
||||
# For both metadata and downloaded files the duration varies among
|
||||
# formats. I just pick the max one
|
||||
duration = max(filter(None, [
|
||||
float_or_none(source.get('duration'), scale=1000)
|
||||
for source in sources]))
|
||||
for fmt in fmts:
|
||||
fmt.update(traverse_obj(source, {
|
||||
'duration': ('duration', {float_or_none(scale=1000)}),
|
||||
'filesize': ('kilobytes', {float_or_none(invscale=1000)}),
|
||||
'format_id': (('format', 'label'), {str}, all, {lambda x: join_nonempty(*x)}),
|
||||
'height': ('height', {int_or_none}),
|
||||
'tbr': ('bitrate', {int_or_none}),
|
||||
'width': ('width', {int_or_none}),
|
||||
}))
|
||||
formats.extend(fmts)
|
||||
|
||||
subtitles = {}
|
||||
for translation in traverse_obj(video_data, (
|
||||
'translations', lambda _, v: url_or_none(v['vttPath']),
|
||||
)):
|
||||
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation.get('language_medium')) or 'und'
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'ext': 'vtt',
|
||||
'url': self._proto_relative_url(translation['vttPath']),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('video', {}).get('poster'),
|
||||
'duration': duration,
|
||||
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(video_data, {
|
||||
'title': ('title', {clean_html}),
|
||||
'description': ('description', {clean_html}, filter),
|
||||
'thumbnail': ('video', 'poster', {self._proto_relative_url}, {url_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
@@ -111,11 +111,9 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
IE_NAME = 'aenetworks'
|
||||
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
|
||||
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
|
||||
shows/[^/]+/season-\d+/episode-\d+|
|
||||
(?:
|
||||
(?:movie|special)s/[^/]+|
|
||||
(?:shows/[^/]+/)?videos
|
||||
)/[^/?#&]+
|
||||
shows/[^/?#]+/season-\d+/episode-\d+|
|
||||
(?P<type>movie|special)s/[^/?#]+(?P<extra>/[^/?#]+)?|
|
||||
(?:shows/[^/?#]+/)?videos/[^/?#]+
|
||||
)'''
|
||||
_TESTS = [{
|
||||
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
|
||||
@@ -128,7 +126,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
'upload_date': '20120529',
|
||||
'uploader': 'AENE-NEW',
|
||||
'duration': 2592.0,
|
||||
'thumbnail': r're:^https?://.*\.jpe?g$',
|
||||
'thumbnail': r're:https?://.+/.+\.jpg',
|
||||
'chapters': 'count:5',
|
||||
'tags': 'count:14',
|
||||
'categories': ['Mountain Men'],
|
||||
@@ -139,10 +137,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
'series': 'Mountain Men',
|
||||
'age_limit': 0,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'add_ie': ['ThePlatform'],
|
||||
'skip': 'Geo-restricted - This content is not available in your location.',
|
||||
}, {
|
||||
@@ -156,7 +151,7 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
'upload_date': '20160112',
|
||||
'uploader': 'AENE-NEW',
|
||||
'duration': 1277.695,
|
||||
'thumbnail': r're:^https?://.*\.jpe?g$',
|
||||
'thumbnail': r're:https?://.+/.+\.jpg',
|
||||
'chapters': 'count:4',
|
||||
'tags': 'count:23',
|
||||
'episode': 'Inlawful Entry',
|
||||
@@ -166,10 +161,53 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
'series': 'Duck Dynasty',
|
||||
'age_limit': 0,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'add_ie': ['ThePlatform'],
|
||||
}, {
|
||||
'url': 'https://play.mylifetime.com/movies/v-c-andrews-web-of-dreams',
|
||||
'info_dict': {
|
||||
'id': '1590627395981',
|
||||
'ext': 'mp4',
|
||||
'title': 'VC Andrews\' Web of Dreams',
|
||||
'description': 'md5:2a8ba13ae64271c79eb65c0577d312ce',
|
||||
'uploader': 'AENE-NEW',
|
||||
'age_limit': 14,
|
||||
'duration': 5253.665,
|
||||
'thumbnail': r're:https?://.+/.+\.jpg',
|
||||
'chapters': 'count:8',
|
||||
'tags': ['lifetime', 'mylifetime', 'lifetime channel', "VC Andrews' Web of Dreams"],
|
||||
'series': '',
|
||||
'season': 'Season 0',
|
||||
'season_number': 0,
|
||||
'episode': 'VC Andrews\' Web of Dreams',
|
||||
'episode_number': 0,
|
||||
'timestamp': 1566489703.0,
|
||||
'upload_date': '20190822',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'add_ie': ['ThePlatform'],
|
||||
}, {
|
||||
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story',
|
||||
'info_dict': {
|
||||
'id': '1488235587551',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hunting JonBenet\'s Killer: The Untold Story',
|
||||
'description': 'md5:209869425ee392d74fe29201821e48b4',
|
||||
'uploader': 'AENE-NEW',
|
||||
'age_limit': 14,
|
||||
'duration': 5003.903,
|
||||
'thumbnail': r're:https?://.+/.+\.jpg',
|
||||
'chapters': 'count:10',
|
||||
'tags': 'count:11',
|
||||
'series': '',
|
||||
'season': 'Season 0',
|
||||
'season_number': 0,
|
||||
'episode': 'Hunting JonBenet\'s Killer: The Untold Story',
|
||||
'episode_number': 0,
|
||||
'timestamp': 1554987697.0,
|
||||
'upload_date': '20190411',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'add_ie': ['ThePlatform'],
|
||||
}, {
|
||||
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
|
||||
@@ -198,7 +236,9 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, canonical = self._match_valid_url(url).groups()
|
||||
domain, canonical, url_type, extra = self._match_valid_url(url).group('domain', 'id', 'type', 'extra')
|
||||
if url_type in ('movie', 'special') and not extra:
|
||||
canonical += f'/full-{url_type}'
|
||||
return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
|
||||
|
||||
|
||||
|
||||
@@ -11,12 +11,11 @@ class APAIE(InfoExtractor):
|
||||
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
|
||||
_TESTS = [{
|
||||
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
|
||||
'info_dict': {
|
||||
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'ext': 'mp4',
|
||||
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
|
||||
@@ -28,6 +27,15 @@ class APAIE(InfoExtractor):
|
||||
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.vol.at/blue-man-group/5593454',
|
||||
'info_dict': {
|
||||
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'ext': 'mp4',
|
||||
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
dict_get,
|
||||
extract_attributes,
|
||||
get_element_by_id,
|
||||
get_element_text_and_html_by_tag,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
js_to_json,
|
||||
@@ -32,7 +33,6 @@
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
urlhandle_detect_ext,
|
||||
variadic,
|
||||
)
|
||||
|
||||
|
||||
@@ -72,6 +72,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'display_id': 'Cops-v2.mp4',
|
||||
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
|
||||
'duration': 1091.96,
|
||||
'track': 'Cops-v2',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
@@ -86,6 +87,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
|
||||
'duration': 59.77,
|
||||
'display_id': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
|
||||
'track': 'Commercial-JFK1960ElectionAdCampaignJingle',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
|
||||
@@ -102,6 +104,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'duration': 59.51,
|
||||
'license': 'http://creativecommons.org/licenses/publicdomain/',
|
||||
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
|
||||
'track': 'Commercial-Nixon1960ElectionAdToughonDefense',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
|
||||
@@ -182,6 +185,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'duration': 130.46,
|
||||
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_01_000117.jpg',
|
||||
'display_id': 'irelandthemakingofarepublicreel1_01.mov',
|
||||
'track': 'irelandthemakingofarepublicreel1 01',
|
||||
},
|
||||
}, {
|
||||
'md5': '67335ee3b23a0da930841981c1e79b02',
|
||||
@@ -192,6 +196,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'title': 'irelandthemakingofarepublicreel1_02.mov',
|
||||
'display_id': 'irelandthemakingofarepublicreel1_02.mov',
|
||||
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_02_001374.jpg',
|
||||
'track': 'irelandthemakingofarepublicreel1 02',
|
||||
},
|
||||
}, {
|
||||
'md5': 'e470e86787893603f4a341a16c281eb5',
|
||||
@@ -202,6 +207,7 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'title': 'irelandthemakingofarepublicreel2.mov',
|
||||
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
|
||||
'display_id': 'irelandthemakingofarepublicreel2.mov',
|
||||
'track': 'irelandthemakingofarepublicreel2',
|
||||
},
|
||||
},
|
||||
],
|
||||
@@ -225,19 +231,29 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'release_date': '19950402',
|
||||
'timestamp': 1084927901,
|
||||
},
|
||||
}, {
|
||||
# metadata['metadata']['description'] is a list of strings instead of str
|
||||
'url': 'https://archive.org/details/pra-KZ1908.02',
|
||||
'info_dict': {
|
||||
'id': 'pra-KZ1908.02',
|
||||
'ext': 'mp3',
|
||||
'display_id': 'KZ1908.02_01.wav',
|
||||
'title': 'Crips and Bloods speak about gang life',
|
||||
'description': 'md5:2b56b35ff021311e3554b47a285e70b3',
|
||||
'uploader': 'jake@archive.org',
|
||||
'duration': 1733.74,
|
||||
'track': 'KZ1908.02 01',
|
||||
'track_number': 1,
|
||||
'timestamp': 1336026026,
|
||||
'upload_date': '20120503',
|
||||
'release_year': 1992,
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _playlist_data(webpage):
|
||||
element = re.findall(r'''(?xs)
|
||||
<input
|
||||
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
|
||||
\s+class=['"]?js-play8-playlist['"]?
|
||||
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
|
||||
\s*/>
|
||||
''', webpage)[0]
|
||||
|
||||
return json.loads(extract_attributes(element)['value'])
|
||||
element = get_element_text_and_html_by_tag('play-av', webpage)[1]
|
||||
return json.loads(extract_attributes(element)['playlist'])
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = urllib.parse.unquote_plus(self._match_id(url))
|
||||
@@ -274,34 +290,40 @@ def _real_extract(self, url):
|
||||
m = metadata['metadata']
|
||||
identifier = m['identifier']
|
||||
|
||||
info = {
|
||||
info = traverse_obj(m, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
|
||||
'uploader': (('uploader', 'adder'), {str}, any),
|
||||
'creators': ('creator', (None, ...), {str}, filter, all, filter),
|
||||
'license': ('licenseurl', {url_or_none}),
|
||||
'release_date': ('date', {unified_strdate}),
|
||||
'timestamp': (('publicdate', 'addeddate'), {unified_timestamp}, any),
|
||||
'location': ('venue', {str}),
|
||||
'release_year': ('year', {int_or_none}),
|
||||
})
|
||||
info.update({
|
||||
'id': identifier,
|
||||
'title': m['title'],
|
||||
'description': clean_html(m.get('description')),
|
||||
'uploader': dict_get(m, ['uploader', 'adder']),
|
||||
'creators': traverse_obj(m, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
|
||||
'license': m.get('licenseurl'),
|
||||
'release_date': unified_strdate(m.get('date')),
|
||||
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
|
||||
'webpage_url': f'https://archive.org/details/{identifier}',
|
||||
'location': m.get('venue'),
|
||||
'release_year': int_or_none(m.get('year'))}
|
||||
})
|
||||
|
||||
for f in metadata['files']:
|
||||
if f['name'] in entries:
|
||||
entries[f['name']] = merge_dicts(entries[f['name']], {
|
||||
'id': identifier + '/' + f['name'],
|
||||
'title': f.get('title') or f['name'],
|
||||
'display_id': f['name'],
|
||||
'description': clean_html(f.get('description')),
|
||||
'creators': traverse_obj(f, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
|
||||
'duration': parse_duration(f.get('length')),
|
||||
'track_number': int_or_none(f.get('track')),
|
||||
'album': f.get('album'),
|
||||
'discnumber': int_or_none(f.get('disc')),
|
||||
'release_year': int_or_none(f.get('year'))})
|
||||
**traverse_obj(f, {
|
||||
'title': (('title', 'name'), {str}, any),
|
||||
'display_id': ('name', {str}),
|
||||
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
|
||||
'creators': ('creator', (None, ...), {str}, filter, all, filter),
|
||||
'duration': ('length', {parse_duration}),
|
||||
'track_number': ('track', {int_or_none}),
|
||||
'album': ('album', {str}),
|
||||
'discnumber': ('disc', {int_or_none}),
|
||||
'release_year': ('year', {int_or_none}),
|
||||
}),
|
||||
})
|
||||
entry = entries[f['name']]
|
||||
elif traverse_obj(f, 'original', expected_type=str) in entries:
|
||||
elif traverse_obj(f, ('original', {str})) in entries:
|
||||
entry = entries[f['original']]
|
||||
else:
|
||||
continue
|
||||
|
||||
@@ -62,6 +62,20 @@ class ArcPublishingIE(InfoExtractor):
|
||||
'url': 'arcpublishing:tronc:460f2931-8130-4719-8ea1-ffcb2d7cb685',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.uppermichiganssource.com/2025/07/18/scattered-showers-storms-bring-heavy-rain-potential/',
|
||||
'info_dict': {
|
||||
'id': '508116f7-e999-48db-b7c2-60a04842679b',
|
||||
'ext': 'mp4',
|
||||
'title': 'Scattered showers & storms bring heavy rain potential',
|
||||
'description': 'Scattered showers & storms bring heavy rain potential',
|
||||
'duration': 2016,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'timestamp': 1752881287,
|
||||
'upload_date': '20250718',
|
||||
},
|
||||
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
|
||||
}]
|
||||
_POWA_DEFAULTS = [
|
||||
(['cmg', 'prisa'], '%s-config-prod.api.cdn.arcpublishing.com/video'),
|
||||
([
|
||||
|
||||
@@ -1,150 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
parse_qs,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class ArkenaIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
|
||||
play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
|
||||
)
|
||||
'''
|
||||
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
|
||||
_TESTS = [{
|
||||
'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
|
||||
'md5': '97f117754e5f3c020f5f26da4a44ebaf',
|
||||
'info_dict': {
|
||||
'id': 'd8ab4607-00090107-aab86310',
|
||||
'ext': 'mp4',
|
||||
'title': 'EM_HT20_117_roslund_v2.mp4',
|
||||
'timestamp': 1608285912,
|
||||
'upload_date': '20201218',
|
||||
'duration': 1429.162667,
|
||||
'subtitles': {
|
||||
'sv': 'count:3',
|
||||
},
|
||||
},
|
||||
}, {
|
||||
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
video_id = mobj.group('id')
|
||||
account_id = mobj.group('account_id')
|
||||
|
||||
# Handle http://video.arkena.com/play2/embed/player URL
|
||||
if not video_id:
|
||||
qs = parse_qs(url)
|
||||
video_id = qs.get('mediaId', [None])[0]
|
||||
account_id = qs.get('accountId', [None])[0]
|
||||
if not video_id or not account_id:
|
||||
raise ExtractorError('Invalid URL', expected=True)
|
||||
|
||||
media = self._download_json(
|
||||
f'https://video.qbrick.com/api/v1/public/accounts/{account_id}/medias/{video_id}',
|
||||
video_id, query={
|
||||
# https://video.qbrick.com/docs/api/examples/library-api.html
|
||||
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
|
||||
})
|
||||
metadata = media.get('metadata') or {}
|
||||
title = metadata['title']
|
||||
|
||||
duration = None
|
||||
formats = []
|
||||
thumbnails = []
|
||||
subtitles = {}
|
||||
for resource in media['asset']['resources']:
|
||||
for rendition in (resource.get('renditions') or []):
|
||||
rendition_type = rendition.get('type')
|
||||
for i, link in enumerate(rendition.get('links') or []):
|
||||
href = link.get('href')
|
||||
if not href:
|
||||
continue
|
||||
if rendition_type == 'image':
|
||||
thumbnails.append({
|
||||
'filesize': int_or_none(rendition.get('size')),
|
||||
'height': int_or_none(rendition.get('height')),
|
||||
'id': rendition.get('id'),
|
||||
'url': href,
|
||||
'width': int_or_none(rendition.get('width')),
|
||||
})
|
||||
elif rendition_type == 'subtitle':
|
||||
subtitles.setdefault(rendition.get('language') or 'en', []).append({
|
||||
'url': href,
|
||||
})
|
||||
elif rendition_type == 'video':
|
||||
f = {
|
||||
'filesize': int_or_none(rendition.get('size')),
|
||||
'format_id': rendition.get('id'),
|
||||
'url': href,
|
||||
}
|
||||
video = try_get(rendition, lambda x: x['videos'][i], dict)
|
||||
if video:
|
||||
if not duration:
|
||||
duration = float_or_none(video.get('duration'))
|
||||
f.update({
|
||||
'height': int_or_none(video.get('height')),
|
||||
'tbr': int_or_none(video.get('bitrate'), 1000),
|
||||
'vcodec': video.get('codec'),
|
||||
'width': int_or_none(video.get('width')),
|
||||
})
|
||||
audio = try_get(video, lambda x: x['audios'][0], dict)
|
||||
if audio:
|
||||
f.update({
|
||||
'acodec': audio.get('codec'),
|
||||
'asr': int_or_none(audio.get('sampleRate')),
|
||||
})
|
||||
formats.append(f)
|
||||
elif rendition_type == 'index':
|
||||
mime_type = link.get('mimeType')
|
||||
if mime_type == 'application/smil+xml':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
href, video_id, fatal=False))
|
||||
elif mime_type == 'application/x-mpegURL':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
href, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif mime_type == 'application/hds+xml':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
href, video_id, f4m_id='hds', fatal=False))
|
||||
elif mime_type == 'application/dash+xml':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
href, video_id, mpd_id='dash', fatal=False))
|
||||
elif mime_type == 'application/vnd.ms-sstr+xml':
|
||||
formats.extend(self._extract_ism_formats(
|
||||
href, video_id, ism_id='mss', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': metadata.get('description'),
|
||||
'timestamp': parse_iso8601(media.get('created')),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'duration': duration,
|
||||
'tags': media.get('tags'),
|
||||
'formats': formats,
|
||||
}
|
||||
@@ -51,8 +51,8 @@ class ArteTVIE(ArteTVBaseIE):
|
||||
'id': '109067-000-A',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:d2ca367b8ecee028dddaa8bd1aebc739',
|
||||
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
|
||||
'timestamp': 1713927600,
|
||||
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/3rR6PLzfbigSkkeHtkCZNF/940x530',
|
||||
'duration': 7599,
|
||||
'title': 'La loi de Téhéran',
|
||||
'upload_date': '20240424',
|
||||
@@ -62,6 +62,7 @@ class ArteTVIE(ArteTVBaseIE):
|
||||
'fr-forced': 'mincount:1',
|
||||
},
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
'note': 'age-restricted',
|
||||
'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
|
||||
@@ -69,9 +70,9 @@ class ArteTVIE(ArteTVBaseIE):
|
||||
'id': '006785-000-A',
|
||||
'description': 'md5:c2f94fdfefc8a280e4dab68ab96ab0ba',
|
||||
'title': 'The Element of Crime',
|
||||
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
|
||||
'timestamp': 1696111200,
|
||||
'duration': 5849,
|
||||
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/q82dTTfyuCXupPsGxXsd7B/940x530',
|
||||
'upload_date': '20230930',
|
||||
'ext': 'mp4',
|
||||
},
|
||||
@@ -252,6 +253,30 @@ class ArteTVEmbedIE(InfoExtractor):
|
||||
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://timesofmalta.com/article/watch-sunken-warships-north-sea-arte.1108358',
|
||||
'info_dict': {
|
||||
'id': '110288-000-A',
|
||||
'ext': 'mp4',
|
||||
'title': 'Danger on the Seabed',
|
||||
'alt_title': 'Sunken Warships in the North Sea',
|
||||
'description': 'md5:a2c84cbad37d280bddb6484087120add',
|
||||
'duration': 3148,
|
||||
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
|
||||
'timestamp': 1741686820,
|
||||
'upload_date': '20250311',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.eurockeennes.fr/en-live/',
|
||||
'info_dict': {
|
||||
'id': 'en-live',
|
||||
'title': 'Les Eurocks en live | Les Eurockéennes de Belfort – 3-4-5-6 juillet 2025 sur la Presqu'Île du Malsaucy',
|
||||
},
|
||||
'playlist_count': 4,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
qs = parse_qs(url)
|
||||
@@ -304,9 +329,9 @@ class ArteTVCategoryIE(ArteTVBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'politics-and-society',
|
||||
'title': 'Politics and society',
|
||||
'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
|
||||
'description': 'Watch documentaries and reportage about politics, society and current affairs.',
|
||||
},
|
||||
'playlist_mincount': 13,
|
||||
'playlist_mincount': 3,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
jwt_encode_hs256,
|
||||
jwt_encode,
|
||||
try_get,
|
||||
)
|
||||
|
||||
@@ -83,11 +83,10 @@ def _real_extract(self, url):
|
||||
'nbf': int(not_before.timestamp()),
|
||||
'exp': int(expire.timestamp()),
|
||||
}
|
||||
jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
|
||||
videos = self._download_json(
|
||||
'https://vas-v4.p7s1video.net/4.0/getsources',
|
||||
content_id, 'Downloading videos JSON', query={
|
||||
'token': jwt_token.decode('utf-8'),
|
||||
'token': jwt_encode(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID}),
|
||||
})
|
||||
|
||||
video_id, videos_data = next(iter(videos['data'].items()))
|
||||
|
||||
@@ -1,33 +0,0 @@
|
||||
from .brightcove import BrightcoveNewBaseIE
|
||||
from ..utils import extract_attributes
|
||||
|
||||
|
||||
class BandaiChannelIE(BrightcoveNewBaseIE):
|
||||
IE_NAME = 'bandaichannel'
|
||||
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.b-ch.com/titles/514/001',
|
||||
'md5': 'a0f2d787baa5729bed71108257f613a4',
|
||||
'info_dict': {
|
||||
'id': '6128044564001',
|
||||
'ext': 'mp4',
|
||||
'title': 'メタルファイターMIKU 第1話',
|
||||
'timestamp': 1580354056,
|
||||
'uploader_id': '5797077852001',
|
||||
'upload_date': '20200130',
|
||||
'duration': 1387.733,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
attrs = extract_attributes(self._search_regex(
|
||||
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
|
||||
bc = self._download_json(
|
||||
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
|
||||
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
|
||||
return self._parse_brightcove_metadata(bc, bc['id'])
|
||||
@@ -7,6 +7,7 @@
|
||||
from ..utils import (
|
||||
KNOWN_EXTENSIONS,
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
@@ -19,7 +20,7 @@
|
||||
url_or_none,
|
||||
urljoin,
|
||||
)
|
||||
from ..utils.traversal import find_element, traverse_obj
|
||||
from ..utils.traversal import find_element, find_elements, traverse_obj
|
||||
|
||||
|
||||
class BandcampIE(InfoExtractor):
|
||||
@@ -35,14 +36,12 @@ class BandcampIE(InfoExtractor):
|
||||
'duration': 9.8485,
|
||||
'uploader': 'youtube-dl "\'/\\ä↭',
|
||||
'upload_date': '20121129',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1354224127,
|
||||
'track': 'youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
|
||||
'album_artist': 'youtube-dl "\'/\\ä↭',
|
||||
'track_id': '1812978515',
|
||||
'artist': 'youtube-dl "\'/\\ä↭',
|
||||
'uploader_url': 'https://youtube-dl.bandcamp.com',
|
||||
'uploader_id': 'youtube-dl',
|
||||
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
|
||||
'artists': ['youtube-dl "\'/\\ä↭'],
|
||||
'album_artists': ['youtube-dl "\'/\\ä↭'],
|
||||
},
|
||||
@@ -53,10 +52,9 @@ class BandcampIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '2650410135',
|
||||
'ext': 'm4a',
|
||||
'acodec': r're:[fa]lac',
|
||||
'title': 'Ben Prunty - Lanius (Battle)',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'Ben Prunty',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1396508491,
|
||||
'upload_date': '20140403',
|
||||
'release_timestamp': 1396483200,
|
||||
@@ -65,11 +63,12 @@ class BandcampIE(InfoExtractor):
|
||||
'track': 'Lanius (Battle)',
|
||||
'track_number': 1,
|
||||
'track_id': '2650410135',
|
||||
'artist': 'Ben Prunty',
|
||||
'album_artist': 'Ben Prunty',
|
||||
'album': 'FTL: Advanced Edition Soundtrack',
|
||||
'uploader_url': 'https://benprunty.bandcamp.com',
|
||||
'uploader_id': 'benprunty',
|
||||
'tags': ['soundtrack', 'chiptunes', 'cinematic', 'electronic', 'video game music', 'California'],
|
||||
'artists': ['Ben Prunty'],
|
||||
'album_artists': ['Ben Prunty'],
|
||||
},
|
||||
}, {
|
||||
# no free download, mp3 128
|
||||
@@ -79,8 +78,8 @@ class BandcampIE(InfoExtractor):
|
||||
'id': '2584466013',
|
||||
'ext': 'mp3',
|
||||
'title': 'Mastodon - Hail to Fire',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'Mastodon',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1322005399,
|
||||
'upload_date': '20111122',
|
||||
'release_timestamp': 1076112000,
|
||||
@@ -89,11 +88,12 @@ class BandcampIE(InfoExtractor):
|
||||
'track': 'Hail to Fire',
|
||||
'track_number': 5,
|
||||
'track_id': '2584466013',
|
||||
'artist': 'Mastodon',
|
||||
'album_artist': 'Mastodon',
|
||||
'album': 'Call of the Mastodon',
|
||||
'uploader_url': 'https://relapsealumni.bandcamp.com',
|
||||
'uploader_id': 'relapsealumni',
|
||||
'tags': ['Philadelphia'],
|
||||
'artists': ['Mastodon'],
|
||||
'album_artists': ['Mastodon'],
|
||||
},
|
||||
}, {
|
||||
# track from compilation album (artist/album_artist difference)
|
||||
@@ -103,8 +103,8 @@ class BandcampIE(InfoExtractor):
|
||||
'id': '1978174799',
|
||||
'ext': 'mp3',
|
||||
'title': 'submerse - submerse - Safehouse',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'submerse',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1480779297,
|
||||
'upload_date': '20161203',
|
||||
'release_timestamp': 1481068800,
|
||||
@@ -113,11 +113,36 @@ class BandcampIE(InfoExtractor):
|
||||
'track': 'submerse - Safehouse',
|
||||
'track_number': 3,
|
||||
'track_id': '1978174799',
|
||||
'artist': 'submerse',
|
||||
'album_artist': 'Diskotopia',
|
||||
'album': 'DSK F/W 2016-2017 Free Compilation',
|
||||
'uploader_url': 'https://diskotopia.bandcamp.com',
|
||||
'uploader_id': 'diskotopia',
|
||||
'tags': ['Japan'],
|
||||
'artists': ['submerse'],
|
||||
'album_artists': ['Diskotopia'],
|
||||
},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.punknews.org/article/85809/stay-inside-super-sonic',
|
||||
'info_dict': {
|
||||
'id': '2475540375',
|
||||
'ext': 'mp3',
|
||||
'title': 'Stay Inside - Super Sonic',
|
||||
'album': 'Lunger',
|
||||
'album_artists': ['Stay Inside'],
|
||||
'artists': ['Stay Inside'],
|
||||
'duration': 166.157,
|
||||
'release_date': '20251003',
|
||||
'release_timestamp': 1759449600.0,
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1749473029.0,
|
||||
'track': 'Super Sonic',
|
||||
'track_id': '2475540375',
|
||||
'track_number': 3,
|
||||
'upload_date': '20250609',
|
||||
'uploader': 'Stay Inside',
|
||||
'uploader_id': 'stayinside',
|
||||
'uploader_url': 'https://stayinside.bandcamp.com',
|
||||
},
|
||||
}]
|
||||
|
||||
@@ -252,6 +277,7 @@ def _real_extract(self, url):
|
||||
'album': embed.get('album_title'),
|
||||
'album_artist': album_artist,
|
||||
'formats': formats,
|
||||
'tags': traverse_obj(webpage, ({find_elements(cls='tag')}, ..., {clean_html})),
|
||||
}
|
||||
|
||||
|
||||
@@ -268,10 +294,10 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
|
||||
'id': '1353101989',
|
||||
'ext': 'mp3',
|
||||
'title': 'Blazo - Intro',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1311756226,
|
||||
'upload_date': '20110727',
|
||||
'uploader': 'Blazo',
|
||||
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
|
||||
'album_artists': ['Blazo'],
|
||||
'uploader_url': 'https://blazo.bandcamp.com',
|
||||
'release_date': '20110727',
|
||||
@@ -291,6 +317,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
|
||||
'id': '38097443',
|
||||
'ext': 'mp3',
|
||||
'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
|
||||
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
|
||||
'timestamp': 1311757238,
|
||||
'upload_date': '20110727',
|
||||
'uploader': 'Blazo',
|
||||
@@ -304,7 +331,6 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
|
||||
'uploader_id': 'blazo',
|
||||
'album_artists': ['Blazo'],
|
||||
'artists': ['Blazo'],
|
||||
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
|
||||
'release_timestamp': 1311724800.0,
|
||||
},
|
||||
},
|
||||
|
||||
@@ -1,91 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class BellMediaIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?
|
||||
(?P<domain>
|
||||
(?:
|
||||
ctv|
|
||||
tsn|
|
||||
bnn(?:bloomberg)?|
|
||||
thecomedynetwork|
|
||||
discovery|
|
||||
discoveryvelocity|
|
||||
sciencechannel|
|
||||
investigationdiscovery|
|
||||
animalplanet|
|
||||
bravo|
|
||||
mtv|
|
||||
space|
|
||||
etalk|
|
||||
marilyn
|
||||
)\.ca|
|
||||
(?:much|cp24)\.com
|
||||
)/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
|
||||
'md5': '3e5b8e38370741d5089da79161646635',
|
||||
'info_dict': {
|
||||
'id': '1403070',
|
||||
'ext': 'flv',
|
||||
'title': 'David Cockfield\'s Top Picks',
|
||||
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
|
||||
'upload_date': '20180525',
|
||||
'timestamp': 1527288600,
|
||||
'season_id': '73997',
|
||||
'season': '2018',
|
||||
'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg',
|
||||
'tags': [],
|
||||
'categories': ['ETFs'],
|
||||
'season_number': 8,
|
||||
'duration': 272.038,
|
||||
'series': 'Market Call Tonight',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.etalk.ca/video?videoid=663455',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cp24.com/video?clipId=1982548',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_DOMAINS = {
|
||||
'thecomedynetwork': 'comedy',
|
||||
'discoveryvelocity': 'discvel',
|
||||
'sciencechannel': 'discsci',
|
||||
'investigationdiscovery': 'invdisc',
|
||||
'animalplanet': 'aniplan',
|
||||
'etalk': 'ctv',
|
||||
'bnnbloomberg': 'bnn',
|
||||
'marilyn': 'ctv_marilyn',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, video_id = self._match_valid_url(url).groups()
|
||||
domain = domain.split('.')[0]
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'url': f'9c9media:{self._DOMAINS.get(domain, domain)}_web:{video_id}',
|
||||
'ie_key': 'NineCNineMedia',
|
||||
}
|
||||
@@ -1,79 +1,47 @@
|
||||
from .mtv import MTVServicesInfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
from .mtv import MTVServicesBaseIE
|
||||
|
||||
|
||||
class BetIE(MTVServicesInfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
|
||||
'info_dict': {
|
||||
'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
|
||||
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
|
||||
'ext': 'flv',
|
||||
'title': 'A Conversation With President Obama',
|
||||
'description': 'President Obama urges persistence in confronting racism and bias.',
|
||||
'duration': 1534,
|
||||
'upload_date': '20141208',
|
||||
'thumbnail': r're:(?i)^https?://.*\.jpg$',
|
||||
'subtitles': {
|
||||
'en': 'mincount:2',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
class BetIE(MTVServicesBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:video-clips|episodes)/(?P<id>[\da-z]{6})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bet.com/video-clips/w9mk7v',
|
||||
'info_dict': {
|
||||
'id': '3022d121-d191-43fd-b5fb-b2c26f335497',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'w9mk7v',
|
||||
'title': 'New Normal',
|
||||
'description': 'md5:d7898c124713b4646cecad9d16ff01f3',
|
||||
'duration': 30.08,
|
||||
'series': 'Tyler Perry\'s Sistas',
|
||||
'season': 'Season 0',
|
||||
'season_number': 0,
|
||||
'episode': 'Episode 0',
|
||||
'episode_number': 0,
|
||||
'timestamp': 1755269073,
|
||||
'upload_date': '20250815',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
|
||||
'info_dict': {
|
||||
'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
|
||||
'display_id': 'justice-for-ferguson-a-community-reacts',
|
||||
'ext': 'flv',
|
||||
'title': 'Justice for Ferguson: A Community Reacts',
|
||||
'description': 'A BET News special.',
|
||||
'duration': 1696,
|
||||
'upload_date': '20141125',
|
||||
'thumbnail': r're:(?i)^https?://.*\.jpg$',
|
||||
'subtitles': {
|
||||
'en': 'mincount:2',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.bet.com/episodes/nmce72/tyler-perry-s-sistas-heavy-is-the-crown-season-9-ep-5',
|
||||
'info_dict': {
|
||||
'id': '6427562b-3029-11f0-b405-16fff45bc035',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'nmce72',
|
||||
'title': 'Heavy Is the Crown',
|
||||
'description': 'md5:1ed345d3157a50572d2464afcc7a652a',
|
||||
'channel': 'BET',
|
||||
'duration': 2550.0,
|
||||
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref',
|
||||
'series': 'Tyler Perry\'s Sistas',
|
||||
'season': 'Season 9',
|
||||
'season_number': 9,
|
||||
'episode': 'Episode 5',
|
||||
'episode_number': 5,
|
||||
'timestamp': 1755165600,
|
||||
'upload_date': '20250814',
|
||||
'release_timestamp': 1755129600,
|
||||
'release_date': '20250814',
|
||||
},
|
||||
]
|
||||
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/bet-mrss-player'
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'uuid': uri,
|
||||
}
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
mgid = self._extract_mgid(webpage)
|
||||
videos_info = self._get_videos_info(mgid)
|
||||
|
||||
info_dict = videos_info['entries'][0]
|
||||
|
||||
upload_date = unified_strdate(self._html_search_meta('date', webpage))
|
||||
description = self._html_search_meta('description', webpage)
|
||||
|
||||
info_dict.update({
|
||||
'display_id': display_id,
|
||||
'description': description,
|
||||
'upload_date': upload_date,
|
||||
})
|
||||
|
||||
return info_dict
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'skip': 'Requires provider sign-in',
|
||||
}]
|
||||
|
||||
@@ -304,7 +304,7 @@ def _get_interactive_entries(self, video_id, cid, metainfo, headers=None):
|
||||
|
||||
|
||||
class BiliBiliIE(BilibiliBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)(?P<prefix>[aAbB][vV])(?P<id>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bilibili.com/video/BV13x41117TL',
|
||||
@@ -353,7 +353,7 @@ class BiliBiliIE(BilibiliBaseIE):
|
||||
'id': 'BV1bK411W797',
|
||||
'title': '物语中的人物是如何吐槽自己的OP的',
|
||||
},
|
||||
'playlist_count': 18,
|
||||
'playlist_count': 23,
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': 'BV1bK411W797_p1',
|
||||
@@ -373,6 +373,7 @@ class BiliBiliIE(BilibiliBaseIE):
|
||||
'_old_archive_ids': ['bilibili 498159642_part1'],
|
||||
},
|
||||
}],
|
||||
'params': {'playlist_items': '2'},
|
||||
}, {
|
||||
'note': 'Specific page of Anthology',
|
||||
'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1',
|
||||
@@ -562,7 +563,7 @@ class BiliBiliIE(BilibiliBaseIE):
|
||||
},
|
||||
}],
|
||||
}, {
|
||||
'note': '301 redirect to bangumi link',
|
||||
'note': 'redirect from bvid to bangumi link via redirect_url',
|
||||
'url': 'https://www.bilibili.com/video/BV1TE411f7f1',
|
||||
'info_dict': {
|
||||
'id': '288525',
|
||||
@@ -579,7 +580,27 @@ class BiliBiliIE(BilibiliBaseIE):
|
||||
'duration': 1183.957,
|
||||
'timestamp': 1571648124,
|
||||
'upload_date': '20191021',
|
||||
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
|
||||
'thumbnail': r're:https?://.*\.(jpg|jpeg|png)$',
|
||||
},
|
||||
}, {
|
||||
'note': 'redirect from aid to bangumi link via redirect_url',
|
||||
'url': 'https://www.bilibili.com/video/av114868162141203',
|
||||
'info_dict': {
|
||||
'id': '1933368',
|
||||
'title': 'PV 引爆变革的起点',
|
||||
'ext': 'mp4',
|
||||
'duration': 63.139,
|
||||
'series': '时光代理人',
|
||||
'series_id': '5183',
|
||||
'season': '第三季',
|
||||
'season_number': 4,
|
||||
'season_id': '105212',
|
||||
'episode': '引爆变革的起点',
|
||||
'episode_number': 1,
|
||||
'episode_id': '1933368',
|
||||
'timestamp': 1752849001,
|
||||
'upload_date': '20250718',
|
||||
'thumbnail': r're:https?://.*\.(jpg|jpeg|png)$',
|
||||
},
|
||||
}, {
|
||||
'note': 'video has subtitles, which requires login',
|
||||
@@ -635,7 +656,7 @@ class BiliBiliIE(BilibiliBaseIE):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_id, prefix = self._match_valid_url(url).group('id', 'prefix')
|
||||
headers = self.geo_verification_headers()
|
||||
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers)
|
||||
if not self._match_valid_url(urlh.url):
|
||||
@@ -643,7 +664,24 @@ def _real_extract(self, url):
|
||||
|
||||
headers['Referer'] = url
|
||||
|
||||
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
|
||||
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id, default=None)
|
||||
if not initial_state:
|
||||
if self._search_json(r'\bwindow\._riskdata_\s*=', webpage, 'risk', video_id, default={}).get('v_voucher'):
|
||||
raise ExtractorError('You have exceeded the rate limit. Try again later', expected=True)
|
||||
query = {'platform': 'web'}
|
||||
prefix = prefix.upper()
|
||||
if prefix == 'BV':
|
||||
query['bvid'] = prefix + video_id
|
||||
elif prefix == 'AV':
|
||||
query['aid'] = video_id
|
||||
detail = self._download_json(
|
||||
'https://api.bilibili.com/x/web-interface/wbi/view/detail', video_id,
|
||||
note='Downloading redirection URL', errnote='Failed to download redirection URL',
|
||||
query=self._sign_wbi(query, video_id), headers=headers)
|
||||
new_url = traverse_obj(detail, ('data', 'View', 'redirect_url', {url_or_none}))
|
||||
if new_url and BiliBiliBangumiIE.suitable(new_url):
|
||||
return self.url_result(new_url, BiliBiliBangumiIE)
|
||||
raise ExtractorError('Unable to extract initial state')
|
||||
|
||||
if traverse_obj(initial_state, ('error', 'trueCode')) == -403:
|
||||
self.raise_login_required()
|
||||
@@ -899,11 +937,26 @@ def _real_extract(self, url):
|
||||
'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id},
|
||||
headers=headers))
|
||||
|
||||
geo_blocked = traverse_obj(play_info, (
|
||||
'raw', 'data', 'plugins', lambda _, v: v['name'] == 'AreaLimitPanel', 'config', 'is_block', {bool}, any))
|
||||
premium_only = play_info.get('code') == -10403
|
||||
# play_info can be structured in at least three different ways, e.g.:
|
||||
# 1.) play_info['result']['video_info'] and play_info['code']
|
||||
# 2.) play_info['raw']['data']['video_info'] and play_info['code']
|
||||
# 3.) play_info['data']['result']['video_info'] and play_info['data']['code']
|
||||
# So we need to transform any of the above into a common structure
|
||||
status_code = play_info.get('code')
|
||||
if 'raw' in play_info:
|
||||
play_info = play_info['raw']
|
||||
if 'data' in play_info:
|
||||
play_info = play_info['data']
|
||||
if status_code is None:
|
||||
status_code = play_info.get('code')
|
||||
if 'result' in play_info:
|
||||
play_info = play_info['result']
|
||||
|
||||
video_info = traverse_obj(play_info, (('result', ('raw', 'data')), 'video_info', {dict}, any)) or {}
|
||||
geo_blocked = traverse_obj(play_info, (
|
||||
'plugins', lambda _, v: v['name'] == 'AreaLimitPanel', 'config', 'is_block', {bool}, any))
|
||||
premium_only = status_code == -10403
|
||||
|
||||
video_info = traverse_obj(play_info, ('video_info', {dict})) or {}
|
||||
formats = self.extract_formats(video_info)
|
||||
|
||||
if not formats:
|
||||
@@ -913,8 +966,8 @@ def _real_extract(self, url):
|
||||
self.raise_login_required('This video is for premium members only')
|
||||
|
||||
if traverse_obj(play_info, ((
|
||||
('result', 'play_check', 'play_detail'), # 'PLAY_PREVIEW' vs 'PLAY_WHOLE'
|
||||
('raw', 'data', 'play_video_type'), # 'preview' vs 'whole'
|
||||
('play_check', 'play_detail'), # 'PLAY_PREVIEW' vs 'PLAY_WHOLE' vs 'PLAY_NONE'
|
||||
'play_video_type', # 'preview' vs 'whole' vs 'none'
|
||||
), any, {lambda x: x in ('PLAY_PREVIEW', 'preview')})):
|
||||
self.report_warning(
|
||||
'Only preview format is available, '
|
||||
@@ -1000,6 +1053,7 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
|
||||
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
|
||||
},
|
||||
}],
|
||||
'params': {'playlist_items': '2'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -1055,6 +1109,7 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
|
||||
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
|
||||
},
|
||||
}],
|
||||
'params': {'playlist_items': '2'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -1226,6 +1281,26 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
|
||||
'id': '313580179',
|
||||
},
|
||||
'playlist_mincount': 92,
|
||||
}, {
|
||||
# Hidden-mode collection
|
||||
'url': 'https://space.bilibili.com/3669403/video',
|
||||
'info_dict': {
|
||||
'id': '3669403',
|
||||
},
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': '3669403_3958082',
|
||||
'title': '合集·直播回放',
|
||||
'description': '',
|
||||
'uploader': '月路Yuel',
|
||||
'uploader_id': '3669403',
|
||||
'timestamp': int,
|
||||
'upload_date': str,
|
||||
'thumbnail': str,
|
||||
},
|
||||
}],
|
||||
'params': {'playlist_items': '7'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -1282,8 +1357,14 @@ def get_metadata(page_data):
|
||||
}
|
||||
|
||||
def get_entries(page_data):
|
||||
for entry in traverse_obj(page_data, ('list', 'vlist')) or []:
|
||||
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
|
||||
for entry in traverse_obj(page_data, ('list', 'vlist', ..., {dict})):
|
||||
if traverse_obj(entry, ('meta', 'attribute')) == 156:
|
||||
# hidden-mode collection doesn't show its videos in uploads; extract as playlist instead
|
||||
yield self.url_result(
|
||||
f'https://space.bilibili.com/{entry["mid"]}/lists/{entry["meta"]["id"]}?type=season',
|
||||
BilibiliCollectionListIE, f'{entry["mid"]}_{entry["meta"]["id"]}')
|
||||
else:
|
||||
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
|
||||
|
||||
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
|
||||
return self.playlist_result(paged_list, playlist_id)
|
||||
@@ -1819,7 +1900,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
|
||||
'thumbnail': r're:^https?://.+\.jpg',
|
||||
'timestamp': 1564836614,
|
||||
'upload_date': '20190803',
|
||||
'uploader': 'tsukimi-つきみぐー',
|
||||
'uploader': '十六夜tsukimiつきみぐ',
|
||||
'view_count': int,
|
||||
},
|
||||
}
|
||||
@@ -1874,10 +1955,10 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
|
||||
'url': 'https://www.bilibili.com/audio/am10624',
|
||||
'info_dict': {
|
||||
'id': '10624',
|
||||
'title': '每日新曲推荐(每日11:00更新)',
|
||||
'title': '新曲推荐',
|
||||
'description': '每天11:00更新,为你推送最新音乐',
|
||||
},
|
||||
'playlist_count': 19,
|
||||
'playlist_count': 16,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -1,16 +1,27 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601
|
||||
from ..utils import (
|
||||
UnsupportedError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
jwt_decode_hs256,
|
||||
mimetype2ext,
|
||||
parse_iso8601,
|
||||
parse_qs,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class BlackboardCollaborateIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?P<region>[a-z-]+)\.bbcollab\.com/
|
||||
(?P<region>[a-z]+)(?:-lti)?\.bbcollab\.com/
|
||||
(?:
|
||||
collab/ui/session/playback/load|
|
||||
recording
|
||||
)/
|
||||
(?P<id>[^/]+)'''
|
||||
(?P<id>[^/?#]+)'''
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
|
||||
@@ -19,9 +30,55 @@ class BlackboardCollaborateIE(InfoExtractor):
|
||||
'id': '0a633b6a88824deb8c918f470b22b256',
|
||||
'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
|
||||
'ext': 'mp4',
|
||||
'duration': 1896000,
|
||||
'timestamp': 1620331399,
|
||||
'duration': 1896,
|
||||
'timestamp': 1620333295,
|
||||
'upload_date': '20210506',
|
||||
'subtitles': {
|
||||
'live_chat': 'mincount:1',
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://eu.bbcollab.com/collab/ui/session/playback/load/4bde2dee104f40289a10f8e554270600',
|
||||
'md5': '108db6a8f83dcb0c2a07793649581865',
|
||||
'info_dict': {
|
||||
'id': '4bde2dee104f40289a10f8e554270600',
|
||||
'title': 'Meeting - Azerbaycanca erize formasi',
|
||||
'ext': 'mp4',
|
||||
'duration': 880,
|
||||
'timestamp': 1671176868,
|
||||
'upload_date': '20221216',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://eu.bbcollab.com/recording/f83be390ecff46c0bf7dccb9dddcf5f6',
|
||||
'md5': 'e3b0b88ddf7847eae4b4c0e2d40b83a5',
|
||||
'info_dict': {
|
||||
'id': 'f83be390ecff46c0bf7dccb9dddcf5f6',
|
||||
'title': 'Keynote lecture by Laura Carvalho - recording_1',
|
||||
'ext': 'mp4',
|
||||
'duration': 5506,
|
||||
'timestamp': 1662721705,
|
||||
'upload_date': '20220909',
|
||||
'subtitles': {
|
||||
'live_chat': 'mincount:1',
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://eu.bbcollab.com/recording/c3e1e7c9e83d4cd9981c93c74888d496',
|
||||
'md5': 'fdb2d8c43d66fbc0b0b74ef5e604eb1f',
|
||||
'info_dict': {
|
||||
'id': 'c3e1e7c9e83d4cd9981c93c74888d496',
|
||||
'title': 'International Ally User Group - recording_18',
|
||||
'ext': 'mp4',
|
||||
'duration': 3479,
|
||||
'timestamp': 1721919621,
|
||||
'upload_date': '20240725',
|
||||
'subtitles': {
|
||||
'en': 'mincount:1',
|
||||
'live_chat': 'mincount:1',
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
@@ -42,22 +99,81 @@ class BlackboardCollaborateIE(InfoExtractor):
|
||||
},
|
||||
]
|
||||
|
||||
def _call_api(self, region, video_id, path=None, token=None, note=None, fatal=False):
|
||||
# Ref: https://github.com/blackboard/BBDN-Collab-Postman-REST
|
||||
return self._download_json(
|
||||
join_nonempty(f'https://{region}.bbcollab.com/collab/api/csa/recordings', video_id, path, delim='/'),
|
||||
video_id, note or 'Downloading JSON metadata', fatal=fatal,
|
||||
headers={'Authorization': f'Bearer {token}'} if token else None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
region = mobj.group('region')
|
||||
video_id = mobj.group('id')
|
||||
info = self._download_json(
|
||||
f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
|
||||
duration = info.get('duration')
|
||||
title = info['name']
|
||||
upload_date = info.get('created')
|
||||
streams = info['streams']
|
||||
formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
|
||||
token = parse_qs(url).get('authToken', [None])[-1]
|
||||
|
||||
video_info = self._call_api(region, video_id, path='data/secure', token=token, note='Trying auth token')
|
||||
if video_info:
|
||||
video_extra = self._call_api(region, video_id, token=token, note='Retrieving extra attributes')
|
||||
else:
|
||||
video_info = self._call_api(region, video_id, path='data', note='Trying fallback', fatal=True)
|
||||
video_extra = {}
|
||||
|
||||
formats = traverse_obj(video_info, ('extStreams', lambda _, v: url_or_none(v['streamUrl']), {
|
||||
'url': 'streamUrl',
|
||||
'ext': ('contentType', {mimetype2ext}),
|
||||
'aspect_ratio': ('aspectRatio', {float_or_none}),
|
||||
}))
|
||||
|
||||
if filesize := traverse_obj(video_extra, ('storageSize', {int_or_none})):
|
||||
for fmt in formats:
|
||||
fmt['filesize'] = filesize
|
||||
|
||||
subtitles = {}
|
||||
for subs in traverse_obj(video_info, ('subtitles', lambda _, v: url_or_none(v['url']))):
|
||||
subtitles.setdefault(subs.get('lang') or 'und', []).append({
|
||||
'name': traverse_obj(subs, ('label', {str})),
|
||||
'url': subs['url'],
|
||||
})
|
||||
|
||||
for live_chat_url in traverse_obj(video_info, ('chats', ..., 'url', {url_or_none})):
|
||||
subtitles.setdefault('live_chat', []).append({'url': live_chat_url})
|
||||
|
||||
return {
|
||||
'duration': duration,
|
||||
**traverse_obj(video_info, {
|
||||
'title': ('name', {str}),
|
||||
'timestamp': ('created', {parse_iso8601}),
|
||||
'duration': ('duration', {int_or_none(scale=1000)}),
|
||||
}),
|
||||
'formats': formats,
|
||||
'id': video_id,
|
||||
'timestamp': parse_iso8601(upload_date),
|
||||
'title': title,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class BlackboardCollaborateLaunchIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://[a-z]+\.bbcollab\.com/launch/(?P<id>[^/?#]+)'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://au.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.xuELw4EafEwUMoYcCHidGn4Tw9O1QCbYHzYGJUl0kKk',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://us.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.yOhRZNaIjXYoMYMpcTzgjZJCnIFaYf2cAzbco8OAxlY',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://eu.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJiYkNvbGxhYkFwaSIsInN1YiI6ImJiQ29sbGFiQXBpIiwiZXhwIjoxNzUyNjgyODYwLCJpYXQiOjE3NTI2ODI1NjAsInJlc291cmNlQWNjZXNzVGlja2V0Ijp7InJlc291cmNlSWQiOiI4MjQzYjFiODg2Nzk0NTZkYjkwN2NmNDZmZmE1MmFhZiIsImNvbnN1bWVySWQiOiI5ZTY4NzYwZWJiNzM0MzRiYWY3NTQyZjA1YmJkOTMzMCIsInR5cGUiOiJSRUNPUkRJTkciLCJyZXN0cmljdGlvbiI6eyJ0eXBlIjoiVElNRSIsImV4cGlyYXRpb25Ib3VycyI6MCwiZXhwaXJhdGlvbk1pbnV0ZXMiOjUsIm1heFJlcXVlc3RzIjotMX0sImRpc3Bvc2l0aW9uIjoiTEFVTkNIIiwibGF1bmNoVHlwZSI6bnVsbCwibGF1bmNoQ29tcG9uZW50IjpudWxsLCJsYXVuY2hQYXJhbUtleSI6bnVsbH19.Xj4ymojYLwZ1vKPKZ-KxjpqQvFXoJekjRaG0npngwWs',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
token = self._match_id(url)
|
||||
video_id = jwt_decode_hs256(token)['resourceAccessTicket']['resourceId']
|
||||
|
||||
redirect_url = self._request_webpage(url, video_id).url
|
||||
if self.suitable(redirect_url):
|
||||
raise UnsupportedError(redirect_url)
|
||||
return self.url_result(redirect_url, BlackboardCollaborateIE, video_id)
|
||||
|
||||
@@ -19,8 +19,19 @@ class BloggerIE(InfoExtractor):
|
||||
'id': 'BLOGGER-video-3c740e3a49197e16-796',
|
||||
'title': 'BLOGGER-video-3c740e3a49197e16-796',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'duration': 76.068,
|
||||
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
|
||||
},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://blog.tomeuvizoso.net/2019/01/a-panfrost-milestone.html',
|
||||
'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
|
||||
'info_dict': {
|
||||
'id': 'BLOGGER-video-3c740e3a49197e16-12203',
|
||||
'ext': 'mp4',
|
||||
'title': 'BLOGGER-video-3c740e3a49197e16-12203',
|
||||
'duration': 76.068,
|
||||
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
|
||||
},
|
||||
}]
|
||||
|
||||
|
||||
73
yt_dlp/extractor/btvplus.py
Normal file
73
yt_dlp/extractor/btvplus.py
Normal file
@@ -0,0 +1,73 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
bug_reports_message,
|
||||
clean_html,
|
||||
get_element_by_class,
|
||||
js_to_json,
|
||||
mimetype2ext,
|
||||
strip_or_none,
|
||||
url_or_none,
|
||||
urljoin,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class BTVPlusIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?btvplus\.bg/produkt/(?:predavaniya|seriali|novini)/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://btvplus.bg/produkt/predavaniya/67271/btv-reporterite/btv-reporterite-12-07-2025-g',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'id': '67271',
|
||||
'title': 'bTV Репортерите - 12.07.2025 г.',
|
||||
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jul2025/2113606319.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://btvplus.bg/produkt/seriali/66942/sezon-2/plen-sezon-2-epizod-55',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'id': '66942',
|
||||
'title': 'Плен - сезон 2, епизод 55',
|
||||
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jun2025/2113595104.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://btvplus.bg/produkt/novini/67270/btv-novinite-centralna-emisija-12-07-2025',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
player_url = self._search_regex(
|
||||
r'var\s+videoUrl\s*=\s*[\'"]([^\'"]+)[\'"]',
|
||||
webpage, 'player URL')
|
||||
|
||||
player_config = self._download_json(
|
||||
urljoin('https://btvplus.bg', player_url), video_id)['config']
|
||||
|
||||
videojs_data = self._search_json(
|
||||
r'videojs\(["\'][^"\']+["\'],', player_config, 'videojs data',
|
||||
video_id, transform_source=js_to_json)
|
||||
formats = []
|
||||
subtitles = {}
|
||||
for src in traverse_obj(videojs_data, ('sources', lambda _, v: url_or_none(v['src']))):
|
||||
ext = mimetype2ext(src.get('type'))
|
||||
if ext == 'm3u8':
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
else:
|
||||
self.report_warning(f'Unknown format type {ext}{bug_reports_message()}')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'title': (
|
||||
strip_or_none(self._og_search_title(webpage, default=None))
|
||||
or clean_html(get_element_by_class('product-title', webpage))),
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'description': self._og_search_description(webpage, default=None),
|
||||
}
|
||||
@@ -19,18 +19,16 @@ class CloudflareStreamIE(InfoExtractor):
|
||||
'id': '31c9291ab41fac05471db4e73aa11717',
|
||||
'ext': 'mp4',
|
||||
'title': '31c9291ab41fac05471db4e73aa11717',
|
||||
'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://watch.cloudflarestream.com/embed/sdk-iframe-integration.fla9.latest.js?video=0e8e040aec776862e1d632a699edf59e',
|
||||
'info_dict': {
|
||||
'id': '0e8e040aec776862e1d632a699edf59e',
|
||||
'ext': 'mp4',
|
||||
'title': '0e8e040aec776862e1d632a699edf59e',
|
||||
'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
|
||||
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
|
||||
@@ -54,11 +52,21 @@ class CloudflareStreamIE(InfoExtractor):
|
||||
'id': 'eaef9dea5159cf968be84241b5cedfe7',
|
||||
'ext': 'mp4',
|
||||
'title': 'eaef9dea5159cf968be84241b5cedfe7',
|
||||
'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
|
||||
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
|
||||
},
|
||||
'params': {
|
||||
'extractor_args': {'generic': {'impersonate': ['chrome']}},
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}, {
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.cloudflare.com/developer-platform/products/cloudflare-stream/',
|
||||
'info_dict': {
|
||||
'id': 'e7bd2dd67e0f8860b4ae81e33a966049',
|
||||
'ext': 'mp4',
|
||||
'title': 'e7bd2dd67e0f8860b4ae81e33a966049',
|
||||
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
from .mtv import MTVIE
|
||||
|
||||
# TODO: Remove - Reason: Outdated Site
|
||||
|
||||
|
||||
class CMTIE(MTVIE): # XXX: Do not subclass from concrete IE
|
||||
_WORKING = False
|
||||
IE_NAME = 'cmt.com'
|
||||
_VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
|
||||
'md5': 'e6b7ef3c4c45bbfae88061799bbba6c2',
|
||||
'info_dict': {
|
||||
'id': '989124',
|
||||
'ext': 'mp4',
|
||||
'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
|
||||
'description': 'Blame It All On My Roots',
|
||||
},
|
||||
'skip': 'Video not available',
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/videos/misc/1504699/still-the-king-ep-109-in-3-minutes.jhtml#id=1739908',
|
||||
'md5': 'e61a801ca4a183a466c08bd98dccbb1c',
|
||||
'info_dict': {
|
||||
'id': '1504699',
|
||||
'ext': 'mp4',
|
||||
'title': 'Still The King Ep. 109 in 3 Minutes',
|
||||
'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9.',
|
||||
'timestamp': 1469421000.0,
|
||||
'upload_date': '20160725',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_mgid(self, webpage, url):
|
||||
mgid = self._search_regex(
|
||||
r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
|
||||
webpage, 'mgid', group='mgid', default=None)
|
||||
if not mgid:
|
||||
mgid = self._extract_triforce_mgid(webpage)
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
mgid = self._extract_mgid(webpage, url)
|
||||
return self.url_result(f'http://media.mtvnservices.com/embed/{mgid}')
|
||||
@@ -1,55 +1,27 @@
|
||||
from .mtv import MTVServicesInfoExtractor
|
||||
from .mtv import MTVServicesBaseIE
|
||||
|
||||
|
||||
class ComedyCentralIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?|collection-playlist|movies)/(?P<id>[0-9a-z]{6})'
|
||||
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
|
||||
|
||||
class ComedyCentralIE(MTVServicesBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?cc\.com/video-clips/(?P<id>[\da-z]{6})'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
|
||||
'md5': 'b8acb347177c680ff18a292aa2166f80',
|
||||
'url': 'https://www.cc.com/video-clips/wl12cx',
|
||||
'info_dict': {
|
||||
'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
|
||||
'id': 'dec6953e-80c8-43b3-96cd-05e9230e704d',
|
||||
'ext': 'mp4',
|
||||
'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
|
||||
'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
|
||||
'timestamp': 1598670000,
|
||||
'upload_date': '20200829',
|
||||
'display_id': 'wl12cx',
|
||||
'title': 'Alison Brie and Dave Franco -"Together"- Extended Interview',
|
||||
'description': 'md5:ec68e38d3282f863de9cde0ce5cd231c',
|
||||
'duration': 516.76,
|
||||
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref:',
|
||||
'series': 'The Daily Show',
|
||||
'season': 'Season 30',
|
||||
'season_number': 30,
|
||||
'episode': 'Episode 0',
|
||||
'episode_number': 0,
|
||||
'timestamp': 1753973314,
|
||||
'upload_date': '20250731',
|
||||
'release_timestamp': 1753977914,
|
||||
'release_date': '20250731',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cc.com/collection-playlist/cosnej/stand-up-specials/t6vtjb',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cc.com/movies/tkp406/a-cluesterfuenke-christmas',
|
||||
'only_matching': True,
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
|
||||
class ComedyCentralTVIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
|
||||
'info_dict': {
|
||||
'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
|
||||
'ext': 'mp4',
|
||||
'title': 'Josh Investigates',
|
||||
'description': 'Steht uns das Ende der Welt bevor?',
|
||||
},
|
||||
}]
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'accountOverride': 'intl.mtvi.com',
|
||||
'arcEp': 'web.cc.tv',
|
||||
'ep': 'b9032c3a',
|
||||
'imageEp': 'web.cc.tv',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import base64
|
||||
import collections
|
||||
import contextlib
|
||||
import functools
|
||||
import getpass
|
||||
import http.client
|
||||
@@ -37,7 +38,6 @@
|
||||
TransportError,
|
||||
network_exceptions,
|
||||
)
|
||||
from ..networking.impersonate import ImpersonateTarget
|
||||
from ..utils import (
|
||||
IDENTITY,
|
||||
JSON_LD_RE,
|
||||
@@ -243,7 +243,7 @@ class InfoExtractor:
|
||||
* extra_param_to_segment_url A query string to append to each
|
||||
fragment's URL, or to update each existing query string
|
||||
with. If it is an HLS stream with an AES-128 decryption key,
|
||||
the query paramaters will be passed to the key URI as well,
|
||||
the query parameters will be passed to the key URI as well,
|
||||
unless there is an `extra_param_to_key_url` given,
|
||||
or unless an external key URI is provided via `hls_aes`.
|
||||
Only applied by the native HLS/DASH downloaders.
|
||||
@@ -258,11 +258,20 @@ class InfoExtractor:
|
||||
* key The key (as hex) used to decrypt fragments.
|
||||
If `key` is given, any key URI will be ignored
|
||||
* iv The IV (as hex) used to decrypt fragments
|
||||
* impersonate Impersonate target(s). Can be any of the following entities:
|
||||
* an instance of yt_dlp.networking.impersonate.ImpersonateTarget
|
||||
* a string in the format of CLIENT[:OS]
|
||||
* a list or a tuple of CLIENT[:OS] strings or ImpersonateTarget instances
|
||||
* a boolean value; True means any impersonate target is sufficient
|
||||
* available_at Unix timestamp of when a format will be available to download
|
||||
* downloader_options A dictionary of downloader options
|
||||
(For internal use only)
|
||||
* http_chunk_size Chunk size for HTTP downloads
|
||||
* ffmpeg_args Extra arguments for ffmpeg downloader (input)
|
||||
* ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
|
||||
* ws (NiconicoLiveFD only) WebSocketResponse
|
||||
* ws_url (NiconicoLiveFD only) Websockets URL
|
||||
* max_quality (NiconicoLiveFD only) Max stream quality string
|
||||
* is_dash_periods Whether the format is a result of merging
|
||||
multiple DASH periods.
|
||||
RTMP formats can also have the additional fields: page_url,
|
||||
@@ -332,6 +341,7 @@ class InfoExtractor:
|
||||
* "name": Name or description of the subtitles
|
||||
* "http_headers": A dictionary of additional HTTP headers
|
||||
to add to the request.
|
||||
* "impersonate": Impersonate target(s); same as the "formats" field
|
||||
"ext" will be calculated from URL if missing
|
||||
automatic_captions: Like 'subtitles'; contains automatically generated
|
||||
captions instead of normal subtitles
|
||||
@@ -388,6 +398,8 @@ class InfoExtractor:
|
||||
chapters: A list of dictionaries, with the following entries:
|
||||
* "start_time" - The start time of the chapter in seconds
|
||||
* "end_time" - The end time of the chapter in seconds
|
||||
(optional: core code can determine this value from
|
||||
the next chapter's start_time or the video's duration)
|
||||
* "title" (optional, string)
|
||||
heatmap: A list of dictionaries, with the following entries:
|
||||
* "start_time" - The start time of the data point in seconds
|
||||
@@ -402,12 +414,13 @@ class InfoExtractor:
|
||||
'unlisted' or 'public'. Use 'InfoExtractor._availability'
|
||||
to set it
|
||||
media_type: The type of media as classified by the site, e.g. "episode", "clip", "trailer"
|
||||
_old_archive_ids: A list of old archive ids needed for backward compatibility
|
||||
_old_archive_ids: A list of old archive ids needed for backward
|
||||
compatibility. Use yt_dlp.utils.make_archive_id to generate ids
|
||||
_format_sort_fields: A list of fields to use for sorting formats
|
||||
__post_extractor: A function to be called just before the metadata is
|
||||
written to either disk, logger or console. The function
|
||||
must return a dict which will be added to the info_dict.
|
||||
This is usefull for additional information that is
|
||||
This is useful for additional information that is
|
||||
time-consuming to extract. Note that the fields thus
|
||||
extracted will not be available to output template and
|
||||
match_filter. So, only "comments" and "comment_count" are
|
||||
@@ -880,26 +893,17 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa
|
||||
|
||||
extensions = {}
|
||||
|
||||
if impersonate in (True, ''):
|
||||
impersonate = ImpersonateTarget()
|
||||
requested_targets = [
|
||||
t if isinstance(t, ImpersonateTarget) else ImpersonateTarget.from_str(t)
|
||||
for t in variadic(impersonate)
|
||||
] if impersonate else []
|
||||
|
||||
available_target = next(filter(self._downloader._impersonate_target_available, requested_targets), None)
|
||||
available_target, requested_targets = self._downloader._parse_impersonate_targets(impersonate)
|
||||
if available_target:
|
||||
extensions['impersonate'] = available_target
|
||||
elif requested_targets:
|
||||
message = 'The extractor is attempting impersonation, but '
|
||||
message += (
|
||||
'no impersonate target is available' if not str(impersonate)
|
||||
else f'none of these impersonate targets are available: "{", ".join(map(str, requested_targets))}"')
|
||||
info_msg = ('see https://github.com/yt-dlp/yt-dlp#impersonation '
|
||||
'for information on installing the required dependencies')
|
||||
msg = 'The extractor is attempting impersonation'
|
||||
if require_impersonation:
|
||||
raise ExtractorError(f'{message}; {info_msg}', expected=True)
|
||||
self.report_warning(f'{message}; if you encounter errors, then {info_msg}', only_once=True)
|
||||
raise ExtractorError(
|
||||
self._downloader._unavailable_targets_message(requested_targets, note=msg, is_error=True),
|
||||
expected=True)
|
||||
self.report_warning(
|
||||
self._downloader._unavailable_targets_message(requested_targets, note=msg), only_once=True)
|
||||
|
||||
try:
|
||||
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query, extensions))
|
||||
@@ -1524,11 +1528,11 @@ def _rta_search(html):
|
||||
r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
|
||||
]
|
||||
|
||||
age_limit = 0
|
||||
age_limit = None
|
||||
for marker in AGE_LIMIT_MARKERS:
|
||||
mobj = re.search(marker, html)
|
||||
if mobj:
|
||||
age_limit = max(age_limit, int(traverse_obj(mobj, 1, default=18)))
|
||||
age_limit = max(age_limit or 0, int(traverse_obj(mobj, 1, default=18)))
|
||||
return age_limit
|
||||
|
||||
def _media_rating_search(self, html):
|
||||
@@ -1779,6 +1783,59 @@ def _search_nextjs_data(self, webpage, video_id, *, fatal=True, default=NO_DEFAU
|
||||
r'<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>', webpage, 'next.js data',
|
||||
video_id, end_pattern='</script>', fatal=fatal, default=default, **kw)
|
||||
|
||||
def _search_nextjs_v13_data(self, webpage, video_id, fatal=True):
|
||||
"""Parses Next.js app router flight data that was introduced in Next.js v13"""
|
||||
nextjs_data = {}
|
||||
if not fatal and not isinstance(webpage, str):
|
||||
return nextjs_data
|
||||
|
||||
def flatten(flight_data):
|
||||
if not isinstance(flight_data, list):
|
||||
return
|
||||
if len(flight_data) == 4 and flight_data[0] == '$':
|
||||
_, name, _, data = flight_data
|
||||
if not isinstance(data, dict):
|
||||
return
|
||||
children = data.pop('children', None)
|
||||
if data and isinstance(name, str) and re.fullmatch(r'\$L[0-9a-f]+', name):
|
||||
# It is useful hydration JSON data
|
||||
nextjs_data[name[2:]] = data
|
||||
flatten(children)
|
||||
return
|
||||
for f in flight_data:
|
||||
flatten(f)
|
||||
|
||||
flight_text = ''
|
||||
# The pattern for the surrounding JS/tag should be strict as it's a hardcoded string in the next.js source
|
||||
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L189
|
||||
for flight_segment in re.findall(r'<script\b[^>]*>self\.__next_f\.push\((\[.+?\])\)</script>', webpage):
|
||||
segment = self._parse_json(flight_segment, video_id, fatal=fatal, errnote=None if fatal else False)
|
||||
# Some earlier versions of next.js "optimized" away this array structure; this is unsupported
|
||||
# Ref: https://github.com/vercel/next.js/commit/0123a9d5c9a9a77a86f135b7ae30b46ca986d761
|
||||
if not isinstance(segment, list) or len(segment) != 2:
|
||||
self.write_debug(
|
||||
f'{video_id}: Unsupported next.js flight data structure detected', only_once=True)
|
||||
continue
|
||||
# Only use the relevant payload type (1 == data)
|
||||
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L11-L14
|
||||
payload_type, chunk = segment
|
||||
if payload_type == 1:
|
||||
flight_text += chunk
|
||||
|
||||
for f in flight_text.splitlines():
|
||||
prefix, _, body = f.lstrip().partition(':')
|
||||
if not re.fullmatch(r'[0-9a-f]+', prefix):
|
||||
continue
|
||||
# The body still isn't guaranteed to be valid JSON, so parsing should always be non-fatal
|
||||
if body.startswith('[') and body.endswith(']'):
|
||||
flatten(self._parse_json(body, video_id, fatal=False, errnote=False))
|
||||
elif body.startswith('{') and body.endswith('}'):
|
||||
data = self._parse_json(body, video_id, fatal=False, errnote=False)
|
||||
if data is not None:
|
||||
nextjs_data[prefix] = data
|
||||
|
||||
return nextjs_data
|
||||
|
||||
def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal=True, traverse=('data', 0)):
|
||||
"""Parses Nuxt.js metadata. This works as long as the function __NUXT__ invokes is a pure function"""
|
||||
rectx = re.escape(context_name)
|
||||
@@ -2126,21 +2183,33 @@ def _extract_m3u8_formats_and_subtitles(
|
||||
raise ExtractorError(errnote, video_id=video_id)
|
||||
self.report_warning(f'{errnote}{bug_reports_message()}')
|
||||
return [], {}
|
||||
|
||||
res = self._download_webpage_handle(
|
||||
m3u8_url, video_id,
|
||||
note='Downloading m3u8 information' if note is None else note,
|
||||
errnote='Failed to download m3u8 information' if errnote is None else errnote,
|
||||
if note is None:
|
||||
note = 'Downloading m3u8 information'
|
||||
if errnote is None:
|
||||
errnote = 'Failed to download m3u8 information'
|
||||
response = self._request_webpage(
|
||||
m3u8_url, video_id, note=note, errnote=errnote,
|
||||
fatal=fatal, data=data, headers=headers, query=query)
|
||||
|
||||
if res is False:
|
||||
if response is False:
|
||||
return [], {}
|
||||
|
||||
m3u8_doc, urlh = res
|
||||
m3u8_url = urlh.url
|
||||
with contextlib.closing(response):
|
||||
prefix = response.read(512)
|
||||
if not prefix.startswith(b'#EXTM3U'):
|
||||
msg = 'Response data has no m3u header'
|
||||
if fatal:
|
||||
raise ExtractorError(msg, video_id=video_id)
|
||||
self.report_warning(f'{msg}{bug_reports_message()}', video_id=video_id)
|
||||
return [], {}
|
||||
|
||||
content = self._webpage_read_content(
|
||||
response, m3u8_url, video_id, note=note, errnote=errnote,
|
||||
fatal=fatal, prefix=prefix, data=data)
|
||||
if content is False:
|
||||
return [], {}
|
||||
|
||||
return self._parse_m3u8_formats_and_subtitles(
|
||||
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
|
||||
content, response.url, ext=ext, entry_protocol=entry_protocol,
|
||||
preference=preference, quality=quality, m3u8_id=m3u8_id,
|
||||
note=note, errnote=errnote, fatal=fatal, live=live, data=data,
|
||||
headers=headers, query=query, video_id=video_id)
|
||||
@@ -2900,7 +2969,7 @@ def extract_Initialization(source):
|
||||
else:
|
||||
codecs = parse_codecs(codec_str)
|
||||
if content_type not in ('video', 'audio', 'text'):
|
||||
if mime_type == 'image/jpeg':
|
||||
if mime_type in ('image/avif', 'image/jpeg'):
|
||||
content_type = mime_type
|
||||
elif codecs.get('vcodec', 'none') != 'none':
|
||||
content_type = 'video'
|
||||
@@ -2960,14 +3029,14 @@ def extract_Initialization(source):
|
||||
'manifest_url': mpd_url,
|
||||
'filesize': filesize,
|
||||
}
|
||||
elif content_type == 'image/jpeg':
|
||||
elif content_type in ('image/avif', 'image/jpeg'):
|
||||
# See test case in VikiIE
|
||||
# https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'ext': 'mhtml',
|
||||
'manifest_url': mpd_url,
|
||||
'format_note': 'DASH storyboards (jpeg)',
|
||||
'format_note': f'DASH storyboards ({mimetype2ext(mime_type)})',
|
||||
'acodec': 'none',
|
||||
'vcodec': 'none',
|
||||
}
|
||||
@@ -3039,7 +3108,6 @@ def location_key(location):
|
||||
else:
|
||||
# $Number*$ or $Time$ in media template with S list available
|
||||
# Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
|
||||
# Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
|
||||
representation_ms_info['fragments'] = []
|
||||
segment_time = 0
|
||||
segment_d = None
|
||||
@@ -3109,7 +3177,7 @@ def add_segment_url():
|
||||
'url': mpd_url or base_url,
|
||||
'fragment_base_url': base_url,
|
||||
'fragments': [],
|
||||
'protocol': 'http_dash_segments' if mime_type != 'image/jpeg' else 'mhtml',
|
||||
'protocol': 'mhtml' if mime_type in ('image/avif', 'image/jpeg') else 'http_dash_segments',
|
||||
})
|
||||
if 'initialization_url' in representation_ms_info:
|
||||
initialization_url = representation_ms_info['initialization_url']
|
||||
@@ -3124,7 +3192,7 @@ def add_segment_url():
|
||||
else:
|
||||
# Assuming direct URL to unfragmented media.
|
||||
f['url'] = base_url
|
||||
if content_type in ('video', 'audio', 'image/jpeg'):
|
||||
if content_type in ('video', 'audio', 'image/avif', 'image/jpeg'):
|
||||
f['manifest_stream_number'] = stream_numbers[f['url']]
|
||||
stream_numbers[f['url']] += 1
|
||||
period_entry['formats'].append(f)
|
||||
|
||||
@@ -96,6 +96,24 @@ class CondeNastIE(InfoExtractor):
|
||||
'upload_date': '20150916',
|
||||
'timestamp': 1442434920,
|
||||
},
|
||||
}, {
|
||||
# FIXME: Subtitles
|
||||
'url': 'https://www.vanityfair.com/video/watch/vf-quiz-show-squid-game-s3',
|
||||
'info_dict': {
|
||||
'id': '6862f999c1afbc5ff06b4803',
|
||||
'ext': 'mp4',
|
||||
'title': '\'Squid Game\' Cast Tests How Well They Know Each Other',
|
||||
'categories': ['Arts & Culture', 'Hollywood'],
|
||||
'description': 'md5:7a9c668a1fc87648e77da13842ec1534',
|
||||
'duration': 955,
|
||||
'season': 'Season 1',
|
||||
'series': 'Quizzing Each Other',
|
||||
'tags': 'count:2',
|
||||
'thumbnail': r're:https?://dwgyu36up6iuz\.cloudfront\.net/.+\.jpg',
|
||||
'timestamp': 1751341306,
|
||||
'upload_date': '20250701',
|
||||
'uploader': 'vanityfair',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
|
||||
'only_matching': True,
|
||||
|
||||
@@ -8,7 +8,6 @@
|
||||
class CrooksAndLiarsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
|
||||
_EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
|
||||
'info_dict': {
|
||||
@@ -16,7 +15,7 @@ class CrooksAndLiarsIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
|
||||
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
|
||||
'timestamp': 1428207000,
|
||||
'upload_date': '20150405',
|
||||
'uploader': 'Heather',
|
||||
@@ -26,6 +25,20 @@ class CrooksAndLiarsIE(InfoExtractor):
|
||||
'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
|
||||
'info_dict': {
|
||||
'id': '8RUoRhRi',
|
||||
'ext': 'mp4',
|
||||
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
|
||||
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
|
||||
'duration': 236,
|
||||
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
|
||||
'timestamp': 1428207000,
|
||||
'upload_date': '20150405',
|
||||
'uploader': 'Heather',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@@ -1,49 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class CTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P<id>(?:show|movie)s/[^/]+/[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88',
|
||||
'info_dict': {
|
||||
'id': '2102249',
|
||||
'ext': 'flv',
|
||||
'title': 'Wednesday, December 23, 2020',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.',
|
||||
'timestamp': 1608732000,
|
||||
'upload_date': '20201223',
|
||||
'series': 'Your Morning',
|
||||
'season': '2020-2021',
|
||||
'season_number': 5,
|
||||
'episode_number': 88,
|
||||
'tags': ['Your Morning'],
|
||||
'categories': ['Talk Show'],
|
||||
'duration': 7467.126,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
content = self._download_json(
|
||||
'https://www.ctv.ca/space-graphql/graphql', display_id, query={
|
||||
'query': '''{
|
||||
resolvedPath(path: "/%s") {
|
||||
lastSegment {
|
||||
content {
|
||||
... on AxisContent {
|
||||
axisId
|
||||
videoPlayerDestCode
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}''' % display_id, # noqa: UP031
|
||||
})['data']['resolvedPath']['lastSegment']['content']
|
||||
video_id = content['axisId']
|
||||
return self.url_result(
|
||||
'9c9media:{}:{}'.format(content['videoPlayerDestCode'], video_id),
|
||||
'NineCNineMedia', video_id)
|
||||
@@ -19,11 +19,22 @@ class DailyMailIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
|
||||
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
|
||||
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.daily-news.gr/lifestyle/%ce%b7-%cf%84%cf%81%ce%b1%ce%b3%ce%bf%cf%85%ce%b4%ce%af%cf%83%cf%84%cf%81%ce%b9%ce%b1-jessie-j-%ce%bc%ce%bf%ce%b9%cf%81%ce%ac%cf%83%cf%84%ce%b7%ce%ba%ce%b5-%cf%83%cf%85%ce%b3%ce%ba%ce%bb%ce%bf%ce%bd/',
|
||||
'info_dict': {
|
||||
'id': '3463585',
|
||||
'ext': 'mp4',
|
||||
'title': 'Jessie J reveals she has undergone surgery as she shares clips',
|
||||
'description': 'md5:9fa9a25feca5b656b0b4a39c922fad1e',
|
||||
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@@ -119,13 +119,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
_EMBED_REGEX = [rf'(?ix)<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)["\'](?P<url>{_VALID_URL[5:]})']
|
||||
_TESTS = [{
|
||||
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
|
||||
'md5': '074b95bdee76b9e3654137aee9c79dfe',
|
||||
'info_dict': {
|
||||
'id': 'x5kesuj',
|
||||
'ext': 'mp4',
|
||||
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
|
||||
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
|
||||
'duration': 187,
|
||||
'tags': 'count:5',
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1493651285,
|
||||
'upload_date': '20170501',
|
||||
'uploader': 'Deadline',
|
||||
@@ -133,18 +134,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'age_limit': 0,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
|
||||
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1cmt4ZcZ9KiM/x1080',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
|
||||
'md5': 'e2f9717c6604773f963f069ca53a07f8',
|
||||
'info_dict': {
|
||||
'id': 'x89eyek',
|
||||
'ext': 'mp4',
|
||||
'title': "En quête d'esprit du 27/03/2022",
|
||||
'title': 'En quête d\'esprit du 27/03/2022',
|
||||
'description': 'md5:66542b9f4df2eb23f314fc097488e553',
|
||||
'duration': 2756,
|
||||
'tags': 'count:1',
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1648383669,
|
||||
'upload_date': '20220327',
|
||||
'uploader': 'CNEWS',
|
||||
@@ -152,8 +152,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'age_limit': 0,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'tags': ['en_quete_d_esprit'],
|
||||
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1clTH6StrxMP/x1080',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
|
||||
@@ -163,8 +161,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
|
||||
'description': 'Several come bundled with the Steam Controller.',
|
||||
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
|
||||
'duration': 74,
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1425657362,
|
||||
'upload_date': '20150306',
|
||||
'uploader': 'IGN',
|
||||
@@ -173,20 +171,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'view_count': int,
|
||||
},
|
||||
'skip': 'video gone',
|
||||
}, {
|
||||
# Vevo video
|
||||
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
|
||||
'info_dict': {
|
||||
'title': 'Roar (Official)',
|
||||
'id': 'USUV71301934',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'Katy Perry',
|
||||
'upload_date': '20130905',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'VEVO is only available in some countries',
|
||||
}, {
|
||||
# age-restricted video
|
||||
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
|
||||
@@ -259,9 +243,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'uploader_id': 'x2vtgmm',
|
||||
'age_limit': 0,
|
||||
'tags': [],
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'thumbnail': r're:https://\w+.dmcdn.net/v/WnEY61cmvMxt2Fi6d/x1080',
|
||||
},
|
||||
}, {
|
||||
# https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
|
||||
@@ -276,18 +260,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'x8u4owg',
|
||||
'ext': 'mp4',
|
||||
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
|
||||
'like_count': int,
|
||||
'uploader': 'Le Parisien',
|
||||
'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
|
||||
'upload_date': '20240309',
|
||||
'view_count': int,
|
||||
'tags': 'count:7',
|
||||
'thumbnail': r're:https?://www\.leparisien\.fr/.+\.jpg',
|
||||
'timestamp': 1709997866,
|
||||
'age_limit': 0,
|
||||
'uploader_id': 'x32f7b',
|
||||
'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
|
||||
'duration': 428.0,
|
||||
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
|
||||
'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
|
||||
},
|
||||
}, {
|
||||
# https://geo.dailymotion.com/player/xry80.html?video=x8vu47w
|
||||
@@ -297,9 +281,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'like_count': int,
|
||||
'uploader': 'Metatube',
|
||||
'thumbnail': r're:https://\w+.dmcdn.net/v/W1G_S1coGSFTfkTeR/x1080',
|
||||
'upload_date': '20240326',
|
||||
'view_count': int,
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1711496732,
|
||||
'age_limit': 0,
|
||||
'uploader_id': 'x2xpy74',
|
||||
@@ -308,6 +292,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'description': 'Que lindura',
|
||||
'tags': [],
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# //geo.dailymotion.com/player/xysxq.html?video=k2Y4Mjp7krAF9iCuINM
|
||||
'url': 'https://lcp.fr/programmes/avant-la-catastrophe-la-naissance-de-la-dictature-nazie-1933-1936-346819',
|
||||
@@ -322,11 +307,30 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'like_count': int,
|
||||
'age_limit': 0,
|
||||
'duration': 3220,
|
||||
'thumbnail': 'https://s1.dmcdn.net/v/Xvumk1djJBUZfjj2a/x1080',
|
||||
'tags': [],
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1739919947,
|
||||
'upload_date': '20250218',
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
'url': 'https://forum.ionicframework.com/t/ionic-2-jw-player-dailymotion-player/83248',
|
||||
'info_dict': {
|
||||
'id': 'xwr14q',
|
||||
'ext': 'mp4',
|
||||
'title': 'Macklemore & Ryan Lewis - Thrift Shop (feat. Wanz)',
|
||||
'age_limit': 0,
|
||||
'description': 'md5:47fbe168b5a6ddc4a205e20dd6c841b2',
|
||||
'duration': 234,
|
||||
'like_count': int,
|
||||
'tags': 'count:5',
|
||||
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
|
||||
'timestamp': 1358177670,
|
||||
'upload_date': '20130114',
|
||||
'uploader': 'Macklemore Official',
|
||||
'uploader_id': 'x19qlwr',
|
||||
'view_count': int,
|
||||
},
|
||||
}]
|
||||
_GEO_BYPASS = False
|
||||
_COMMON_MEDIA_FIELDS = '''description
|
||||
@@ -540,7 +544,7 @@ class DailymotionSearchIE(DailymotionPlaylistBaseIE):
|
||||
'id': 'king of turtles',
|
||||
'title': 'king of turtles',
|
||||
},
|
||||
'playlist_mincount': 90,
|
||||
'playlist_mincount': 0,
|
||||
}]
|
||||
_SEARCH_QUERY = 'query SEARCH_QUERY( $query: String! $page: Int $limit: Int ) { search { videos( query: $query first: $limit page: $page ) { edges { node { xid } } } } } '
|
||||
|
||||
@@ -584,7 +588,7 @@ class DailymotionUserIE(DailymotionPlaylistBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'nqtv',
|
||||
},
|
||||
'playlist_mincount': 152,
|
||||
'playlist_mincount': 148,
|
||||
}, {
|
||||
'url': 'http://www.dailymotion.com/user/UnderProject',
|
||||
'info_dict': {
|
||||
|
||||
@@ -11,8 +11,14 @@
|
||||
|
||||
class DangalPlayBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'dangalplay'
|
||||
_REGION = 'IN'
|
||||
_OTV_USER_ID = None
|
||||
_LOGIN_HINT = 'Pass credentials as -u "token" -p "USER_ID" where USER_ID is the `otv_user_id` in browser local storage'
|
||||
_LOGIN_HINT = (
|
||||
'Pass credentials as -u "token" -p "USER_ID" '
|
||||
'(where USER_ID is the value of "otv_user_id" in your browser local storage). '
|
||||
'Your login region can be optionally suffixed to the username as @REGION '
|
||||
'(where REGION is the two-letter "region" code found in your browser local storage), '
|
||||
'e.g.: -u "token@IN" -p "USER_ID"')
|
||||
_API_BASE = 'https://ottapi.dangalplay.com'
|
||||
_AUTH_TOKEN = 'jqeGWxRKK7FK5zEk3xCM' # from https://www.dangalplay.com/main.48ad19e24eb46acccef3.js
|
||||
_SECRET_KEY = 'f53d31a4377e4ef31fa0' # same as above
|
||||
@@ -20,8 +26,12 @@ class DangalPlayBaseIE(InfoExtractor):
|
||||
def _perform_login(self, username, password):
|
||||
if self._OTV_USER_ID:
|
||||
return
|
||||
if username != 'token' or not re.fullmatch(r'[\da-f]{32}', password):
|
||||
mobj = re.fullmatch(r'token(?:@(?P<region>[A-Z]{2}))?', username)
|
||||
if not mobj or not re.fullmatch(r'[\da-f]{32}', password):
|
||||
raise ExtractorError(self._LOGIN_HINT, expected=True)
|
||||
if region := mobj.group('region'):
|
||||
self._REGION = region
|
||||
self.write_debug(f'Setting login region to "{self._REGION}"')
|
||||
self._OTV_USER_ID = password
|
||||
|
||||
def _real_initialize(self):
|
||||
@@ -52,7 +62,7 @@ def _call_api(self, path, display_id, note='Downloading JSON metadata', fatal=Tr
|
||||
f'{self._API_BASE}/{path}', display_id, note, fatal=fatal,
|
||||
headers={'Accept': 'application/json'}, query={
|
||||
'auth_token': self._AUTH_TOKEN,
|
||||
'region': 'IN',
|
||||
'region': self._REGION,
|
||||
**query,
|
||||
})
|
||||
|
||||
@@ -106,7 +116,7 @@ def _generate_api_data(self, data):
|
||||
'catalog_id': catalog_id,
|
||||
'content_id': content_id,
|
||||
'category': '',
|
||||
'region': 'IN',
|
||||
'region': self._REGION,
|
||||
'auth_token': self._AUTH_TOKEN,
|
||||
'id': self._OTV_USER_ID,
|
||||
'md5': hashlib.md5(unhashed.encode()).hexdigest(),
|
||||
@@ -129,11 +139,14 @@ def _real_extract(self, url):
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 422:
|
||||
error_info = traverse_obj(e.cause.response.read().decode(), ({json.loads}, 'error', {dict})) or {}
|
||||
if error_info.get('code') == '1016':
|
||||
error_code = error_info.get('code')
|
||||
if error_code == '1016':
|
||||
self.raise_login_required(
|
||||
f'Your token has expired or is invalid. {self._LOGIN_HINT}', method=None)
|
||||
elif msg := error_info.get('message'):
|
||||
raise ExtractorError(msg)
|
||||
elif error_code == '4028':
|
||||
self.raise_login_required(
|
||||
f'Your login region is unspecified or incorrect. {self._LOGIN_HINT}', method=None)
|
||||
raise ExtractorError(join_nonempty(error_code, error_info.get('message'), delim=': '))
|
||||
raise
|
||||
|
||||
m3u8_url = traverse_obj(details, (
|
||||
|
||||
@@ -12,13 +12,13 @@ class DBTVIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
|
||||
'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'upload_date': '20160916',
|
||||
'duration': 69,
|
||||
'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
|
||||
'uploader': 'Dagbladet',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
|
||||
'only_matching': True,
|
||||
@@ -26,6 +26,20 @@ class DBTVIE(InfoExtractor):
|
||||
'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.dagbladet.no/nyheter/rekordstort-russisk-angrep/83325693',
|
||||
'info_dict': {
|
||||
'id': '1HW7fYry',
|
||||
'ext': 'mp4',
|
||||
'title': 'Putin taler - så skjer dette',
|
||||
'description': 'md5:3e8bacee33de861a9663d9a3fcc54e5e',
|
||||
'display_id': 'putin-taler-sa-skjer-dette',
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
'timestamp': 1751043600,
|
||||
'upload_date': '20250627',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id, video_id = self._match_valid_url(url).groups()
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
jwt_decode_hs256,
|
||||
parse_codecs,
|
||||
try_get,
|
||||
@@ -222,11 +223,18 @@ def _entries(self, items, language, type_, **kwargs):
|
||||
raise
|
||||
|
||||
formats = []
|
||||
for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
|
||||
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
for fmt in formats:
|
||||
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
|
||||
fmt.update(parse_codecs(fmt['format_note']))
|
||||
for fmt_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
|
||||
ext = determine_ext(fmt_url)
|
||||
if ext == 'm3u8':
|
||||
fmts = self._extract_m3u8_formats(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
for fmt in fmts:
|
||||
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
|
||||
fmt.update(parse_codecs(fmt['format_note']))
|
||||
formats.extend(fmts)
|
||||
elif ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(fmt_url, video_id, mpd_id='dash', fatal=False))
|
||||
else:
|
||||
self.report_warning(f'Skipping unsupported format extension "{ext}"')
|
||||
|
||||
yield {
|
||||
'id': video_id,
|
||||
|
||||
@@ -90,10 +90,6 @@ def _real_extract(self, url):
|
||||
webpage, 'embed data'), video_id)
|
||||
video_data = page_data['video']
|
||||
|
||||
for external in video_data.get('externals', []):
|
||||
if external.get('source') == 'vevo':
|
||||
return self.url_result('vevo:' + external['data_id'], 'Vevo')
|
||||
|
||||
video_id = video_data['id']
|
||||
title = video_data['title']
|
||||
|
||||
|
||||
@@ -1,215 +0,0 @@
|
||||
import functools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class EaglePlatformIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
eagleplatform:(?P<custom_host>[^/]+):|
|
||||
https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
|
||||
_TESTS = [{
|
||||
# http://lenta.ru/news/2015/03/06/navalny/
|
||||
'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
|
||||
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
|
||||
'info_dict': {
|
||||
'id': '227304',
|
||||
'ext': 'mp4',
|
||||
'title': 'Навальный вышел на свободу',
|
||||
'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 87,
|
||||
'view_count': int,
|
||||
'age_limit': 0,
|
||||
},
|
||||
}, {
|
||||
# http://muz-tv.ru/play/7129/
|
||||
# http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
|
||||
'url': 'eagleplatform:media.clipyou.ru:12820',
|
||||
'md5': '358597369cf8ba56675c1df15e7af624',
|
||||
'info_dict': {
|
||||
'id': '12820',
|
||||
'ext': 'mp4',
|
||||
'title': "'O Sole Mio",
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 216,
|
||||
'view_count': int,
|
||||
},
|
||||
'skip': 'Georestricted',
|
||||
}, {
|
||||
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
|
||||
'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
add_referer = functools.partial(smuggle_url, data={'referrer': url})
|
||||
|
||||
res = tuple(super()._extract_embed_urls(url, webpage))
|
||||
if res:
|
||||
return map(add_referer, res)
|
||||
|
||||
PLAYER_JS_RE = r'''
|
||||
<script[^>]+
|
||||
src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
|
||||
.+?
|
||||
'''
|
||||
# "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
|
||||
mobj = re.search(
|
||||
rf'''(?xs)
|
||||
{PLAYER_JS_RE}
|
||||
<div[^>]+
|
||||
class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
|
||||
data-id=["\'](?P<id>\d+)
|
||||
''', webpage)
|
||||
if mobj is not None:
|
||||
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
|
||||
# Generalization of "Javascript code usage", "Combined usage" and
|
||||
# "Usage without attaching to DOM" embeddings (see
|
||||
# http://dultonmedia.github.io/eplayer/)
|
||||
mobj = re.search(
|
||||
r'''(?xs)
|
||||
%s
|
||||
<script>
|
||||
.+?
|
||||
new\s+EaglePlayer\(
|
||||
(?:[^,]+\s*,\s*)?
|
||||
{
|
||||
.+?
|
||||
\bid\s*:\s*["\']?(?P<id>\d+)
|
||||
.+?
|
||||
}
|
||||
\s*\)
|
||||
.+?
|
||||
</script>
|
||||
''' % PLAYER_JS_RE, webpage) # noqa: UP031
|
||||
if mobj is not None:
|
||||
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
|
||||
|
||||
@staticmethod
|
||||
def _handle_error(response):
|
||||
status = int_or_none(response.get('status', 200))
|
||||
if status != 200:
|
||||
raise ExtractorError(' '.join(response['errors']), expected=True)
|
||||
|
||||
def _download_json(self, url_or_request, video_id, *args, **kwargs):
|
||||
try:
|
||||
response = super()._download_json(
|
||||
url_or_request, video_id, *args, **kwargs)
|
||||
except ExtractorError as ee:
|
||||
if isinstance(ee.cause, HTTPError):
|
||||
response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
|
||||
self._handle_error(response)
|
||||
raise
|
||||
return response
|
||||
|
||||
def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
|
||||
return self._download_json(url_or_request, video_id, note)['data'][0]
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
mobj = self._match_valid_url(url)
|
||||
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
|
||||
|
||||
headers = {}
|
||||
query = {
|
||||
'id': video_id,
|
||||
}
|
||||
|
||||
referrer = smuggled_data.get('referrer')
|
||||
if referrer:
|
||||
headers['Referer'] = referrer
|
||||
query['referrer'] = referrer
|
||||
|
||||
player_data = self._download_json(
|
||||
f'http://{host}/api/player_data', video_id,
|
||||
headers=headers, query=query)
|
||||
|
||||
media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
|
||||
|
||||
title = media['title']
|
||||
description = media.get('description')
|
||||
thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
|
||||
duration = int_or_none(media.get('duration'))
|
||||
view_count = int_or_none(media.get('views'))
|
||||
|
||||
age_restriction = media.get('age_restriction')
|
||||
age_limit = None
|
||||
if age_restriction:
|
||||
age_limit = 0 if age_restriction == 'allow_all' else 18
|
||||
|
||||
secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
|
||||
|
||||
formats = []
|
||||
|
||||
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False)
|
||||
formats.extend(m3u8_formats)
|
||||
|
||||
m3u8_formats_dict = {}
|
||||
for f in m3u8_formats:
|
||||
if f.get('height') is not None:
|
||||
m3u8_formats_dict[f['height']] = f
|
||||
|
||||
mp4_data = self._download_json(
|
||||
# Secure mp4 URL is constructed according to Player.prototype.mp4 from
|
||||
# http://lentaru.media.eagleplatform.com/player/player.js
|
||||
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
|
||||
video_id, 'Downloading mp4 JSON', fatal=False)
|
||||
if mp4_data:
|
||||
for format_id, format_url in mp4_data.get('data', {}).items():
|
||||
if not url_or_none(format_url):
|
||||
continue
|
||||
height = int_or_none(format_id)
|
||||
if height is not None and m3u8_formats_dict.get(height):
|
||||
f = m3u8_formats_dict[height].copy()
|
||||
f.update({
|
||||
'format_id': f['format_id'].replace('hls', 'http'),
|
||||
'protocol': 'http',
|
||||
})
|
||||
else:
|
||||
f = {
|
||||
'format_id': f'http-{format_id}',
|
||||
'height': int_or_none(format_id),
|
||||
}
|
||||
f['url'] = format_url
|
||||
formats.append(f)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'age_limit': age_limit,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class ClipYouEmbedIE(InfoExtractor):
|
||||
_VALID_URL = False
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
|
||||
if mobj is not None:
|
||||
yield smuggle_url('eagleplatform:{host}:{id}'.format(**mobj.groupdict()), {'referrer': url})
|
||||
@@ -64,14 +64,12 @@ class ERTFlixCodenameIE(ERTFlixBaseIE):
|
||||
_VALID_URL = r'ertflix:(?P<id>[\w-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'ertflix:monogramma-praxitelis-tzanoylinos',
|
||||
'md5': '5b9c2cd171f09126167e4082fc1dd0ef',
|
||||
'info_dict': {
|
||||
'id': 'monogramma-praxitelis-tzanoylinos',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:ef0b439902963d56c43ac83c3f41dd0e',
|
||||
'title': 'monogramma-praxitelis-tzanoylinos',
|
||||
},
|
||||
},
|
||||
]
|
||||
}]
|
||||
|
||||
def _extract_formats_and_subs(self, video_id):
|
||||
media_info = self._call_api(video_id, codename=video_id)
|
||||
@@ -131,13 +129,14 @@ class ERTFlixIE(ERTFlixBaseIE):
|
||||
'duration': 3166,
|
||||
'age_limit': 8,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma',
|
||||
'info_dict': {
|
||||
'id': 'ser.3448',
|
||||
'age_limit': 8,
|
||||
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
|
||||
'title': 'Μονόγραμμα',
|
||||
'title': 'Monogramma',
|
||||
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
|
||||
},
|
||||
'playlist_mincount': 64,
|
||||
}, {
|
||||
@@ -145,28 +144,28 @@ class ERTFlixIE(ERTFlixBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'ser.3448',
|
||||
'age_limit': 8,
|
||||
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
|
||||
'title': 'Μονόγραμμα',
|
||||
'title': 'Monogramma',
|
||||
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
|
||||
},
|
||||
'playlist_count': 22,
|
||||
'playlist_mincount': 66,
|
||||
}, {
|
||||
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1&season=2021%20-%202022',
|
||||
'info_dict': {
|
||||
'id': 'ser.3448',
|
||||
'age_limit': 8,
|
||||
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
|
||||
'title': 'Μονόγραμμα',
|
||||
'title': 'Monogramma',
|
||||
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
|
||||
},
|
||||
'playlist_mincount': 36,
|
||||
'playlist_mincount': 25,
|
||||
}, {
|
||||
'url': 'https://www.ertflix.gr/series/ser.164991-to-diktuo-1?season=1-9',
|
||||
'info_dict': {
|
||||
'id': 'ser.164991',
|
||||
'age_limit': 8,
|
||||
'description': 'Η πρώτη ελληνική εκπομπή με θεματολογία αποκλειστικά γύρω από το ίντερνετ.',
|
||||
'title': 'Το δίκτυο',
|
||||
'title': 'The Network',
|
||||
'description': 'The first Greek show featuring topics exclusively around the internet.',
|
||||
},
|
||||
'playlist_mincount': 9,
|
||||
'playlist_mincount': 0,
|
||||
}, {
|
||||
'url': 'https://www.ertflix.gr/en/vod/vod.127652-ta-kalytera-mas-chronia-ep1-mia-volta-sto-feggari',
|
||||
'only_matching': True,
|
||||
@@ -282,6 +281,16 @@ class ERTWebtvEmbedIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 'https://program.ert.gr/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.ertnews.gr/video/manolis-goyalles-o-anthropos-piso-apo-ti-diadiktyaki-vasilopita/',
|
||||
'info_dict': {
|
||||
'id': '2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
|
||||
'ext': 'mp4',
|
||||
'title': 'VOD - 2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
|
||||
'thumbnail': r're:https?://www\.ert\.gr/themata/photos/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -81,13 +81,14 @@ class FacebookIE(InfoExtractor):
|
||||
'description': 'md5:34675bda53336b1d16400265c2bb9b3b',
|
||||
'uploader': 'RADIO KICKS FM',
|
||||
'upload_date': '20230818',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1692346159,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'uploader_id': '100063551323670',
|
||||
'duration': 3133.583,
|
||||
'view_count': int,
|
||||
'concurrent_view_count': 0,
|
||||
},
|
||||
'expected_warnings': ['Cannot parse data'],
|
||||
}, {
|
||||
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
|
||||
'md5': '6a40d33c0eccbb1af76cf0485a052659',
|
||||
@@ -106,17 +107,18 @@ class FacebookIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '274175099429670',
|
||||
'ext': 'mp4',
|
||||
'title': 'Asif',
|
||||
'title': '119 reactions · 1.4K shares | Asif Nawab Butt on Reels',
|
||||
'description': '',
|
||||
'uploader': 'Asif Nawab Butt',
|
||||
'upload_date': '20140506',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1399398998,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl',
|
||||
'uploader_id': 'pfbid028xue38TBXRyNbiqBSV2LFs3QK3yopvKjupbqFoL6U9SKbx4p2SMdJjQSBvnjsHGWl',
|
||||
'duration': 131.03,
|
||||
'concurrent_view_count': int,
|
||||
'view_count': int,
|
||||
},
|
||||
'expected_warnings': ['Cannot parse data'],
|
||||
}, {
|
||||
'note': 'Video with DASH manifest',
|
||||
'url': 'https://www.facebook.com/video.php?v=957955867617029',
|
||||
@@ -158,7 +160,7 @@ class FacebookIE(InfoExtractor):
|
||||
'id': '10153664894881749',
|
||||
'ext': 'mp4',
|
||||
'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1456259628,
|
||||
'upload_date': '20160223',
|
||||
'uploader': 'Barack Obama',
|
||||
@@ -168,7 +170,7 @@ class FacebookIE(InfoExtractor):
|
||||
# have 1080P, but only up to 720p in swf params
|
||||
# data.video.story.attachments[].media
|
||||
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
|
||||
'md5': '1659aa21fb3dd1585874f668e81a72c8',
|
||||
'md5': '70b82ebf5f0e9b91b2a49d3db3563611',
|
||||
'info_dict': {
|
||||
'id': '10155529876156509',
|
||||
'ext': 'mp4',
|
||||
@@ -177,7 +179,7 @@ class FacebookIE(InfoExtractor):
|
||||
'timestamp': 1477818095,
|
||||
'upload_date': '20161030',
|
||||
'uploader': 'CNN',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'view_count': int,
|
||||
'uploader_id': '100059479812265',
|
||||
'concurrent_view_count': int,
|
||||
@@ -198,13 +200,11 @@ class FacebookIE(InfoExtractor):
|
||||
'uploader': 'Yaroslav Korpan',
|
||||
'uploader_id': 'pfbid06AScABAWcW91qpiuGrLt99Ef9tvwHoXP6t8KeFYEqkSfreMtfa9nTveh8b2ZEVSWl',
|
||||
'concurrent_view_count': int,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'view_count': int,
|
||||
'duration': 11736.446,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# FIXME: Cannot parse data error
|
||||
'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
|
||||
@@ -215,7 +215,7 @@ class FacebookIE(InfoExtractor):
|
||||
'timestamp': 1477305000,
|
||||
'upload_date': '20161024',
|
||||
'uploader': 'La Guía Del Varón',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
},
|
||||
'skip': 'Requires logging in',
|
||||
}, {
|
||||
@@ -244,9 +244,10 @@ class FacebookIE(InfoExtractor):
|
||||
'upload_date': '20171124',
|
||||
'uploader': 'Vickie Gentry',
|
||||
'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'duration': 148.224,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# data.node.comet_sections.content.story.attachments[].styles.attachment.media
|
||||
'url': 'https://www.facebook.com/attn/posts/pfbid0j1Czf2gGDVqeQ8KiMLFm3pWN8GxsQmeRrVhimWDzMuKQoR8r4b1knNsejELmUgyhl',
|
||||
@@ -260,7 +261,7 @@ class FacebookIE(InfoExtractor):
|
||||
'duration': 132.675,
|
||||
'uploader_id': '100064451419378',
|
||||
'view_count': int,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1701975646,
|
||||
},
|
||||
}, {
|
||||
@@ -271,9 +272,9 @@ class FacebookIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Lela Evans',
|
||||
'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'uploader': 'Lela Evans',
|
||||
'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl',
|
||||
'uploader_id': 'pfbid02wjMpknobSMnyynK3TNKN4Ww1StcpAKXgowqTyge3bz7LwHZMQ68uiXzzbu7xeryBl',
|
||||
'upload_date': '20231228',
|
||||
'timestamp': 1703804085,
|
||||
'duration': 394.347,
|
||||
@@ -326,28 +327,27 @@ class FacebookIE(InfoExtractor):
|
||||
'uploader_id': '100066514874195',
|
||||
'duration': 4524.001,
|
||||
'view_count': int,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'concurrent_view_count': int,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.all_subattachments.nodes[].media
|
||||
'url': 'https://www.facebook.com/100033620354545/videos/106560053808006/',
|
||||
'info_dict': {
|
||||
'id': '106560053808006',
|
||||
'ext': 'mp4',
|
||||
'title': 'Josef',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'title': 'Josef Novak on Reels',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'concurrent_view_count': int,
|
||||
'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl',
|
||||
'uploader_id': 'pfbid0cjYJYXpePWqhZ9DgpB6gKXrN2q3obwducdKm4wT7K5nkhbfKg5cneocYbsdaji7fl',
|
||||
'timestamp': 1549275572,
|
||||
'duration': 3.283,
|
||||
'uploader': 'Josef Novak',
|
||||
'description': '',
|
||||
'upload_date': '20190204',
|
||||
},
|
||||
'expected_warnings': ['Cannot parse data'],
|
||||
}, {
|
||||
# data.video.story.attachments[].media
|
||||
'url': 'https://www.facebook.com/watch/?v=647537299265662',
|
||||
@@ -406,7 +406,7 @@ class FacebookIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'ANALISI IN CAMPO OSCURO " Coaguli nel sangue dei vaccinati"',
|
||||
'description': 'Other event by Comitato Liberi Pensatori on Tuesday, October 18 2022',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'uploader': 'Comitato Liberi Pensatori',
|
||||
'uploader_id': '100065709540881',
|
||||
},
|
||||
@@ -414,6 +414,56 @@ class FacebookIE(InfoExtractor):
|
||||
'url': 'https://www.facebook.com/groups/1513990329015294/posts/d41d8cd9/2013209885760000/?app=fbl',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# <iframe> embed
|
||||
'url': 'http://www.unique-almeria.com/mini-hollywood.html',
|
||||
'md5': 'cba5d8c5021e9340dcefe925255e2c3e',
|
||||
'info_dict': {
|
||||
'id': '1529066599879',
|
||||
'ext': 'mp4',
|
||||
'title': 'Facebook video #1529066599879',
|
||||
},
|
||||
'expected_warnings': ['unable to extract uploader'],
|
||||
}, {
|
||||
# FIXME: Embed detection
|
||||
# <iframe> embed, plugin video
|
||||
'url': 'https://www.newsmemory.com/eedition/e-publishing-solutions/2-in-one-app/',
|
||||
'md5': 'ae97d4a44f8cc9a8b1a4c03b9ed793af',
|
||||
'info_dict': {
|
||||
'id': '10155710648695814',
|
||||
'ext': 'mp4',
|
||||
'title': 'Download the all new and improved Trinidad Express App',
|
||||
'concurrent_view_count': int,
|
||||
'description': 'md5:4806195c99908e4189b45b1c23bd4f89',
|
||||
'duration': 69.408,
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1533919195,
|
||||
'upload_date': '20180810',
|
||||
'uploader': 'Trinidad Express Newspapers',
|
||||
'uploader_id': '100064446413648',
|
||||
'view_count': int,
|
||||
},
|
||||
'expected_warnings': ['Cannot parse data'],
|
||||
}, {
|
||||
# API embed
|
||||
'url': 'https://www.curs.md/ro',
|
||||
'md5': '090bae53b9bff2be993c896edc2ea205',
|
||||
'info_dict': {
|
||||
'id': '334484292523563',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:9abffe1c86cdd967ffa224e1ccc13b90',
|
||||
'concurrent_view_count': int,
|
||||
'description': 'md5:0ba98567a61c640f9fabf1882235b33d',
|
||||
'duration': 8789.891,
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1700603114,
|
||||
'upload_date': '20231121',
|
||||
'uploader': 'Istoria Moldovei',
|
||||
'uploader_id': '100063529778592',
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {'extractor_args': {'generic': {'impersonate': ['chrome']}}},
|
||||
}]
|
||||
_SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
|
||||
_api_config = {
|
||||
'graphURI': '/api/graphql/',
|
||||
@@ -898,20 +948,24 @@ def _real_extract(self, url):
|
||||
|
||||
class FacebookPluginsVideoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
|
||||
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
|
||||
'md5': 'af83aeae1d595f377c6e47a450828155',
|
||||
'info_dict': {
|
||||
'id': '10154383743583686',
|
||||
'ext': 'mp4',
|
||||
# TODO: Fix title, uploader
|
||||
'title': 'What to do during the haze?',
|
||||
'uploader': 'Gov.sg',
|
||||
'upload_date': '20160826',
|
||||
'concurrent_view_count': int,
|
||||
'description': 'md5:81839c0979803a014b20798df255ed0b',
|
||||
'duration': 65.087,
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1472184808,
|
||||
'upload_date': '20160826',
|
||||
'uploader': 'gov.sg',
|
||||
'uploader_id': '100064718678925',
|
||||
'view_count': int,
|
||||
},
|
||||
'add_ie': [FacebookIE.ie_key()],
|
||||
'expected_warnings': ['Cannot parse data'],
|
||||
}, {
|
||||
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
|
||||
'only_matching': True,
|
||||
@@ -945,7 +999,7 @@ class FacebookRedirectURLIE(InfoExtractor):
|
||||
'tags': 'count:11',
|
||||
'duration': 3332,
|
||||
'live_status': 'not_live',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/pO8h3EaFRdo/maxresdefault.jpg',
|
||||
'thumbnail': r're:https?://i\.ytimg\.com/vi/.+',
|
||||
'channel_url': 'https://www.youtube.com/channel/UCGBpxWJr9FNOcFYA5GkKrMg',
|
||||
'availability': 'public',
|
||||
'uploader_url': 'http://www.youtube.com/user/brtvofficial',
|
||||
@@ -954,8 +1008,7 @@ class FacebookRedirectURLIE(InfoExtractor):
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
'params': {'skip_download': 'Youtube'},
|
||||
'skip': 'Youtube video is now private',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -968,22 +1021,20 @@ def _real_extract(self, url):
|
||||
class FacebookReelIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/reel/(?P<id>\d+)'
|
||||
IE_NAME = 'facebook:reel'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.facebook.com/reel/1195289147628387',
|
||||
'md5': 'a53256d10fc2105441fe0c4212ed8cea',
|
||||
'md5': 'aeb0153ecb2eaacdf2dc2bf88f593fef',
|
||||
'info_dict': {
|
||||
'id': '1195289147628387',
|
||||
'ext': 'mp4',
|
||||
'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$',
|
||||
'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$',
|
||||
'uploader': 'Beast Camp Training',
|
||||
'title': '9.7K views · 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the “Slapathon” commence!! 👊👋 | Beast Camp Training',
|
||||
'description': 'md5:5a767dc7e78718667b150a7facc4a34f',
|
||||
'uploader': '9.7K views · 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the “Slapathon” commence!! 👊👋 | Beast Camp Training',
|
||||
'uploader_id': '100040874179269',
|
||||
'duration': 9.579,
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1637502609,
|
||||
'upload_date': '20211121',
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
},
|
||||
@@ -998,7 +1049,6 @@ def _real_extract(self, url):
|
||||
class FacebookAdsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/ads/library/?\?(?:[^#]+&)?id=(?P<id>\d+)'
|
||||
IE_NAME = 'facebook:ads'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.facebook.com/ads/library/?id=899206155126718',
|
||||
'info_dict': {
|
||||
@@ -1008,12 +1058,13 @@ class FacebookAdsIE(InfoExtractor):
|
||||
'description': 'md5:0822724069e3aca97cbed5dabbab282e',
|
||||
'uploader': 'Kandao',
|
||||
'uploader_id': '774114102743284',
|
||||
'uploader_url': r're:^https?://.*',
|
||||
'uploader_url': 'https://facebook.com/KandaoVR',
|
||||
'timestamp': 1702548330,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'upload_date': '20231214',
|
||||
'like_count': int,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# key 'watermarked_video_sd_url' missing
|
||||
'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
|
||||
@@ -1024,9 +1075,9 @@ class FacebookAdsIE(InfoExtractor):
|
||||
'description': 'md5:02a446ace7ff8c3c37a2892922492490',
|
||||
'uploader': 'mat.nawrocki',
|
||||
'uploader_id': '148586968341456',
|
||||
'uploader_url': r're:^https?://.*',
|
||||
'uploader_url': 'https://www.instagram.com/_u/mat.nawrocki',
|
||||
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
|
||||
'timestamp': 1723452305,
|
||||
'thumbnail': r're:^https?://.*',
|
||||
'upload_date': '20240812',
|
||||
'like_count': int,
|
||||
},
|
||||
@@ -1037,12 +1088,13 @@ class FacebookAdsIE(InfoExtractor):
|
||||
'title': 'Jusqu\u2019\u00e0 -25% sur une s\u00e9lection de vins p\u00e9tillants italiens ',
|
||||
'uploader': 'Eataly Paris Marais',
|
||||
'uploader_id': '2086668958314152',
|
||||
'uploader_url': r're:^https?://.*',
|
||||
'uploader_url': 'https://facebook.com/EatalyParisMarais',
|
||||
'timestamp': 1703571529,
|
||||
'upload_date': '20231226',
|
||||
'like_count': int,
|
||||
},
|
||||
'playlist_count': 3,
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
|
||||
'only_matching': True,
|
||||
|
||||
237
yt_dlp/extractor/faulio.py
Normal file
237
yt_dlp/extractor/faulio.py
Normal file
@@ -0,0 +1,237 @@
|
||||
import re
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none, js_to_json, url_or_none
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FaulioBaseIE(InfoExtractor):
|
||||
_DOMAINS = (
|
||||
'aloula.sba.sa',
|
||||
'bahry.com',
|
||||
'maraya.sba.net.ae',
|
||||
'sat7plus.org',
|
||||
)
|
||||
_LANGUAGES = ('ar', 'en', 'fa')
|
||||
_BASE_URL_RE = fr'https?://(?:{"|".join(map(re.escape, _DOMAINS))})/(?:(?:{"|".join(_LANGUAGES)})/)?'
|
||||
|
||||
def _get_headers(self, url):
|
||||
parsed_url = urllib.parse.urlparse(url)
|
||||
return {
|
||||
'Referer': url,
|
||||
'Origin': f'{parsed_url.scheme}://{parsed_url.hostname}',
|
||||
}
|
||||
|
||||
def _get_api_base(self, url, video_id):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
config_data = self._search_json(
|
||||
r'window\.__NUXT__\.config=', webpage, 'config', video_id, transform_source=js_to_json)
|
||||
return config_data['public']['TRANSLATIONS_API_URL']
|
||||
|
||||
|
||||
class FaulioIE(FaulioBaseIE):
|
||||
_VALID_URL = fr'{FaulioBaseIE._BASE_URL_RE}(?:episode|media)/(?P<id>[a-zA-Z0-9-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://aloula.sba.sa/en/episode/29102',
|
||||
'info_dict': {
|
||||
'id': 'aloula.faulio.com_29102',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'هذا-مكانك-03-004-v-29102',
|
||||
'title': 'الحلقة 4',
|
||||
'episode': 'الحلقة 4',
|
||||
'description': '',
|
||||
'series': 'هذا مكانك',
|
||||
'season': 'Season 3',
|
||||
'season_number': 3,
|
||||
'episode_number': 4,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 4855,
|
||||
'age_limit': 3,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://bahry.com/en/media/1191',
|
||||
'info_dict': {
|
||||
'id': 'bahry.faulio.com_1191',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'Episode-4-1191',
|
||||
'title': 'Episode 4',
|
||||
'episode': 'Episode 4',
|
||||
'description': '',
|
||||
'series': 'Wild Water',
|
||||
'season': 'Season 1',
|
||||
'season_number': 1,
|
||||
'episode_number': 4,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1653,
|
||||
'age_limit': 0,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://maraya.sba.net.ae/episode/127735',
|
||||
'info_dict': {
|
||||
'id': 'maraya.faulio.com_127735',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'عبدالله-الهاجري---عبدالرحمن-المطروشي-127735',
|
||||
'title': 'عبدالله الهاجري - عبدالرحمن المطروشي',
|
||||
'episode': 'عبدالله الهاجري - عبدالرحمن المطروشي',
|
||||
'description': 'md5:53de01face66d3d6303221e5a49388a0',
|
||||
'series': 'أبناؤنا في الخارج',
|
||||
'season': 'Season 3',
|
||||
'season_number': 3,
|
||||
'episode_number': 7,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1316,
|
||||
'age_limit': 0,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://sat7plus.org/episode/18165',
|
||||
'info_dict': {
|
||||
'id': 'sat7.faulio.com_18165',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'ep-13-ADHD-18165',
|
||||
'title': 'ADHD and creativity',
|
||||
'episode': 'ADHD and creativity',
|
||||
'description': '',
|
||||
'series': 'ADHD Podcast',
|
||||
'season': 'Season 1',
|
||||
'season_number': 1,
|
||||
'episode_number': 13,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 2492,
|
||||
'age_limit': 0,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://aloula.sba.sa/en/episode/0',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
api_base = self._get_api_base(url, video_id)
|
||||
video_info = self._download_json(f'{api_base}/video/{video_id}', video_id, fatal=False)
|
||||
player_info = self._download_json(f'{api_base}/video/{video_id}/player', video_id)
|
||||
|
||||
headers = self._get_headers(url)
|
||||
formats = []
|
||||
subtitles = {}
|
||||
if hls_url := traverse_obj(player_info, ('settings', 'protocols', 'hls', {url_or_none})):
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False, headers=headers)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
if mpd_url := traverse_obj(player_info, ('settings', 'protocols', 'dash', {url_or_none})):
|
||||
fmts, subs = self._extract_mpd_formats_and_subtitles(
|
||||
mpd_url, video_id, mpd_id='dash', fatal=False, headers=headers)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
return {
|
||||
'id': f'{urllib.parse.urlparse(api_base).hostname}_{video_id}',
|
||||
**traverse_obj(traverse_obj(video_info, ('blocks', 0)), {
|
||||
'display_id': ('slug', {str}),
|
||||
'title': ('title', {str}),
|
||||
'episode': ('title', {str}),
|
||||
'description': ('description', {str}),
|
||||
'series': ('program_title', {str}),
|
||||
'season_number': ('season_number', {int_or_none}),
|
||||
'episode_number': ('episode', {int_or_none}),
|
||||
'thumbnail': ('image', {url_or_none}),
|
||||
'duration': ('duration', 'total', {int_or_none}),
|
||||
'age_limit': ('age_rating', {int_or_none}),
|
||||
}),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'http_headers': headers,
|
||||
}
|
||||
|
||||
|
||||
class FaulioLiveIE(FaulioBaseIE):
|
||||
_VALID_URL = fr'{FaulioBaseIE._BASE_URL_RE}live/(?P<id>[a-zA-Z0-9-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://aloula.sba.sa/live/saudiatv',
|
||||
'info_dict': {
|
||||
'id': 'aloula.faulio.com_saudiatv',
|
||||
'title': str,
|
||||
'description': str,
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'Livestream',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://bahry.com/live/1',
|
||||
'info_dict': {
|
||||
'id': 'bahry.faulio.com_1',
|
||||
'title': str,
|
||||
'description': str,
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'Livestream',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://maraya.sba.net.ae/live/1',
|
||||
'info_dict': {
|
||||
'id': 'maraya.faulio.com_1',
|
||||
'title': str,
|
||||
'description': str,
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'Livestream',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://sat7plus.org/live/pars',
|
||||
'info_dict': {
|
||||
'id': 'sat7.faulio.com_pars',
|
||||
'title': str,
|
||||
'description': str,
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'Livestream',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://sat7plus.org/fa/live/arabic',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
api_base = self._get_api_base(url, video_id)
|
||||
|
||||
channel = traverse_obj(
|
||||
self._download_json(f'{api_base}/channels', video_id),
|
||||
(lambda k, v: v['url'] == video_id, any))
|
||||
|
||||
headers = self._get_headers(url)
|
||||
formats = []
|
||||
subtitles = {}
|
||||
if hls_url := traverse_obj(channel, ('streams', 'hls', {url_or_none})):
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
hls_url, video_id, 'mp4', m3u8_id='hls', live=True, fatal=False, headers=headers)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
if mpd_url := traverse_obj(channel, ('streams', 'mpd', {url_or_none})):
|
||||
fmts, subs = self._extract_mpd_formats_and_subtitles(
|
||||
mpd_url, video_id, mpd_id='dash', fatal=False, headers=headers)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
return {
|
||||
'id': f'{urllib.parse.urlparse(api_base).hostname}_{video_id}',
|
||||
**traverse_obj(channel, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('description', {str}),
|
||||
}),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'http_headers': headers,
|
||||
'is_live': True,
|
||||
}
|
||||
@@ -22,8 +22,23 @@ class FC2IE(InfoExtractor):
|
||||
'md5': 'a6ebe8ebe0396518689d963774a54eb7',
|
||||
'info_dict': {
|
||||
'id': '20121103kUan1KHs',
|
||||
'ext': 'flv',
|
||||
'title': 'Boxing again with Puff',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://.+\.jpe?g',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}, {
|
||||
# Direct video url
|
||||
'url': 'https://video.fc2.com/content/20121209FP73fxDx',
|
||||
'md5': '066bdb9b3a56a97f49cbf0d0b8a75a1f',
|
||||
'info_dict': {
|
||||
'id': '20121209FP73fxDx',
|
||||
'title': 'Farewelling The Wiggles Live in Sydney Dec 8 2012',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://.+\.jpe?g',
|
||||
'description': 'Saying goodbye to the Wiggles at their Celebration Concert in Sydney, and what a concert that was!',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
|
||||
@@ -104,7 +119,7 @@ def _real_extract(self, url):
|
||||
'title': title,
|
||||
'url': vid_url,
|
||||
'ext': 'mp4',
|
||||
'protocol': 'm3u8_native',
|
||||
'protocol': 'm3u8_native' if vidplaylist.get('type') == 2 else 'https',
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
@@ -17,8 +17,140 @@
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FloatplaneIE(InfoExtractor):
|
||||
class FloatplaneBaseIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
post_id = self._match_id(url)
|
||||
|
||||
post_data = self._download_json(
|
||||
f'{self._BASE_URL}/api/v3/content/post', post_id, query={'id': post_id},
|
||||
note='Downloading post data', errnote='Unable to download post data',
|
||||
impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
|
||||
raise ExtractorError('Post does not contain a video or audio track', expected=True)
|
||||
|
||||
uploader_url = format_field(
|
||||
post_data, [('creator', 'urlname')], f'{self._BASE_URL}/channel/%s/home') or None
|
||||
|
||||
common_info = {
|
||||
'uploader_url': uploader_url,
|
||||
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
|
||||
'availability': self._availability(needs_subscription=True),
|
||||
**traverse_obj(post_data, {
|
||||
'uploader': ('creator', 'title', {str}),
|
||||
'uploader_id': ('creator', 'id', {str}),
|
||||
'channel': ('channel', 'title', {str}),
|
||||
'channel_id': ('channel', 'id', {str}),
|
||||
'release_timestamp': ('releaseDate', {parse_iso8601}),
|
||||
}),
|
||||
}
|
||||
|
||||
items = []
|
||||
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
|
||||
media_id = media['id']
|
||||
media_typ = media.get('type') or 'video'
|
||||
|
||||
metadata = self._download_json(
|
||||
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
|
||||
note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
stream = self._download_json(
|
||||
f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
|
||||
'type': 'vod' if media_typ == 'video' else 'aod',
|
||||
'guid': metadata['guid'],
|
||||
}, note=f'Downloading {media_typ} stream data',
|
||||
impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
|
||||
|
||||
def format_path(params):
|
||||
path = path_template
|
||||
for i, val in (params or {}).items():
|
||||
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
|
||||
return path
|
||||
|
||||
formats = []
|
||||
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
|
||||
url = urljoin(stream['cdn'], format_path(traverse_obj(
|
||||
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
|
||||
format_id = traverse_obj(quality, ('name', {str}))
|
||||
hls_aes = {}
|
||||
m3u8_data = None
|
||||
|
||||
# If we need impersonation for the API, then we need it for HLS keys too: extract in advance
|
||||
if self._IMPERSONATE_TARGET is not None:
|
||||
m3u8_data = self._download_webpage(
|
||||
url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
|
||||
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
|
||||
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
|
||||
if not m3u8_data:
|
||||
continue
|
||||
|
||||
key_url = self._search_regex(
|
||||
r'#EXT-X-KEY:METHOD=AES-128,URI="(https?://[^"]+)"',
|
||||
m3u8_data, 'HLS AES key URI', default=None)
|
||||
if key_url:
|
||||
urlh = self._request_webpage(
|
||||
key_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
|
||||
note=join_nonempty('Downloading', format_id, 'HLS AES key', delim=' '),
|
||||
errnote=join_nonempty('Failed to download', format_id, 'HLS AES key', delim=' '))
|
||||
if urlh:
|
||||
hls_aes['key'] = urlh.read().hex()
|
||||
|
||||
formats.append({
|
||||
**traverse_obj(quality, {
|
||||
'format_note': ('label', {str}),
|
||||
'width': ('width', {int}),
|
||||
'height': ('height', {int}),
|
||||
}),
|
||||
**parse_codecs(quality.get('codecs')),
|
||||
'url': url,
|
||||
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
|
||||
'format_id': format_id,
|
||||
'hls_media_playlist_data': m3u8_data,
|
||||
'hls_aes': hls_aes or None,
|
||||
})
|
||||
items.append({
|
||||
**common_info,
|
||||
'id': media_id,
|
||||
**traverse_obj(metadata, {
|
||||
'title': ('title', {str}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
post_info = {
|
||||
**common_info,
|
||||
'id': post_id,
|
||||
'display_id': post_id,
|
||||
**traverse_obj(post_data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('text', {clean_html}),
|
||||
'like_count': ('likes', {int_or_none}),
|
||||
'dislike_count': ('dislikes', {int_or_none}),
|
||||
'comment_count': ('comments', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'http_headers': self._HEADERS,
|
||||
}
|
||||
|
||||
if len(items) > 1:
|
||||
return self.playlist_result(items, **post_info)
|
||||
|
||||
post_info.update(items[0])
|
||||
return post_info
|
||||
|
||||
|
||||
class FloatplaneIE(FloatplaneBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/post/(?P<id>\w+)'
|
||||
_BASE_URL = 'https://www.floatplane.com'
|
||||
_IMPERSONATE_TARGET = None
|
||||
_HEADERS = {
|
||||
'Origin': _BASE_URL,
|
||||
'Referer': f'{_BASE_URL}/',
|
||||
}
|
||||
_TESTS = [{
|
||||
'url': 'https://www.floatplane.com/post/2Yf3UedF7C',
|
||||
'info_dict': {
|
||||
@@ -170,105 +302,9 @@ class FloatplaneIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._get_cookies('https://www.floatplane.com').get('sails.sid'):
|
||||
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
|
||||
self.raise_login_required()
|
||||
|
||||
def _real_extract(self, url):
|
||||
post_id = self._match_id(url)
|
||||
|
||||
post_data = self._download_json(
|
||||
'https://www.floatplane.com/api/v3/content/post', post_id, query={'id': post_id},
|
||||
note='Downloading post data', errnote='Unable to download post data')
|
||||
|
||||
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
|
||||
raise ExtractorError('Post does not contain a video or audio track', expected=True)
|
||||
|
||||
uploader_url = format_field(
|
||||
post_data, [('creator', 'urlname')], 'https://www.floatplane.com/channel/%s/home') or None
|
||||
|
||||
common_info = {
|
||||
'uploader_url': uploader_url,
|
||||
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
|
||||
'availability': self._availability(needs_subscription=True),
|
||||
**traverse_obj(post_data, {
|
||||
'uploader': ('creator', 'title', {str}),
|
||||
'uploader_id': ('creator', 'id', {str}),
|
||||
'channel': ('channel', 'title', {str}),
|
||||
'channel_id': ('channel', 'id', {str}),
|
||||
'release_timestamp': ('releaseDate', {parse_iso8601}),
|
||||
}),
|
||||
}
|
||||
|
||||
items = []
|
||||
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
|
||||
media_id = media['id']
|
||||
media_typ = media.get('type') or 'video'
|
||||
|
||||
metadata = self._download_json(
|
||||
f'https://www.floatplane.com/api/v3/content/{media_typ}', media_id, query={'id': media_id},
|
||||
note=f'Downloading {media_typ} metadata')
|
||||
|
||||
stream = self._download_json(
|
||||
'https://www.floatplane.com/api/v2/cdn/delivery', media_id, query={
|
||||
'type': 'vod' if media_typ == 'video' else 'aod',
|
||||
'guid': metadata['guid'],
|
||||
}, note=f'Downloading {media_typ} stream data')
|
||||
|
||||
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
|
||||
|
||||
def format_path(params):
|
||||
path = path_template
|
||||
for i, val in (params or {}).items():
|
||||
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
|
||||
return path
|
||||
|
||||
formats = []
|
||||
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
|
||||
url = urljoin(stream['cdn'], format_path(traverse_obj(
|
||||
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
|
||||
formats.append({
|
||||
**traverse_obj(quality, {
|
||||
'format_id': ('name', {str}),
|
||||
'format_note': ('label', {str}),
|
||||
'width': ('width', {int}),
|
||||
'height': ('height', {int}),
|
||||
}),
|
||||
**parse_codecs(quality.get('codecs')),
|
||||
'url': url,
|
||||
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
|
||||
})
|
||||
|
||||
items.append({
|
||||
**common_info,
|
||||
'id': media_id,
|
||||
**traverse_obj(metadata, {
|
||||
'title': ('title', {str}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
post_info = {
|
||||
**common_info,
|
||||
'id': post_id,
|
||||
'display_id': post_id,
|
||||
**traverse_obj(post_data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('text', {clean_html}),
|
||||
'like_count': ('likes', {int_or_none}),
|
||||
'dislike_count': ('dislikes', {int_or_none}),
|
||||
'comment_count': ('comments', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
if len(items) > 1:
|
||||
return self.playlist_result(items, **post_info)
|
||||
|
||||
post_info.update(items[0])
|
||||
return post_info
|
||||
|
||||
|
||||
class FloatplaneChannelIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'
|
||||
|
||||
@@ -1,9 +1,7 @@
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
@@ -58,16 +56,7 @@ class FrancaisFacileIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = urllib.parse.unquote(self._match_id(url))
|
||||
|
||||
try: # yt-dlp's default user-agents are too old and blocked by the site
|
||||
webpage = self._download_webpage(url, display_id, headers={
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
|
||||
})
|
||||
except ExtractorError as e:
|
||||
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
|
||||
raise
|
||||
# Retry with impersonation if hardcoded UA is insufficient
|
||||
webpage = self._download_webpage(url, display_id, impersonate=True)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
data = self._search_json(
|
||||
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import json
|
||||
import re
|
||||
import urllib.parse
|
||||
|
||||
@@ -19,7 +18,11 @@
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import find_element, traverse_obj
|
||||
from ..utils.traversal import (
|
||||
find_element,
|
||||
get_first,
|
||||
traverse_obj,
|
||||
)
|
||||
|
||||
|
||||
class FranceTVBaseInfoExtractor(InfoExtractor):
|
||||
@@ -121,9 +124,10 @@ def _extract_video(self, video_id, hostname=None):
|
||||
elif code := traverse_obj(dinfo, ('code', {int})):
|
||||
if code == 2009:
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
elif code in (2015, 2017):
|
||||
elif code in (2015, 2017, 2019):
|
||||
# 2015: L'accès à cette vidéo est impossible. (DRM-only)
|
||||
# 2017: Cette vidéo n'est pas disponible depuis le site web mobile (b/c DRM)
|
||||
# 2019: L'accès à cette vidéo est incompatible avec votre configuration. (DRM-only)
|
||||
drm_formats = True
|
||||
continue
|
||||
self.report_warning(
|
||||
@@ -258,7 +262,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
|
||||
_TESTS = [{
|
||||
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
|
||||
'info_dict': {
|
||||
'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', # old: c5bda21d-2c6f-4470-8849-3d8327adb2ba'
|
||||
'id': 'b2cf9fd8-e971-4757-8651-848f2772df61', # old: ec217ecc-0733-48cf-ac06-af1347b849d1
|
||||
'ext': 'mp4',
|
||||
'title': '13h15, le dimanche... - Les mystères de Jésus',
|
||||
'timestamp': 1502623500,
|
||||
@@ -269,7 +273,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': [FranceTVIE.ie_key()],
|
||||
'skip': 'Unfortunately, this video is no longer available',
|
||||
}, {
|
||||
# geo-restricted
|
||||
'url': 'https://www.france.tv/enfants/six-huit-ans/foot2rue/saison-1/3066387-duel-au-vieux-port.html',
|
||||
@@ -287,7 +291,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1441,
|
||||
},
|
||||
'skip': 'No longer available',
|
||||
'skip': 'Unfortunately, this video is no longer available',
|
||||
}, {
|
||||
# geo-restricted livestream (workflow == 'token-akamai')
|
||||
'url': 'https://www.france.tv/france-4/direct.html',
|
||||
@@ -308,6 +312,19 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {'skip_download': 'livestream'},
|
||||
}, {
|
||||
# Not geo-restricted
|
||||
'url': 'https://www.france.tv/france-2/la-maison-des-maternelles/5574051-nous-sommes-amis-et-nous-avons-fait-un-enfant-ensemble.html',
|
||||
'info_dict': {
|
||||
'id': 'b448bfe4-9fe7-11ee-97d8-2ba3426fa3df',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nous sommes amis et nous avons fait un enfant ensemble - Émission du jeudi 21 décembre 2023',
|
||||
'duration': 1065,
|
||||
'thumbnail': r're:https?://.+/.+\.jpg',
|
||||
'timestamp': 1703147921,
|
||||
'upload_date': '20231221',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
# france3
|
||||
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
|
||||
@@ -342,31 +359,11 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.goplay
|
||||
def _find_json(self, s):
|
||||
return self._search_json(
|
||||
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
nextjs_data = traverse_obj(
|
||||
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
|
||||
(..., {json.loads}, ..., {self._find_json}, ..., 'children', ..., ..., 'children', ..., ..., 'children'))
|
||||
|
||||
if traverse_obj(nextjs_data, (..., ..., 'children', ..., 'isLive', {bool}, any)):
|
||||
# For livestreams we need the id of the stream instead of the currently airing episode id
|
||||
video_id = traverse_obj(nextjs_data, (
|
||||
..., ..., 'children', ..., 'children', ..., 'children', ..., 'children', ..., ...,
|
||||
'children', ..., ..., 'children', ..., ..., 'children', (..., (..., ...)),
|
||||
'options', 'id', {str}, any))
|
||||
else:
|
||||
video_id = traverse_obj(nextjs_data, (
|
||||
..., ..., ..., 'children',
|
||||
lambda _, v: v['video']['url'] == urllib.parse.urlparse(url).path,
|
||||
'video', ('playerReplayId', 'siId'), {str}, any))
|
||||
|
||||
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
|
||||
video_id = get_first(nextjs_data, ('options', 'id', {str}))
|
||||
if not video_id:
|
||||
raise ExtractorError('Unable to extract video ID')
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -112,16 +112,17 @@ class GlomexIE(GlomexBaseIE):
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://video.glomex.com/sport/v-cb24uwg77hgh-nach-2-0-sieg-guardiola-mit-mancity-vor-naechstem-titel',
|
||||
'md5': 'cec33a943c4240c9cb33abea8c26242e',
|
||||
'info_dict': {
|
||||
'id': 'v-cb24uwg77hgh',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:38a90cedcfadd72982c81acf13556e0c',
|
||||
'title': 'Nach 2:0-Sieg: Guardiola mit ManCity vor nächstem Titel',
|
||||
'description': 'md5:1ea6b6caff1443fcbbba159e432eedb8',
|
||||
'duration': 29600,
|
||||
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
|
||||
'timestamp': 1619895017,
|
||||
'upload_date': '20210501',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -140,16 +141,17 @@ class GlomexEmbedIE(GlomexBaseIE):
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://player.glomex.com/integration/1/iframe-player.html?integrationId=4059a013k56vb2yd&playlistId=v-cfa6lye0dkdd-sf',
|
||||
'md5': '68f259b98cc01918ac34180142fce287',
|
||||
'info_dict': {
|
||||
'id': 'v-cfa6lye0dkdd-sf',
|
||||
'ext': 'mp4',
|
||||
'title': 'Φώφη Γεννηματά: Ο επικήδειος λόγος του 17χρονου γιου της, Γιώργου',
|
||||
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
|
||||
'timestamp': 1635337199,
|
||||
'duration': 133080,
|
||||
'upload_date': '20211027',
|
||||
'description': 'md5:e741185fc309310ff5d0c789b437be66',
|
||||
'title': 'md5:35647293513a6c92363817a0fb0a7961',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://player.glomex.com/integration/1/iframe-player.html?origin=fullpage&integrationId=19syy24xjn1oqlpc&playlistId=rl-vcb49w1fb592p&playlistIndex=0',
|
||||
'info_dict': {
|
||||
@@ -157,12 +159,27 @@ class GlomexEmbedIE(GlomexBaseIE):
|
||||
},
|
||||
'playlist_count': 100,
|
||||
}, {
|
||||
# Geo-restricted
|
||||
'url': 'https://player.glomex.com/integration/1/iframe-player.html?playlistId=cl-bgqaata6aw8x&integrationId=19syy24xjn1oqlpc',
|
||||
'info_dict': {
|
||||
'id': 'cl-bgqaata6aw8x',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.skai.gr/news/world/iatrikos-syllogos-tourkias-to-turkovac-aplo-dialyma-erntogan-eiste-apateones-kai-pseytes',
|
||||
'info_dict': {
|
||||
'id': 'v-ch2nkhcirwc9-sf',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ιατρικός Σύλλογος Τουρκίας: Το Turkovac είναι ένα απλό διάλυμα –Ερντογάν: Είστε απατεώνες και ψεύτες',
|
||||
'description': 'md5:8b517a61d577efe7e36fde72fd535995',
|
||||
'duration': 460000,
|
||||
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
|
||||
'timestamp': 1641885019,
|
||||
'upload_date': '20220111',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def build_player_url(cls, video_id, integration, origin_url=None):
|
||||
|
||||
@@ -5,16 +5,11 @@
|
||||
import hmac
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
remove_end,
|
||||
traverse_obj,
|
||||
)
|
||||
from ..utils import ExtractorError, int_or_none
|
||||
from ..utils.traversal import get_first, traverse_obj
|
||||
|
||||
|
||||
class GoPlayIE(InfoExtractor):
|
||||
@@ -27,10 +22,10 @@ class GoPlayIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '2baa4560-87a0-421b-bffc-359914e3c387',
|
||||
'ext': 'mp4',
|
||||
'title': 'S22 - Aflevering 1',
|
||||
'title': 'De Slimste Mens ter Wereld - S22 - Aflevering 1',
|
||||
'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
|
||||
'series': 'De Slimste Mens ter Wereld',
|
||||
'episode': 'Episode 1',
|
||||
'episode': 'Wordt aangekondigd',
|
||||
'season_number': 22,
|
||||
'episode_number': 1,
|
||||
'season': 'Season 22',
|
||||
@@ -52,7 +47,7 @@ class GoPlayIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
|
||||
'ext': 'mp4',
|
||||
'title': 'S11 - Aflevering 1',
|
||||
'title': 'De Mol - S11 - Aflevering 1',
|
||||
'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
|
||||
'episode': 'Episode 1',
|
||||
'series': 'De Mol',
|
||||
@@ -75,21 +70,13 @@ def _real_initialize(self):
|
||||
if not self._id_token:
|
||||
raise self.raise_login_required(method='password')
|
||||
|
||||
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.francetv
|
||||
def _find_json(self, s):
|
||||
return self._search_json(
|
||||
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
nextjs_data = traverse_obj(
|
||||
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
|
||||
(..., {json.loads}, ..., {self._find_json}, ...))
|
||||
meta = traverse_obj(nextjs_data, (
|
||||
..., ..., 'children', ..., ..., 'children',
|
||||
lambda _, v: v['video']['path'] == urllib.parse.urlparse(url).path, 'video', any))
|
||||
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
|
||||
meta = get_first(nextjs_data, (
|
||||
lambda k, v: k in ('video', 'meta') and v['path'] == urllib.parse.urlparse(url).path))
|
||||
|
||||
video_id = meta['uuid']
|
||||
info_dict = traverse_obj(meta, {
|
||||
@@ -98,19 +85,18 @@ def _real_extract(self, url):
|
||||
})
|
||||
|
||||
if traverse_obj(meta, ('program', 'subtype')) != 'movie':
|
||||
for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
|
||||
episode_data = traverse_obj(
|
||||
season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
|
||||
for season_data in traverse_obj(nextjs_data, (..., 'playlists', ..., {dict})):
|
||||
episode_data = traverse_obj(season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
|
||||
if not episode_data:
|
||||
continue
|
||||
|
||||
episode_title = traverse_obj(
|
||||
episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
|
||||
season_number = traverse_obj(season_data, ('season', {int_or_none}))
|
||||
info_dict.update({
|
||||
'title': episode_title or info_dict.get('title'),
|
||||
'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
|
||||
'season_number': traverse_obj(season_data, ('season', {int_or_none})),
|
||||
'episode': traverse_obj(episode_data, ('episodeTitle', {str})),
|
||||
'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
|
||||
'season_number': season_number,
|
||||
'series': self._search_regex(
|
||||
fr'^(.+)? - S{season_number} - ', info_dict.get('title'), 'series', default=None),
|
||||
})
|
||||
break
|
||||
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import functools
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
@@ -9,77 +10,126 @@
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
OnDemandPagedList,
|
||||
determine_ext,
|
||||
filter_dict,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
jwt_decode_hs256,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import require, traverse_obj
|
||||
|
||||
|
||||
class HotStarBaseIE(InfoExtractor):
|
||||
_TOKEN_NAME = 'userUP'
|
||||
_BASE_URL = 'https://www.hotstar.com'
|
||||
_API_URL = 'https://api.hotstar.com'
|
||||
_API_URL_V2 = 'https://apix.hotstar.com/v2'
|
||||
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
|
||||
|
||||
_FREE_HEADERS = {
|
||||
'user-agent': 'Hotstar;in.startv.hotstar/25.06.30.0.11580 (Android/12)',
|
||||
'x-hs-client': 'platform:android;app_id:in.startv.hotstar;app_version:25.06.30.0;os:Android;os_version:12;schema_version:0.0.1523',
|
||||
'x-hs-platform': 'android',
|
||||
}
|
||||
_SUB_HEADERS = {
|
||||
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
|
||||
'x-hs-client': 'platform:androidtv;app_id:in.startv.hotstar.dplus.tv;app_version:23.08.14.4;os:Android;os_version:13;schema_version:0.0.970',
|
||||
'x-hs-platform': 'androidtv',
|
||||
}
|
||||
|
||||
def _has_active_subscription(self, cookies, server_time):
|
||||
server_time = int_or_none(server_time) or int(time.time())
|
||||
expiry = traverse_obj(cookies, (
|
||||
self._TOKEN_NAME, 'value', {jwt_decode_hs256}, 'sub', {json.loads},
|
||||
'subscriptions', 'in', ..., 'expiry', {parse_iso8601}, all, {max})) or 0
|
||||
return expiry > server_time
|
||||
|
||||
def _call_api_v1(self, path, *args, **kwargs):
|
||||
return self._download_json(
|
||||
f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
|
||||
headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
|
||||
|
||||
def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
|
||||
def _call_api_impl(self, path, video_id, query, cookies=None, st=None):
|
||||
st = int_or_none(st) or int(time.time())
|
||||
exp = st + 6000
|
||||
auth = f'st={st}~exp={exp}~acl=/*'
|
||||
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
|
||||
|
||||
if cookies and cookies.get('userUP'):
|
||||
token = cookies.get('userUP').value
|
||||
else:
|
||||
token = self._download_json(
|
||||
f'{self._API_URL}/um/v3/users',
|
||||
video_id, note='Downloading token',
|
||||
data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
|
||||
headers={
|
||||
'hotstarauth': auth,
|
||||
'x-hs-platform': 'PCTV', # or 'web'
|
||||
'Content-Type': 'application/json',
|
||||
})['user_identity']
|
||||
|
||||
response = self._download_json(
|
||||
f'{self._API_URL}/{path}', video_id, query=query,
|
||||
headers={
|
||||
f'{self._API_URL_V2}/{path}', video_id, query=query,
|
||||
headers=filter_dict({
|
||||
**(self._SUB_HEADERS if self._has_active_subscription(cookies, st) else self._FREE_HEADERS),
|
||||
'hotstarauth': auth,
|
||||
'x-hs-appversion': '6.72.2',
|
||||
'x-hs-platform': 'web',
|
||||
'x-hs-usertoken': token,
|
||||
})
|
||||
'x-hs-usertoken': traverse_obj(cookies, (self._TOKEN_NAME, 'value')),
|
||||
'x-hs-device-id': traverse_obj(cookies, ('deviceId', 'value')) or str(uuid.uuid4()),
|
||||
'content-type': 'application/json',
|
||||
}))
|
||||
|
||||
if response['message'] != "Playback URL's fetched successfully":
|
||||
raise ExtractorError(
|
||||
response['message'], expected=True)
|
||||
return response['data']
|
||||
if not traverse_obj(response, ('success', {dict})):
|
||||
raise ExtractorError('API call was unsuccessful')
|
||||
return response['success']
|
||||
|
||||
def _call_api_v2(self, path, video_id, st=None, cookies=None):
|
||||
return self._call_api_impl(
|
||||
f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
|
||||
'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
|
||||
'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
|
||||
'os-name': 'Windows',
|
||||
'os-version': '10',
|
||||
})
|
||||
def _call_api_v2(self, path, video_id, content_type, cookies=None, st=None):
|
||||
return self._call_api_impl(f'{path}', video_id, query={
|
||||
'content_id': video_id,
|
||||
'filters': f'content_type={content_type}',
|
||||
'client_capabilities': json.dumps({
|
||||
'package': ['dash', 'hls'],
|
||||
'container': ['fmp4', 'fmp4br', 'ts'],
|
||||
'ads': ['non_ssai', 'ssai'],
|
||||
'audio_channel': ['stereo', 'dolby51', 'atmos'],
|
||||
'encryption': ['plain', 'widevine'], # wv only so we can raise appropriate error
|
||||
'video_codec': ['h264', 'h265'],
|
||||
'video_codec_non_secure': ['h264', 'h265', 'vp9'],
|
||||
'ladder': ['phone', 'tv', 'full'],
|
||||
'resolution': ['hd', '4k'],
|
||||
'true_resolution': ['hd', '4k'],
|
||||
'dynamic_range': ['sdr', 'hdr'],
|
||||
}, separators=(',', ':')),
|
||||
'drm_parameters': json.dumps({
|
||||
'widevine_security_level': ['SW_SECURE_DECODE', 'SW_SECURE_CRYPTO'],
|
||||
'hdcp_version': ['HDCP_V2_2', 'HDCP_V2_1', 'HDCP_V2', 'HDCP_V1'],
|
||||
}, separators=(',', ':')),
|
||||
}, cookies=cookies, st=st)
|
||||
|
||||
def _playlist_entries(self, path, item_id, root=None, **kwargs):
|
||||
results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
|
||||
for video in traverse_obj(results, (('assets', None), 'items', ...)):
|
||||
if video.get('contentId'):
|
||||
yield self.url_result(
|
||||
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
|
||||
@staticmethod
|
||||
def _parse_metadata_v1(video_data):
|
||||
return traverse_obj(video_data, {
|
||||
'id': ('contentId', {str}),
|
||||
'title': ('title', {str}),
|
||||
'description': ('description', {str}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'timestamp': (('broadcastDate', 'startDate'), {int_or_none}, any),
|
||||
'release_year': ('year', {int_or_none}),
|
||||
'channel': ('channelName', {str}),
|
||||
'channel_id': ('channelId', {int}, {str_or_none}),
|
||||
'series': ('showName', {str}),
|
||||
'season': ('seasonName', {str}),
|
||||
'season_number': ('seasonNo', {int_or_none}),
|
||||
'season_id': ('seasonId', {int}, {str_or_none}),
|
||||
'episode': ('title', {str}),
|
||||
'episode_number': ('episodeNo', {int_or_none}),
|
||||
})
|
||||
|
||||
def _fetch_page(self, path, item_id, name, query, root, page):
|
||||
results = self._call_api_v1(
|
||||
path, item_id, note=f'Downloading {name} page {page + 1} JSON', query={
|
||||
**query,
|
||||
'tao': page * self._PAGE_SIZE,
|
||||
'tas': self._PAGE_SIZE,
|
||||
})['body']['results']
|
||||
|
||||
for video in traverse_obj(results, (('assets', None), 'items', lambda _, v: v['contentId'])):
|
||||
yield self.url_result(
|
||||
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
|
||||
|
||||
|
||||
class HotStarIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar'
|
||||
IE_DESC = 'JioHotstar'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
|
||||
(?:
|
||||
@@ -114,15 +164,16 @@ class HotStarIE(HotStarBaseIE):
|
||||
'upload_date': '20190501',
|
||||
'duration': 1219,
|
||||
'channel': 'StarPlus',
|
||||
'channel_id': '3',
|
||||
'channel_id': '821',
|
||||
'series': 'Ek Bhram - Sarvagun Sampanna',
|
||||
'season': 'Chapter 1',
|
||||
'season_number': 1,
|
||||
'season_id': '6771',
|
||||
'season_id': '1260004607',
|
||||
'episode': 'Janhvi Targets Suman',
|
||||
'episode_number': 8,
|
||||
},
|
||||
}, {
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, { # Metadata call gets HTTP Error 504 with tas=10000
|
||||
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
|
||||
'info_dict': {
|
||||
'id': '1000282843',
|
||||
@@ -134,14 +185,14 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'StarPlus',
|
||||
'series': 'Anupama',
|
||||
'season_number': 1,
|
||||
'season_id': '7399',
|
||||
'season_id': '1260022018',
|
||||
'upload_date': '20230307',
|
||||
'episode': 'Anupama, Anuj Share a Moment',
|
||||
'episode_number': 853,
|
||||
'duration': 1272,
|
||||
'channel_id': '3',
|
||||
'duration': 1266,
|
||||
'channel_id': '821',
|
||||
},
|
||||
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
|
||||
'info_dict': {
|
||||
@@ -154,14 +205,15 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'Hotstar Specials',
|
||||
'series': 'Kana Kaanum Kaalangal',
|
||||
'season_number': 1,
|
||||
'season_id': '9441',
|
||||
'season_id': '1260097089',
|
||||
'upload_date': '20220421',
|
||||
'episode': 'Back To School',
|
||||
'episode_number': 1,
|
||||
'duration': 1810,
|
||||
'channel_id': '54',
|
||||
'channel_id': '1260003991',
|
||||
},
|
||||
}, {
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, { # Metadata call gets HTTP Error 504 with tas=10000
|
||||
'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
|
||||
'info_dict': {
|
||||
'id': '1000262286',
|
||||
@@ -173,6 +225,7 @@ class HotStarIE(HotStarBaseIE):
|
||||
'timestamp': 1622943900,
|
||||
'duration': 5395,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
|
||||
'info_dict': {
|
||||
@@ -180,12 +233,13 @@ class HotStarIE(HotStarBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Premam',
|
||||
'release_year': 2015,
|
||||
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
|
||||
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
|
||||
'timestamp': 1462149000,
|
||||
'upload_date': '20160502',
|
||||
'episode': 'Premam',
|
||||
'duration': 8994,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
|
||||
'only_matching': True,
|
||||
@@ -208,6 +262,13 @@ class HotStarIE(HotStarBaseIE):
|
||||
None: 'content',
|
||||
}
|
||||
|
||||
_CONTENT_TYPE = {
|
||||
'movie': 'MOVIE',
|
||||
'episode': 'EPISODE',
|
||||
'match': 'SPORT',
|
||||
'content': 'CLIPS',
|
||||
}
|
||||
|
||||
_IGNORE_MAP = {
|
||||
'res': 'resolution',
|
||||
'vcodec': 'video_codec',
|
||||
@@ -229,38 +290,50 @@ def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, video_type = self._match_valid_url(url).group('id', 'type')
|
||||
video_type = self._TYPE.get(video_type, video_type)
|
||||
video_type = self._TYPE[video_type]
|
||||
cookies = self._get_cookies(url) # Cookies before any request
|
||||
if not cookies or not cookies.get(self._TOKEN_NAME):
|
||||
self.raise_login_required()
|
||||
|
||||
video_data = traverse_obj(
|
||||
self._call_api_v1(
|
||||
f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
|
||||
('body', 'results', 'item', {dict})) or {}
|
||||
if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
|
||||
self._call_api_v1(f'{video_type}/detail', video_id, fatal=False, query={
|
||||
'tas': 5, # See https://github.com/yt-dlp/yt-dlp/issues/7946
|
||||
'contentId': video_id,
|
||||
}), ('body', 'results', 'item', {dict})) or {}
|
||||
|
||||
if video_data.get('drmProtected'):
|
||||
self.report_drm(video_id)
|
||||
|
||||
# See https://github.com/yt-dlp/yt-dlp/issues/396
|
||||
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
|
||||
|
||||
geo_restricted = False
|
||||
formats, subs = [], {}
|
||||
formats, subs, has_drm = [], {}, False
|
||||
headers = {'Referer': f'{self._BASE_URL}/in'}
|
||||
content_type = traverse_obj(video_data, ('contentType', {str})) or self._CONTENT_TYPE[video_type]
|
||||
|
||||
# change to v2 in the future
|
||||
playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
|
||||
for playback_set in playback_sets:
|
||||
if not isinstance(playback_set, dict):
|
||||
continue
|
||||
tags = str_or_none(playback_set.get('tagsCombination')) or ''
|
||||
# See https://github.com/yt-dlp/yt-dlp/issues/396
|
||||
st = self._request_webpage(
|
||||
f'{self._BASE_URL}/in', video_id, 'Fetching server time').get_header('x-origin-date')
|
||||
watch = self._call_api_v2('pages/watch', video_id, content_type, cookies, st)
|
||||
player_config = traverse_obj(watch, (
|
||||
'page', 'spaces', 'player', 'widget_wrappers', lambda _, v: v['template'] == 'PlayerWidget',
|
||||
'widget', 'data', 'player_config', {dict}, any, {require('player config')}))
|
||||
|
||||
for playback_set in traverse_obj(player_config, (
|
||||
('media_asset', 'media_asset_v2'),
|
||||
('primary', 'fallback'),
|
||||
all, lambda _, v: url_or_none(v['content_url']),
|
||||
)):
|
||||
tags = str_or_none(playback_set.get('playback_tags')) or ''
|
||||
if any(f'{prefix}:{ignore}' in tags
|
||||
for key, prefix in self._IGNORE_MAP.items()
|
||||
for ignore in self._configuration_arg(key)):
|
||||
continue
|
||||
|
||||
format_url = url_or_none(playback_set.get('playbackUrl'))
|
||||
if not format_url:
|
||||
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
|
||||
if tag_dict.get('encryption') not in ('plain', None):
|
||||
has_drm = True
|
||||
continue
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
|
||||
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
|
||||
ext = determine_ext(format_url)
|
||||
|
||||
current_formats, current_subs = [], {}
|
||||
@@ -280,14 +353,12 @@ def _real_extract(self, url):
|
||||
'height': int_or_none(playback_set.get('height')),
|
||||
}]
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
|
||||
geo_restricted = True
|
||||
else:
|
||||
self.write_debug(e)
|
||||
continue
|
||||
|
||||
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
|
||||
if tag_dict.get('encryption') not in ('plain', None):
|
||||
for f in current_formats:
|
||||
f['has_drm'] = True
|
||||
for f in current_formats:
|
||||
for k, v in self._TAG_FIELDS.items():
|
||||
if not f.get(k):
|
||||
@@ -299,6 +370,11 @@ def _real_extract(self, url):
|
||||
'stereo': 2,
|
||||
'dolby51': 6,
|
||||
}.get(tag_dict.get('audio_channel'))
|
||||
if (
|
||||
'Audio_Description' in f['format_id']
|
||||
or 'Audio Description' in (f.get('format_note') or '')
|
||||
):
|
||||
f['source_preference'] = -99 + (f.get('source_preference') or -1)
|
||||
f['format_note'] = join_nonempty(
|
||||
tag_dict.get('ladder'),
|
||||
tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
|
||||
@@ -308,29 +384,22 @@ def _real_extract(self, url):
|
||||
formats.extend(current_formats)
|
||||
subs = self._merge_subtitles(subs, current_subs)
|
||||
|
||||
if not formats and geo_restricted:
|
||||
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
|
||||
if not formats:
|
||||
if geo_restricted:
|
||||
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
|
||||
elif has_drm:
|
||||
self.report_drm(video_id)
|
||||
elif not self._has_active_subscription(cookies, st):
|
||||
self.raise_no_formats('Your account does not have access to this content', expected=True)
|
||||
self._remove_duplicate_formats(formats)
|
||||
for f in formats:
|
||||
f.setdefault('http_headers', {}).update(headers)
|
||||
|
||||
return {
|
||||
**self._parse_metadata_v1(video_data),
|
||||
'id': video_id,
|
||||
'title': video_data.get('title'),
|
||||
'description': video_data.get('description'),
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
|
||||
'release_year': int_or_none(video_data.get('year')),
|
||||
'formats': formats,
|
||||
'subtitles': subs,
|
||||
'channel': video_data.get('channelName'),
|
||||
'channel_id': str_or_none(video_data.get('channelId')),
|
||||
'series': video_data.get('showName'),
|
||||
'season': video_data.get('seasonName'),
|
||||
'season_number': int_or_none(video_data.get('seasonNo')),
|
||||
'season_id': str_or_none(video_data.get('seasonId')),
|
||||
'episode': video_data.get('title'),
|
||||
'episode_number': int_or_none(video_data.get('episodeNo')),
|
||||
}
|
||||
|
||||
|
||||
@@ -371,64 +440,6 @@ def _real_extract(self, url):
|
||||
return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
|
||||
|
||||
|
||||
class HotStarPlaylistIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar:playlist'
|
||||
_VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
|
||||
'info_dict': {
|
||||
'id': '3_2_26',
|
||||
},
|
||||
'playlist_mincount': 20,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
id_ = self._match_id(url)
|
||||
return self.playlist_result(
|
||||
self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
|
||||
|
||||
|
||||
class HotStarSeasonIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar:season'
|
||||
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
|
||||
'info_dict': {
|
||||
'id': '8028',
|
||||
},
|
||||
'playlist_mincount': 35,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
|
||||
'info_dict': {
|
||||
'id': '4357',
|
||||
},
|
||||
'playlist_mincount': 30,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
|
||||
'info_dict': {
|
||||
'id': '8208',
|
||||
},
|
||||
'playlist_mincount': 19,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, season_id = self._match_valid_url(url).groups()
|
||||
return self.playlist_result(self._playlist_entries(
|
||||
'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
|
||||
|
||||
|
||||
class HotStarSeriesIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar:series'
|
||||
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
|
||||
@@ -443,25 +454,29 @@ class HotStarSeriesIE(HotStarBaseIE):
|
||||
'info_dict': {
|
||||
'id': '1260050431',
|
||||
},
|
||||
'playlist_mincount': 43,
|
||||
'playlist_mincount': 42,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
|
||||
'info_dict': {
|
||||
'id': '435',
|
||||
},
|
||||
'playlist_mincount': 267,
|
||||
}, {
|
||||
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
|
||||
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
|
||||
'info_dict': {
|
||||
'id': '1260022017',
|
||||
},
|
||||
'playlist_mincount': 940,
|
||||
'playlist_mincount': 1601,
|
||||
}]
|
||||
_PAGE_SIZE = 100
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, series_id = self._match_valid_url(url).groups()
|
||||
id_ = self._call_api_v1(
|
||||
url, series_id = self._match_valid_url(url).group('url', 'id')
|
||||
eid = self._call_api_v1(
|
||||
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
|
||||
|
||||
return self.playlist_result(self._playlist_entries(
|
||||
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
|
||||
entries = OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, 'tray/g/1/items', series_id,
|
||||
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
|
||||
|
||||
return self.playlist_result(entries, series_id)
|
||||
|
||||
@@ -11,7 +11,6 @@
|
||||
class IndavideoEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
|
||||
# Some example URLs covered by generic extractor:
|
||||
# https://indavideo.hu/video/Vicces_cica_1
|
||||
# https://index.indavideo.hu/video/Hod_Nemetorszagban
|
||||
# https://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
|
||||
# https://film.indavideo.hu/video/f_farkaslesen
|
||||
@@ -25,14 +24,14 @@ class IndavideoEmbedIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Cicatánc',
|
||||
'description': '',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'cukiajanlo',
|
||||
'uploader_id': '83729',
|
||||
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
|
||||
'timestamp': 1439193826,
|
||||
'upload_date': '20150810',
|
||||
'duration': 72,
|
||||
'age_limit': 0,
|
||||
'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
|
||||
'tags': 'count:5',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
|
||||
@@ -45,14 +44,30 @@ class IndavideoEmbedIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Vicces cica',
|
||||
'description': 'Játszik a tablettel. :D',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
|
||||
'uploader': 'Jet_Pack',
|
||||
'uploader_id': '491217',
|
||||
'timestamp': 1390821212,
|
||||
'upload_date': '20140127',
|
||||
'duration': 7,
|
||||
'age_limit': 0,
|
||||
'tags': ['cica', 'Jet_Pack'],
|
||||
'tags': 'count:2',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://palyazat.indavideo.hu/video/RUSH_1',
|
||||
'info_dict': {
|
||||
'id': '3808180',
|
||||
'ext': 'mp4',
|
||||
'title': 'RUSH',
|
||||
'age_limit': 0,
|
||||
'description': '',
|
||||
'duration': 650,
|
||||
'tags': 'count:2',
|
||||
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
|
||||
'timestamp': 1729136266,
|
||||
'upload_date': '20241017',
|
||||
'uploader': '7summerfilms',
|
||||
'uploader_id': '1628496',
|
||||
},
|
||||
}]
|
||||
|
||||
|
||||
@@ -1,408 +0,0 @@
|
||||
import base64
|
||||
import itertools
|
||||
import json
|
||||
import random
|
||||
import re
|
||||
import string
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
jwt_decode_hs256,
|
||||
parse_age_limit,
|
||||
try_call,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class JioCinemaBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'jiocinema'
|
||||
_GEO_BYPASS = False
|
||||
_ACCESS_TOKEN = None
|
||||
_REFRESH_TOKEN = None
|
||||
_GUEST_TOKEN = None
|
||||
_USER_ID = None
|
||||
_DEVICE_ID = None
|
||||
_API_HEADERS = {'Origin': 'https://www.jiocinema.com', 'Referer': 'https://www.jiocinema.com/'}
|
||||
_APP_NAME = {'appName': 'RJIL_JioCinema'}
|
||||
_APP_VERSION = {'appVersion': '5.0.0'}
|
||||
_API_SIGNATURES = 'o668nxgzwff'
|
||||
_METADATA_API_BASE = 'https://content-jiovoot.voot.com/psapi'
|
||||
_ACCESS_HINT = 'the `accessToken` from your browser local storage'
|
||||
_LOGIN_HINT = (
|
||||
'Log in with "-u phone -p <PHONE_NUMBER>" to authenticate with OTP, '
|
||||
f'or use "-u token -p <ACCESS_TOKEN>" to log in with {_ACCESS_HINT}. '
|
||||
'If you have previously logged in with yt-dlp and your session '
|
||||
'has been cached, you can use "-u device -p <DEVICE_ID>"')
|
||||
|
||||
def _cache_token(self, token_type):
|
||||
assert token_type in ('access', 'refresh', 'all')
|
||||
if token_type in ('access', 'all'):
|
||||
self.cache.store(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-access', JioCinemaBaseIE._ACCESS_TOKEN)
|
||||
if token_type in ('refresh', 'all'):
|
||||
self.cache.store(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh', JioCinemaBaseIE._REFRESH_TOKEN)
|
||||
|
||||
def _call_api(self, url, video_id, note='Downloading API JSON', headers={}, data={}):
|
||||
return self._download_json(
|
||||
url, video_id, note, data=json.dumps(data, separators=(',', ':')).encode(), headers={
|
||||
'Content-Type': 'application/json',
|
||||
'Accept': 'application/json',
|
||||
**self._API_HEADERS,
|
||||
**headers,
|
||||
}, expected_status=(400, 403, 474))
|
||||
|
||||
def _call_auth_api(self, service, endpoint, note, headers={}, data={}):
|
||||
return self._call_api(
|
||||
f'https://auth-jiocinema.voot.com/{service}service/apis/v4/{endpoint}',
|
||||
None, note=note, headers=headers, data=data)
|
||||
|
||||
def _refresh_token(self):
|
||||
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._DEVICE_ID:
|
||||
raise ExtractorError('User token has expired', expected=True)
|
||||
response = self._call_auth_api(
|
||||
'token', 'refreshtoken', 'Refreshing token',
|
||||
headers={'accesstoken': self._ACCESS_TOKEN}, data={
|
||||
**self._APP_NAME,
|
||||
'deviceId': self._DEVICE_ID,
|
||||
'refreshToken': self._REFRESH_TOKEN,
|
||||
**self._APP_VERSION,
|
||||
})
|
||||
refresh_token = response.get('refreshTokenId')
|
||||
if refresh_token and refresh_token != JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
|
||||
self._cache_token('refresh')
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
|
||||
self._cache_token('access')
|
||||
|
||||
def _fetch_guest_token(self):
|
||||
JioCinemaBaseIE._DEVICE_ID = ''.join(random.choices(string.digits, k=10))
|
||||
guest_token = self._call_auth_api(
|
||||
'token', 'guest', 'Downloading guest token', data={
|
||||
**self._APP_NAME,
|
||||
'deviceType': 'phone',
|
||||
'os': 'ios',
|
||||
'deviceId': self._DEVICE_ID,
|
||||
'freshLaunch': False,
|
||||
'adId': self._DEVICE_ID,
|
||||
**self._APP_VERSION,
|
||||
})
|
||||
self._GUEST_TOKEN = guest_token['authToken']
|
||||
self._USER_ID = guest_token['userId']
|
||||
|
||||
def _call_login_api(self, endpoint, guest_token, data, note):
|
||||
return self._call_auth_api(
|
||||
'user', f'loginotp/{endpoint}', note, headers={
|
||||
**self.geo_verification_headers(),
|
||||
'accesstoken': self._GUEST_TOKEN,
|
||||
**self._APP_NAME,
|
||||
**traverse_obj(guest_token, 'data', {
|
||||
'deviceType': ('deviceType', {str}),
|
||||
'os': ('os', {str}),
|
||||
})}, data=data)
|
||||
|
||||
def _is_token_expired(self, token):
|
||||
return (try_call(lambda: jwt_decode_hs256(token)['exp']) or 0) <= int(time.time() - 180)
|
||||
|
||||
def _perform_login(self, username, password):
|
||||
if self._ACCESS_TOKEN and not self._is_token_expired(self._ACCESS_TOKEN):
|
||||
return
|
||||
|
||||
UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
|
||||
|
||||
if username.lower() == 'token':
|
||||
if try_call(lambda: jwt_decode_hs256(password)):
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = password
|
||||
refresh_hint = 'the `refreshToken` UUID from your browser local storage'
|
||||
refresh_token = self._configuration_arg('refresh_token', [''], ie_key=JioCinemaIE)[0]
|
||||
if not refresh_token:
|
||||
self.to_screen(
|
||||
'To extend the life of your login session, in addition to your access token, '
|
||||
'you can pass --extractor-args "jiocinema:refresh_token=REFRESH_TOKEN" '
|
||||
f'where REFRESH_TOKEN is {refresh_hint}')
|
||||
elif re.fullmatch(UUID_RE, refresh_token):
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
|
||||
else:
|
||||
self.report_warning(f'Invalid refresh_token value. Use {refresh_hint}')
|
||||
else:
|
||||
raise ExtractorError(
|
||||
f'The password given could not be decoded as a token; use {self._ACCESS_HINT}', expected=True)
|
||||
|
||||
elif username.lower() == 'device' and re.fullmatch(rf'(?:{UUID_RE}|\d+)', password):
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-refresh')
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-access')
|
||||
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._ACCESS_TOKEN:
|
||||
raise ExtractorError(f'Failed to load cached tokens for device ID "{password}"', expected=True)
|
||||
|
||||
elif username.lower() == 'phone' and re.fullmatch(r'\+?\d+', password):
|
||||
self._fetch_guest_token()
|
||||
guest_token = jwt_decode_hs256(self._GUEST_TOKEN)
|
||||
initial_data = {
|
||||
'number': base64.b64encode(password.encode()).decode(),
|
||||
**self._APP_VERSION,
|
||||
}
|
||||
response = self._call_login_api('send', guest_token, initial_data, 'Requesting OTP')
|
||||
if not traverse_obj(response, ('OTPInfo', {dict})):
|
||||
raise ExtractorError('There was a problem with the phone number login attempt')
|
||||
|
||||
is_iphone = guest_token.get('os') == 'ios'
|
||||
response = self._call_login_api('verify', guest_token, {
|
||||
'deviceInfo': {
|
||||
'consumptionDeviceName': 'iPhone' if is_iphone else 'Android',
|
||||
'info': {
|
||||
'platform': {'name': 'iPhone OS' if is_iphone else 'Android'},
|
||||
'androidId': self._DEVICE_ID,
|
||||
'type': 'iOS' if is_iphone else 'Android',
|
||||
},
|
||||
},
|
||||
**initial_data,
|
||||
'otp': self._get_tfa_info('the one-time password sent to your phone'),
|
||||
}, 'Submitting OTP')
|
||||
if traverse_obj(response, 'code') == 1043:
|
||||
raise ExtractorError('Wrong OTP', expected=True)
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = response['refreshToken']
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
|
||||
|
||||
else:
|
||||
raise ExtractorError(self._LOGIN_HINT, expected=True)
|
||||
|
||||
user_token = jwt_decode_hs256(JioCinemaBaseIE._ACCESS_TOKEN)['data']
|
||||
JioCinemaBaseIE._USER_ID = user_token['userId']
|
||||
JioCinemaBaseIE._DEVICE_ID = user_token['deviceId']
|
||||
if JioCinemaBaseIE._REFRESH_TOKEN and username != 'device':
|
||||
self._cache_token('all')
|
||||
if self.get_param('cachedir') is not False:
|
||||
self.to_screen(
|
||||
f'NOTE: For subsequent logins you can use "-u device -p {JioCinemaBaseIE._DEVICE_ID}"')
|
||||
elif not JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh')
|
||||
if JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
self._cache_token('access')
|
||||
self.to_screen(f'Logging in as device ID "{JioCinemaBaseIE._DEVICE_ID}"')
|
||||
if self._is_token_expired(JioCinemaBaseIE._ACCESS_TOKEN):
|
||||
self._refresh_token()
|
||||
|
||||
|
||||
class JioCinemaIE(JioCinemaBaseIE):
|
||||
IE_NAME = 'jiocinema'
|
||||
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/?(?:movies?/[^/?#]+/|tv-shows/(?:[^/?#]+/){3})(?P<id>\d{3,})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.jiocinema.com/tv-shows/agnisakshi-ek-samjhauta/1/pradeep-to-stop-the-wedding/3759931',
|
||||
'info_dict': {
|
||||
'id': '3759931',
|
||||
'ext': 'mp4',
|
||||
'title': 'Pradeep to stop the wedding?',
|
||||
'description': 'md5:75f72d1d1a66976633345a3de6d672b1',
|
||||
'episode': 'Pradeep to stop the wedding?',
|
||||
'episode_number': 89,
|
||||
'season': 'Agnisakshi…Ek Samjhauta-S1',
|
||||
'season_number': 1,
|
||||
'series': 'Agnisakshi Ek Samjhauta',
|
||||
'duration': 1238.0,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'age_limit': 13,
|
||||
'season_id': '3698031',
|
||||
'upload_date': '20230606',
|
||||
'timestamp': 1686009600,
|
||||
'release_date': '20230607',
|
||||
'genres': ['Drama'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.jiocinema.com/movies/bhediya/3754021/watch',
|
||||
'info_dict': {
|
||||
'id': '3754021',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bhediya',
|
||||
'description': 'md5:a6bf2900371ac2fc3f1447401a9f7bb0',
|
||||
'episode': 'Bhediya',
|
||||
'duration': 8500.0,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'age_limit': 13,
|
||||
'upload_date': '20230525',
|
||||
'timestamp': 1685026200,
|
||||
'release_date': '20230524',
|
||||
'genres': ['Comedy'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _extract_formats_and_subtitles(self, playback, video_id):
|
||||
m3u8_url = traverse_obj(playback, (
|
||||
'data', 'playbackUrls', lambda _, v: v['streamtype'] == 'hls', 'url', {url_or_none}, any))
|
||||
if not m3u8_url: # DRM-only content only serves dash urls
|
||||
self.report_drm(video_id)
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls')
|
||||
self._remove_duplicate_formats(formats)
|
||||
|
||||
return {
|
||||
# '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
|
||||
'formats': traverse_obj(formats, (
|
||||
lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
if not self._ACCESS_TOKEN and self._is_token_expired(self._GUEST_TOKEN):
|
||||
self._fetch_guest_token()
|
||||
elif self._ACCESS_TOKEN and self._is_token_expired(self._ACCESS_TOKEN):
|
||||
self._refresh_token()
|
||||
|
||||
playback = self._call_api(
|
||||
f'https://apis-jiovoot.voot.com/playbackjv/v3/{video_id}', video_id,
|
||||
'Downloading playback JSON', headers={
|
||||
**self.geo_verification_headers(),
|
||||
'accesstoken': self._ACCESS_TOKEN or self._GUEST_TOKEN,
|
||||
**self._APP_NAME,
|
||||
'deviceid': self._DEVICE_ID,
|
||||
'uniqueid': self._USER_ID,
|
||||
'x-apisignatures': self._API_SIGNATURES,
|
||||
'x-platform': 'androidweb',
|
||||
'x-platform-token': 'web',
|
||||
}, data={
|
||||
'4k': False,
|
||||
'ageGroup': '18+',
|
||||
'appVersion': '3.4.0',
|
||||
'bitrateProfile': 'xhdpi',
|
||||
'capability': {
|
||||
'drmCapability': {
|
||||
'aesSupport': 'yes',
|
||||
'fairPlayDrmSupport': 'none',
|
||||
'playreadyDrmSupport': 'none',
|
||||
'widevineDRMSupport': 'none',
|
||||
},
|
||||
'frameRateCapability': [{
|
||||
'frameRateSupport': '30fps',
|
||||
'videoQuality': '1440p',
|
||||
}],
|
||||
},
|
||||
'continueWatchingRequired': False,
|
||||
'dolby': False,
|
||||
'downloadRequest': False,
|
||||
'hevc': False,
|
||||
'kidsSafe': False,
|
||||
'manufacturer': 'Windows',
|
||||
'model': 'Windows',
|
||||
'multiAudioRequired': True,
|
||||
'osVersion': '10',
|
||||
'parentalPinValid': True,
|
||||
'x-apisignatures': self._API_SIGNATURES,
|
||||
})
|
||||
|
||||
status_code = traverse_obj(playback, ('code', {int}))
|
||||
if status_code == 474:
|
||||
self.raise_geo_restricted(countries=['IN'])
|
||||
elif status_code == 1008:
|
||||
error_msg = 'This content is only available for premium users'
|
||||
if self._ACCESS_TOKEN:
|
||||
raise ExtractorError(error_msg, expected=True)
|
||||
self.raise_login_required(f'{error_msg}. {self._LOGIN_HINT}', method=None)
|
||||
elif status_code == 400:
|
||||
raise ExtractorError('The requested content is not available', expected=True)
|
||||
elif status_code is not None and status_code != 200:
|
||||
raise ExtractorError(
|
||||
f'JioCinema says: {traverse_obj(playback, ("message", {str})) or status_code}')
|
||||
|
||||
metadata = self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/query/asset-details',
|
||||
video_id, fatal=False, query={
|
||||
'ids': f'include:{video_id}',
|
||||
'responseType': 'common',
|
||||
'devicePlatformType': 'desktop',
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'http_headers': self._API_HEADERS,
|
||||
**self._extract_formats_and_subtitles(playback, video_id),
|
||||
**traverse_obj(playback, ('data', {
|
||||
# fallback metadata
|
||||
'title': ('name', {str}),
|
||||
'description': ('fullSynopsis', {str}),
|
||||
'series': ('show', 'name', {str}, filter),
|
||||
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
|
||||
'season_number': ('episode', 'season', {int_or_none}, filter),
|
||||
'episode': ('fullTitle', {str}),
|
||||
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
|
||||
'age_limit': ('ageNemonic', {parse_age_limit}),
|
||||
'duration': ('totalDuration', {float_or_none}),
|
||||
'thumbnail': ('images', {url_or_none}),
|
||||
})),
|
||||
**traverse_obj(metadata, ('result', 0, {
|
||||
'title': ('fullTitle', {str}),
|
||||
'description': ('fullSynopsis', {str}),
|
||||
'series': ('showName', {str}, filter),
|
||||
'season': ('seasonName', {str}, filter),
|
||||
'season_number': ('season', {int_or_none}),
|
||||
'season_id': ('seasonId', {str}, filter),
|
||||
'episode': ('fullTitle', {str}),
|
||||
'episode_number': ('episode', {int_or_none}),
|
||||
'timestamp': ('uploadTime', {int_or_none}),
|
||||
'release_date': ('telecastDate', {str}),
|
||||
'age_limit': ('ageNemonic', {parse_age_limit}),
|
||||
'duration': ('duration', {float_or_none}),
|
||||
'genres': ('genres', ..., {str}),
|
||||
'thumbnail': ('seo', 'ogImage', {url_or_none}),
|
||||
})),
|
||||
}
|
||||
|
||||
|
||||
class JioCinemaSeriesIE(JioCinemaBaseIE):
|
||||
IE_NAME = 'jiocinema:series'
|
||||
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/tv-shows/(?P<slug>[\w-]+)/(?P<id>\d{3,})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.jiocinema.com/tv-shows/naagin/3499917',
|
||||
'info_dict': {
|
||||
'id': '3499917',
|
||||
'title': 'naagin',
|
||||
},
|
||||
'playlist_mincount': 120,
|
||||
}, {
|
||||
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
|
||||
'info_dict': {
|
||||
'id': '3499820',
|
||||
'title': 'mtv-splitsvilla-x5',
|
||||
},
|
||||
'playlist_mincount': 310,
|
||||
}]
|
||||
|
||||
def _entries(self, series_id):
|
||||
seasons = traverse_obj(self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
|
||||
'Downloading series metadata JSON', query={'responseType': 'common'}), (
|
||||
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
|
||||
'trayTabs', lambda _, v: v['id']))
|
||||
|
||||
for season_num, season in enumerate(seasons, start=1):
|
||||
season_id = season['id']
|
||||
label = season.get('label') or season_num
|
||||
for page_num in itertools.count(1):
|
||||
episodes = traverse_obj(self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',
|
||||
season_id, f'Downloading season {label} page {page_num} JSON', query={
|
||||
'sort': 'episode:asc',
|
||||
'id': season_id,
|
||||
'responseType': 'common',
|
||||
'page': page_num,
|
||||
}), ('result', lambda _, v: v['id'] and url_or_none(v['slug'])))
|
||||
if not episodes:
|
||||
break
|
||||
for episode in episodes:
|
||||
yield self.url_result(
|
||||
episode['slug'], JioCinemaIE, **traverse_obj(episode, {
|
||||
'video_id': 'id',
|
||||
'video_title': ('fullTitle', {str}),
|
||||
'season_number': ('season', {int_or_none}),
|
||||
'episode_number': ('episode', {int_or_none}),
|
||||
}))
|
||||
|
||||
def _real_extract(self, url):
|
||||
slug, series_id = self._match_valid_url(url).group('slug', 'id')
|
||||
return self.playlist_result(self._entries(series_id), series_id, slug)
|
||||
@@ -22,18 +22,17 @@ class JojIE(InfoExtractor):
|
||||
'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
|
||||
'ext': 'mp4',
|
||||
'title': 'NOVÉ BÝVANIE',
|
||||
'thumbnail': r're:^https?://.*?$',
|
||||
'duration': 3118,
|
||||
'thumbnail': r're:https?://img\.joj\.sk/.+',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://media.joj.sk/embed/CSM0Na0l0p1',
|
||||
'info_dict': {
|
||||
'id': 'CSM0Na0l0p1',
|
||||
'ext': 'mp4',
|
||||
'height': 576,
|
||||
'title': 'Extrémne rodiny 2 - POKRAČOVANIE (2012/04/09 21:30:00)',
|
||||
'duration': 3937,
|
||||
'thumbnail': r're:^https?://.*?$',
|
||||
'thumbnail': r're:https?://img\.joj\.sk/.+',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://media.joj.sk/embed/9i1cxv',
|
||||
@@ -45,6 +44,15 @@ class JojIE(InfoExtractor):
|
||||
'url': 'joj:9i1cxv',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
|
||||
'info_dict': {
|
||||
'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
|
||||
'title': 'Slovenskom sa prehnala vlna silných búrok',
|
||||
},
|
||||
'playlist_mincount': 5,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@@ -1,112 +0,0 @@
|
||||
import datetime as dt
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
datetime_from_str,
|
||||
unified_timestamp,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class JoqrAgIE(InfoExtractor):
|
||||
IE_DESC = '超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)'
|
||||
_VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/(?:player|inc-player-hls)\.php',
|
||||
r'https?://(?:www\.)?joqr\.co\.jp/ag/',
|
||||
r'https?://(?:www\.)?joqr\.co\.jp/qr/ag(?:daily|regular)program/?(?:$|[#?])']
|
||||
_TESTS = [{
|
||||
'url': 'https://www.uniqueradio.jp/agplayer5/player.php',
|
||||
'info_dict': {
|
||||
'id': 'live',
|
||||
'title': str,
|
||||
'channel': '超!A&G+',
|
||||
'description': str,
|
||||
'live_status': 'is_live',
|
||||
'release_timestamp': int,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
'ignore_no_formats_error': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.joqr.co.jp/ag/article/103760/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.joqr.co.jp/qr/agdailyprogram/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.joqr.co.jp/qr/agregularprogram/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_metadata(self, variable, html):
|
||||
return clean_html(urllib.parse.unquote_plus(self._search_regex(
|
||||
rf'var\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
|
||||
html, 'metadata', group='value', default=''))) or None
|
||||
|
||||
def _extract_start_timestamp(self, video_id, is_live):
|
||||
def extract_start_time_from(date_str):
|
||||
dt_ = datetime_from_str(date_str) + dt.timedelta(hours=9)
|
||||
date = dt_.strftime('%Y%m%d')
|
||||
start_time = self._search_regex(
|
||||
r'<h3[^>]+\bclass="dailyProgram-itemHeaderTime"[^>]*>[\s\d:]+–\s*(\d{1,2}:\d{1,2})',
|
||||
self._download_webpage(
|
||||
f'https://www.joqr.co.jp/qr/agdailyprogram/?date={date}', video_id,
|
||||
note=f'Downloading program list of {date}', fatal=False,
|
||||
errnote=f'Failed to download program list of {date}') or '',
|
||||
'start time', default=None)
|
||||
if start_time:
|
||||
return unified_timestamp(f'{dt_.strftime("%Y/%m/%d")} {start_time} +09:00')
|
||||
return None
|
||||
|
||||
start_timestamp = extract_start_time_from('today')
|
||||
if not start_timestamp:
|
||||
return None
|
||||
|
||||
if not is_live or start_timestamp < datetime_from_str('now').timestamp():
|
||||
return start_timestamp
|
||||
else:
|
||||
return extract_start_time_from('yesterday')
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = 'live'
|
||||
|
||||
metadata = self._download_webpage(
|
||||
'https://www.uniqueradio.jp/aandg', video_id,
|
||||
note='Downloading metadata', errnote='Failed to download metadata')
|
||||
title = self._extract_metadata('Program_name', metadata)
|
||||
|
||||
if not title or title == '放送休止':
|
||||
formats = []
|
||||
live_status = 'is_upcoming'
|
||||
release_timestamp = self._extract_start_timestamp(video_id, False)
|
||||
msg = 'This stream is not currently live'
|
||||
if release_timestamp:
|
||||
msg += (' and will start at '
|
||||
+ dt.datetime.fromtimestamp(release_timestamp).strftime('%Y-%m-%d %H:%M:%S'))
|
||||
self.raise_no_formats(msg, expected=True)
|
||||
else:
|
||||
m3u8_path = self._search_regex(
|
||||
r'<source\s[^>]*\bsrc="([^"]+)"',
|
||||
self._download_webpage(
|
||||
'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php', video_id,
|
||||
note='Downloading player data', errnote='Failed to download player data'),
|
||||
'm3u8 url')
|
||||
formats = self._extract_m3u8_formats(
|
||||
urljoin('https://www.uniqueradio.jp/', m3u8_path), video_id)
|
||||
live_status = 'is_live'
|
||||
release_timestamp = self._extract_start_timestamp(video_id, True)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'channel': '超!A&G+',
|
||||
'description': self._extract_metadata('Program_text', metadata),
|
||||
'formats': formats,
|
||||
'live_status': live_status,
|
||||
'release_timestamp': release_timestamp,
|
||||
}
|
||||
@@ -8,7 +8,6 @@ class JWPlatformIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
|
||||
_TESTS = [{
|
||||
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
|
||||
'md5': '3aa16e4f6860e6e78b7df5829519aed3',
|
||||
'info_dict': {
|
||||
'id': 'nPripu9l',
|
||||
'ext': 'mp4',
|
||||
@@ -17,13 +16,12 @@ class JWPlatformIE(InfoExtractor):
|
||||
'upload_date': '20081127',
|
||||
'timestamp': 1227796140,
|
||||
'duration': 32.0,
|
||||
'thumbnail': 'https://cdn.jwplayer.com/v2/media/nPripu9l/poster.jpg?width=720',
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_WEBPAGE_TESTS = [{
|
||||
# JWPlatform iframe
|
||||
'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
|
||||
@@ -33,10 +31,11 @@ class JWPlatformIE(InfoExtractor):
|
||||
'upload_date': '20160719',
|
||||
'timestamp': 1468923808,
|
||||
'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
|
||||
'thumbnail': 'https://cdn.jwplayer.com/v2/media/AG26UQXM/poster.jpg?width=720',
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
'description': '',
|
||||
'duration': 294.0,
|
||||
},
|
||||
'skip': 'Site no longer embeds JWPlatform',
|
||||
}, {
|
||||
# Player url not surrounded by quotes
|
||||
'url': 'https://www.deutsche-kinemathek.de/en/online/streaming/school-trip',
|
||||
@@ -45,12 +44,12 @@ class JWPlatformIE(InfoExtractor):
|
||||
'title': 'Klassenfahrt',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230109',
|
||||
'thumbnail': 'https://cdn.jwplayer.com/v2/media/jUxh5uin/poster.jpg?width=720',
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
'timestamp': 1673270298,
|
||||
'description': '',
|
||||
'duration': 5193.0,
|
||||
},
|
||||
'params': {'allowed_extractors': ['generic', 'jwplatform']},
|
||||
'skip': 'Site no longer embeds JWPlatform',
|
||||
}, {
|
||||
# iframe src attribute includes backslash before URL string
|
||||
'url': 'https://www.elespectador.com/colombia/video-asi-se-evito-la-fuga-de-john-poulos-presunto-feminicida-de-valentina-trespalacios-explicacion',
|
||||
@@ -59,11 +58,24 @@ class JWPlatformIE(InfoExtractor):
|
||||
'title': 'Así se evitó la fuga de John Poulos, presunto feminicida de Valentina Trespalacios',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230127',
|
||||
'thumbnail': 'https://cdn.jwplayer.com/v2/media/QD3gsexj/poster.jpg?width=720',
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
'timestamp': 1674862986,
|
||||
'description': 'md5:128fd74591c4e1fc2da598c5cb6f5ce4',
|
||||
'duration': 263.0,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.skimag.com/video/ski-people-1980',
|
||||
'info_dict': {
|
||||
'id': 'YTmgRiNU',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ski People (1980)',
|
||||
'channel': 'snow',
|
||||
'description': 'md5:cf9c3d101452c91e141f292b19fe4843',
|
||||
'duration': 5688.0,
|
||||
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
|
||||
'timestamp': 1610407738,
|
||||
'upload_date': '20210111',
|
||||
},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
|
||||
@@ -41,149 +41,188 @@ class KalturaIE(InfoExtractor):
|
||||
2: 'ttml',
|
||||
3: 'vtt',
|
||||
}
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'kaltura:269692:1_1jc2y3e4',
|
||||
'md5': '3adcbdb3dcc02d647539e53f284ba171',
|
||||
'info_dict': {
|
||||
'id': '1_1jc2y3e4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Straight from the Heart',
|
||||
'upload_date': '20131219',
|
||||
'uploader_id': 'mlundberg@wolfgangsvault.com',
|
||||
'description': 'The Allman Brothers Band, 12/16/1981',
|
||||
'thumbnail': 're:^https?://.*/thumbnail/.*',
|
||||
'timestamp': int,
|
||||
_TESTS = [{
|
||||
'url': 'kaltura:269692:1_1jc2y3e4',
|
||||
'md5': '3adcbdb3dcc02d647539e53f284ba171',
|
||||
'info_dict': {
|
||||
'id': '1_1jc2y3e4',
|
||||
'ext': 'mp4',
|
||||
'title': 'Straight from the Heart',
|
||||
'upload_date': '20131219',
|
||||
'uploader_id': 'mlundberg@wolfgangsvault.com',
|
||||
'description': 'The Allman Brothers Band, 12/16/1981',
|
||||
'thumbnail': r're:https?://.+/thumbnail/.+',
|
||||
'timestamp': int,
|
||||
},
|
||||
'skip': 'The access to this service is forbidden since the specified partner is blocked',
|
||||
}, {
|
||||
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# video with subtitles
|
||||
'url': 'kaltura:111032:1_cw786r8q',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# video with ttml subtitles (no fileExt)
|
||||
'url': 'kaltura:1926081:0_l5ye1133',
|
||||
'info_dict': {
|
||||
'id': '0_l5ye1133',
|
||||
'ext': 'mp4',
|
||||
'title': 'What Can You Do With Python?',
|
||||
'upload_date': '20160221',
|
||||
'uploader_id': 'stork',
|
||||
'thumbnail': r're:https?://.+/thumbnail/.+',
|
||||
'timestamp': int,
|
||||
'subtitles': {
|
||||
'en': [{
|
||||
'ext': 'ttml',
|
||||
}],
|
||||
},
|
||||
'skip': 'The access to this service is forbidden since the specified partner is blocked',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
|
||||
'only_matching': True,
|
||||
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# unavailable source format
|
||||
'url': 'kaltura:513551:1_66x4rg7o',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# html5lib URL using kwidget player
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
|
||||
'info_dict': {
|
||||
'id': '0_c076mna6',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
|
||||
'duration': 3608,
|
||||
'uploader_id': 'commons@swinburne.edu.au',
|
||||
'timestamp': 1408086874,
|
||||
'view_count': int,
|
||||
'upload_date': '20140815',
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
},
|
||||
{
|
||||
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# html5lib playlist URL using kwidget player
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
|
||||
'info_dict': {
|
||||
'id': '1_jovey5nu',
|
||||
'title': '00-00 Introduction',
|
||||
},
|
||||
{
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# video with subtitles
|
||||
'url': 'kaltura:111032:1_cw786r8q',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# video with ttml subtitles (no fileExt)
|
||||
'url': 'kaltura:1926081:0_l5ye1133',
|
||||
'info_dict': {
|
||||
'id': '0_l5ye1133',
|
||||
'ext': 'mp4',
|
||||
'title': 'What Can You Do With Python?',
|
||||
'upload_date': '20160221',
|
||||
'uploader_id': 'stork',
|
||||
'thumbnail': 're:^https?://.*/thumbnail/.*',
|
||||
'timestamp': int,
|
||||
'subtitles': {
|
||||
'en': [{
|
||||
'ext': 'ttml',
|
||||
}],
|
||||
'playlist': [
|
||||
{
|
||||
'info_dict': {
|
||||
'id': '1_b1y5hlvx',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Introduction',
|
||||
'duration': 91,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154447,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_jfb7mdpn',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Three parts to the course',
|
||||
'duration': 63,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154489,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_8xflxdp7',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Textbooks',
|
||||
'duration': 37,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154512,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_3hqew8kn',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Prerequisites',
|
||||
'duration': 49,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154536,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
},
|
||||
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
],
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.cornell.edu/VIDEO/nima-arkani-hamed-standard-models-of-particle-physics',
|
||||
'info_dict': {
|
||||
'id': '1_sgtvehim',
|
||||
'ext': 'mp4',
|
||||
'title': 'Our "Standard Models" of particle physics and cosmology',
|
||||
'duration': 5420,
|
||||
'thumbnail': r're:https?://cdnsecakmi\.kaltura\.com/.+',
|
||||
'timestamp': 1321158993,
|
||||
'upload_date': '20111113',
|
||||
'uploader_id': 'kps1',
|
||||
'view_count': int,
|
||||
},
|
||||
{
|
||||
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
|
||||
'info_dict': {
|
||||
'id': '0_utuok90b',
|
||||
'ext': 'mp4',
|
||||
'title': '06_matthew_brender_raj_dutt',
|
||||
'duration': 331,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'timestamp': 1466638791,
|
||||
'upload_date': '20160622',
|
||||
'uploader_id': '',
|
||||
'view_count': int,
|
||||
},
|
||||
{
|
||||
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
|
||||
'info_dict': {
|
||||
'id': '0_izeg5utt',
|
||||
'ext': 'mp4',
|
||||
'title': '35871',
|
||||
'duration': 3403,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'timestamp': 1355743100,
|
||||
'upload_date': '20121217',
|
||||
'uploader_id': 'cplapp@learn360.com',
|
||||
'view_count': int,
|
||||
},
|
||||
{
|
||||
# unavailable source format
|
||||
'url': 'kaltura:513551:1_66x4rg7o',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cns.nyu.edu/~eero/math-tools17/Videos/lecture-05sep2017.html',
|
||||
'info_dict': {
|
||||
'id': '1_9gzouybz',
|
||||
'ext': 'mp4',
|
||||
'title': 'lecture-05sep2017',
|
||||
'duration': 7219,
|
||||
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
|
||||
'timestamp': 1505340777,
|
||||
'upload_date': '20170913',
|
||||
'uploader_id': 'eps2',
|
||||
'view_count': int,
|
||||
},
|
||||
{
|
||||
# html5lib URL using kwidget player
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
|
||||
'info_dict': {
|
||||
'id': '0_c076mna6',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
|
||||
'duration': 3608,
|
||||
'uploader_id': 'commons@swinburne.edu.au',
|
||||
'timestamp': 1408086874,
|
||||
'view_count': int,
|
||||
'upload_date': '20140815',
|
||||
'thumbnail': 'http://cfvod.kaltura.com/p/691292/sp/69129200/thumbnail/entry_id/0_c076mna6/version/100022',
|
||||
},
|
||||
},
|
||||
{
|
||||
# html5lib playlist URL using kwidget player
|
||||
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
|
||||
'info_dict': {
|
||||
'id': '1_jovey5nu',
|
||||
'title': '00-00 Introduction',
|
||||
},
|
||||
'playlist': [
|
||||
{
|
||||
'info_dict': {
|
||||
'id': '1_b1y5hlvx',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Introduction',
|
||||
'duration': 91,
|
||||
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_b1y5hlvx/version/100001',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154447,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_jfb7mdpn',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Three parts to the course',
|
||||
'duration': 63,
|
||||
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_jfb7mdpn/version/100001',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154489,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_8xflxdp7',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Textbooks',
|
||||
'duration': 37,
|
||||
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_8xflxdp7/version/100001',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154512,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': '1_3hqew8kn',
|
||||
'ext': 'mp4',
|
||||
'title': 'CS7646_00-00 Introductio_Prerequisites',
|
||||
'duration': 49,
|
||||
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_3hqew8kn/version/100001',
|
||||
'view_count': int,
|
||||
'timestamp': 1533154536,
|
||||
'upload_date': '20180801',
|
||||
'uploader_id': 'djoyner3',
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
]
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
import functools
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import HEADRequest
|
||||
from ..utils import (
|
||||
UserNotLive,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
@@ -16,21 +16,17 @@
|
||||
|
||||
|
||||
class KickBaseIE(InfoExtractor):
|
||||
def _real_initialize(self):
|
||||
self._request_webpage(
|
||||
HEADRequest('https://kick.com/'), None, 'Setting up session', fatal=False, impersonate=True)
|
||||
xsrf_token = self._get_cookies('https://kick.com/').get('XSRF-TOKEN')
|
||||
if not xsrf_token:
|
||||
self.write_debug('kick.com did not set XSRF-TOKEN cookie')
|
||||
KickBaseIE._API_HEADERS = {
|
||||
'Authorization': f'Bearer {xsrf_token.value}',
|
||||
'X-XSRF-TOKEN': xsrf_token.value,
|
||||
} if xsrf_token else {}
|
||||
@functools.cached_property
|
||||
def _api_headers(self):
|
||||
token = traverse_obj(
|
||||
self._get_cookies('https://kick.com/'),
|
||||
('session_token', 'value', {urllib.parse.unquote}))
|
||||
return {'Authorization': f'Bearer {token}'} if token else {}
|
||||
|
||||
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
|
||||
return self._download_json(
|
||||
f'https://kick.com/api/{path}', display_id, note=note,
|
||||
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
|
||||
headers={**self._api_headers, **headers}, impersonate=True, **kwargs)
|
||||
|
||||
|
||||
class KickIE(KickBaseIE):
|
||||
|
||||
@@ -89,6 +89,15 @@ class KinjaEmbedIE(InfoExtractor):
|
||||
'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
|
||||
'info_dict': {
|
||||
'id': '106351',
|
||||
'ext': 'mp4',
|
||||
'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}]
|
||||
_JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform')
|
||||
_PROVIDER_MAP = {
|
||||
'fb': ('facebook.com/video.php?v=', 'Facebook'),
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
from .arkena import ArkenaIE
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
|
||||
class LcpPlayIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://play\.lcp\.fr/embed/(?P<id>[^/]+)/(?P<account_id>[^/]+)/[^/]+/[^/]+'
|
||||
_TESTS = [{
|
||||
'url': 'http://play.lcp.fr/embed/327336/131064/darkmatter/0',
|
||||
@@ -21,24 +21,9 @@ class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
|
||||
|
||||
|
||||
class LcpIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://(?:www\.)?lcp\.fr/(?:[^/]+/)*(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# arkena embed
|
||||
'url': 'http://www.lcp.fr/la-politique-en-video/schwartzenberg-prg-preconise-francois-hollande-de-participer-une-primaire',
|
||||
'md5': 'b8bd9298542929c06c1c15788b1f277a',
|
||||
'info_dict': {
|
||||
'id': 'd56d03e9',
|
||||
'ext': 'mp4',
|
||||
'title': 'Schwartzenberg (PRG) préconise à François Hollande de participer à une primaire à gauche',
|
||||
'description': 'md5:96ad55009548da9dea19f4120c6c16a8',
|
||||
'timestamp': 1456488895,
|
||||
'upload_date': '20160226',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# dailymotion live stream
|
||||
'url': 'http://www.lcp.fr/le-direct',
|
||||
'info_dict': {
|
||||
|
||||
@@ -18,12 +18,10 @@ class LibsynIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '6385796',
|
||||
'ext': 'mp3',
|
||||
'title': 'Champion Minded - Developing a Growth Mindset',
|
||||
# description fetched using another request:
|
||||
# http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
|
||||
# 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
|
||||
'title': 'The Allistair McCaw Podcast - Developing a Growth Mindset',
|
||||
'duration': 834.0,
|
||||
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
|
||||
'upload_date': '20180320',
|
||||
'thumbnail': 're:^https?://.*',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://html5-player.libsyn.com/embed/episode/id/3727166/height/75/width/200/theme/standard/direction/no/autoplay/no/autonext/no/thumbnail/no/preload/no/no_addthis/no/',
|
||||
@@ -32,8 +30,32 @@ class LibsynIE(InfoExtractor):
|
||||
'id': '3727166',
|
||||
'ext': 'mp3',
|
||||
'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
|
||||
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
|
||||
'upload_date': '20150818',
|
||||
'thumbnail': 're:^https?://.*',
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://html5-player.libsyn.com/',
|
||||
'md5': '50cff329596b8f674d4449ed077ef2f9',
|
||||
'info_dict': {
|
||||
'id': '2378831',
|
||||
'ext': 'mp3',
|
||||
'title': 'md5:54108b15f98e1b4056612c10b50106b2',
|
||||
'duration': 3561.0,
|
||||
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
|
||||
'upload_date': '20130630',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
|
||||
'md5': '23576952577f9604520a730d90371761',
|
||||
'info_dict': {
|
||||
'id': '3793998',
|
||||
'ext': 'mp3',
|
||||
'title': 'Underground Wellness Radio - Jack Tips: 5 Steps to Permanent Gut Healing',
|
||||
'duration': 3989.0,
|
||||
'thumbnail': r're:https?://assets\.libsyn\.com/.+',
|
||||
'upload_date': '20141126',
|
||||
},
|
||||
}]
|
||||
|
||||
|
||||
@@ -1,358 +0,0 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
try_get,
|
||||
unsmuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class LimelightBaseIE(InfoExtractor):
|
||||
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
lm = {
|
||||
'Media': 'media',
|
||||
'Channel': 'channel',
|
||||
'ChannelList': 'channel_list',
|
||||
}
|
||||
|
||||
def smuggle(url):
|
||||
return smuggle_url(url, {'source_url': url})
|
||||
|
||||
entries = []
|
||||
for kind, video_id in re.findall(
|
||||
r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})',
|
||||
webpage):
|
||||
entries.append(cls.url_result(
|
||||
smuggle(f'limelight:{lm[kind]}:{video_id}'),
|
||||
f'Limelight{kind}', video_id))
|
||||
for mobj in re.finditer(
|
||||
# As per [1] class attribute should be exactly equal to
|
||||
# LimelightEmbeddedPlayerFlash but numerous examples seen
|
||||
# that don't exactly match it (e.g. [2]).
|
||||
# 1. http://support.3playmedia.com/hc/en-us/articles/227732408-Limelight-Embedding-the-Captions-Plugin-with-the-Limelight-Player-on-Your-Webpage
|
||||
# 2. http://www.sedona.com/FacilitatorTraining2017
|
||||
r'''(?sx)
|
||||
<object[^>]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*?
|
||||
<param[^>]+
|
||||
name=(["\'])flashVars\2[^>]+
|
||||
value=(["\'])(?:(?!\3).)*(?P<kind>media|channel(?:List)?)Id=(?P<id>[a-z0-9]{32})
|
||||
''', webpage):
|
||||
kind, video_id = mobj.group('kind'), mobj.group('id')
|
||||
entries.append(cls.url_result(
|
||||
smuggle(f'limelight:{kind}:{video_id}'),
|
||||
f'Limelight{kind.capitalize()}', video_id))
|
||||
# http://support.3playmedia.com/hc/en-us/articles/115009517327-Limelight-Embedding-the-Audio-Description-Plugin-with-the-Limelight-Player-on-Your-Web-Page)
|
||||
for video_id in re.findall(
|
||||
r'(?s)LimelightPlayerUtil\.embed\s*\(\s*{.*?\bmediaId["\']\s*:\s*["\'](?P<id>[a-z0-9]{32})',
|
||||
webpage):
|
||||
entries.append(cls.url_result(
|
||||
smuggle(f'limelight:media:{video_id}'),
|
||||
LimelightMediaIE.ie_key(), video_id))
|
||||
return entries
|
||||
|
||||
def _call_playlist_service(self, item_id, method, fatal=True, referer=None):
|
||||
headers = {}
|
||||
if referer:
|
||||
headers['Referer'] = referer
|
||||
try:
|
||||
return self._download_json(
|
||||
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
|
||||
item_id, f'Downloading PlaylistService {method} JSON',
|
||||
fatal=fatal, headers=headers)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
|
||||
error = self._parse_json(e.cause.response.read().decode(), item_id)['detail']['contentAccessPermission']
|
||||
if error == 'CountryDisabled':
|
||||
self.raise_geo_restricted()
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise
|
||||
|
||||
def _extract(self, item_id, pc_method, mobile_method, referer=None):
|
||||
pc = self._call_playlist_service(item_id, pc_method, referer=referer)
|
||||
mobile = self._call_playlist_service(
|
||||
item_id, mobile_method, fatal=False, referer=referer)
|
||||
return pc, mobile
|
||||
|
||||
def _extract_info(self, pc, mobile, i, referer):
|
||||
get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
|
||||
pc_item = get_item(pc, 'playlistItems')
|
||||
mobile_item = get_item(mobile, 'mediaList')
|
||||
video_id = pc_item.get('mediaId') or mobile_item['mediaId']
|
||||
title = pc_item.get('title') or mobile_item['title']
|
||||
|
||||
formats = []
|
||||
urls = []
|
||||
for stream in pc_item.get('streams', []):
|
||||
stream_url = stream.get('url')
|
||||
if not stream_url or stream_url in urls:
|
||||
continue
|
||||
if not self.get_param('allow_unplayable_formats') and stream.get('drmProtected'):
|
||||
continue
|
||||
urls.append(stream_url)
|
||||
ext = determine_ext(stream_url)
|
||||
if ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
stream_url, video_id, f4m_id='hds', fatal=False))
|
||||
else:
|
||||
fmt = {
|
||||
'url': stream_url,
|
||||
'abr': float_or_none(stream.get('audioBitRate')),
|
||||
'fps': float_or_none(stream.get('videoFrameRate')),
|
||||
'ext': ext,
|
||||
}
|
||||
width = int_or_none(stream.get('videoWidthInPixels'))
|
||||
height = int_or_none(stream.get('videoHeightInPixels'))
|
||||
vbr = float_or_none(stream.get('videoBitRate'))
|
||||
if width or height or vbr:
|
||||
fmt.update({
|
||||
'width': width,
|
||||
'height': height,
|
||||
'vbr': vbr,
|
||||
})
|
||||
else:
|
||||
fmt['vcodec'] = 'none'
|
||||
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', stream_url)
|
||||
if rtmp:
|
||||
format_id = 'rtmp'
|
||||
if stream.get('videoBitRate'):
|
||||
format_id += '-%d' % int_or_none(stream['videoBitRate'])
|
||||
http_format_id = format_id.replace('rtmp', 'http')
|
||||
|
||||
CDN_HOSTS = (
|
||||
('delvenetworks.com', 'cpl.delvenetworks.com'),
|
||||
('video.llnw.net', 's2.content.video.llnw.net'),
|
||||
)
|
||||
for cdn_host, http_host in CDN_HOSTS:
|
||||
if cdn_host not in rtmp.group('host').lower():
|
||||
continue
|
||||
http_url = 'http://{}/{}'.format(http_host, rtmp.group('playpath')[4:])
|
||||
urls.append(http_url)
|
||||
if self._is_valid_url(http_url, video_id, http_format_id):
|
||||
http_fmt = fmt.copy()
|
||||
http_fmt.update({
|
||||
'url': http_url,
|
||||
'format_id': http_format_id,
|
||||
})
|
||||
formats.append(http_fmt)
|
||||
break
|
||||
|
||||
fmt.update({
|
||||
'url': rtmp.group('url'),
|
||||
'play_path': rtmp.group('playpath'),
|
||||
'app': rtmp.group('app'),
|
||||
'ext': 'flv',
|
||||
'format_id': format_id,
|
||||
})
|
||||
formats.append(fmt)
|
||||
|
||||
for mobile_url in mobile_item.get('mobileUrls', []):
|
||||
media_url = mobile_url.get('mobileUrl')
|
||||
format_id = mobile_url.get('targetMediaPlatform')
|
||||
if not media_url or media_url in urls:
|
||||
continue
|
||||
if (format_id in ('Widevine', 'SmoothStreaming')
|
||||
and not self.get_param('allow_unplayable_formats', False)):
|
||||
continue
|
||||
urls.append(media_url)
|
||||
ext = determine_ext(media_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
media_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
stream_url, video_id, f4m_id=format_id, fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': media_url,
|
||||
'format_id': format_id,
|
||||
'quality': -10,
|
||||
'ext': ext,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
for flag in mobile_item.get('flags'):
|
||||
if flag == 'ClosedCaptions':
|
||||
closed_captions = self._call_playlist_service(
|
||||
video_id, 'getClosedCaptionsDetailsByMediaId',
|
||||
False, referer) or []
|
||||
for cc in closed_captions:
|
||||
cc_url = cc.get('webvttFileUrl')
|
||||
if not cc_url:
|
||||
continue
|
||||
lang = cc.get('languageCode') or self._search_regex(r'/([a-z]{2})\.vtt', cc_url, 'lang', default='en')
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': cc_url,
|
||||
})
|
||||
break
|
||||
|
||||
get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': get_meta('description'),
|
||||
'formats': formats,
|
||||
'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
|
||||
'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class LimelightMediaIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:media:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bmediaId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
|
||||
'info_dict': {
|
||||
'id': '3ffd040b522b4485b6d84effc750cd86',
|
||||
'ext': 'mp4',
|
||||
'title': 'HaP and the HB Prince Trailer',
|
||||
'description': 'md5:8005b944181778e313d95c1237ddb640',
|
||||
'thumbnail': r're:^https?://.*\.jpeg$',
|
||||
'duration': 144.23,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# video with subtitles
|
||||
'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',
|
||||
'md5': '2fa3bad9ac321e23860ca23bc2c69e3d',
|
||||
'info_dict': {
|
||||
'id': 'a3e00274d4564ec4a9b29b9466432335',
|
||||
'ext': 'mp4',
|
||||
'title': '3Play Media Overview Video',
|
||||
'thumbnail': r're:^https?://.*\.jpeg$',
|
||||
'duration': 78.101,
|
||||
# TODO: extract all languages that were accessible via API
|
||||
# 'subtitles': 'mincount:9',
|
||||
'subtitles': 'mincount:1',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'media'
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
video_id = self._match_id(url)
|
||||
source_url = smuggled_data.get('source_url')
|
||||
self._initialize_geo_bypass({
|
||||
'countries': smuggled_data.get('geo_countries'),
|
||||
})
|
||||
|
||||
pc, mobile = self._extract(
|
||||
video_id, 'getPlaylistByMediaId',
|
||||
'getMobilePlaylistByMediaId', source_url)
|
||||
|
||||
return self._extract_info(pc, mobile, 0, source_url)
|
||||
|
||||
|
||||
class LimelightChannelIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight:channel'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:channel:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bchannelId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082',
|
||||
'info_dict': {
|
||||
'id': 'ab6a524c379342f9b23642917020c082',
|
||||
'title': 'Javascript Sample Code',
|
||||
'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
|
||||
},
|
||||
'playlist_mincount': 3,
|
||||
}, {
|
||||
'url': 'http://assets.delvenetworks.com/player/loader.swf?channelId=ab6a524c379342f9b23642917020c082',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'channel'
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
channel_id = self._match_id(url)
|
||||
source_url = smuggled_data.get('source_url')
|
||||
|
||||
pc, mobile = self._extract(
|
||||
channel_id, 'getPlaylistByChannelId',
|
||||
'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
|
||||
source_url)
|
||||
|
||||
entries = [
|
||||
self._extract_info(pc, mobile, i, source_url)
|
||||
for i in range(len(pc['playlistItems']))]
|
||||
|
||||
return self.playlist_result(
|
||||
entries, channel_id, pc.get('title'), mobile.get('description'))
|
||||
|
||||
|
||||
class LimelightChannelListIE(LimelightBaseIE):
|
||||
IE_NAME = 'limelight:channel_list'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
limelight:channel_list:|
|
||||
https?://
|
||||
(?:
|
||||
link\.videoplatform\.limelight\.com/media/|
|
||||
assets\.delvenetworks\.com/player/loader\.swf
|
||||
)
|
||||
\?.*?\bchannelListId=
|
||||
)
|
||||
(?P<id>[a-z0-9]{32})
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b',
|
||||
'info_dict': {
|
||||
'id': '301b117890c4465c8179ede21fd92e2b',
|
||||
'title': 'Website - Hero Player',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}, {
|
||||
'url': 'https://assets.delvenetworks.com/player/loader.swf?channelListId=301b117890c4465c8179ede21fd92e2b',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_PLAYLIST_SERVICE_PATH = 'channel_list'
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel_list_id = self._match_id(url)
|
||||
|
||||
channel_list = self._call_playlist_service(
|
||||
channel_list_id, 'getMobileChannelListById')
|
||||
|
||||
entries = [
|
||||
self.url_result('limelight:channel:{}'.format(channel['id']), 'LimelightChannel')
|
||||
for channel in channel_list['channelList']]
|
||||
|
||||
return self.playlist_result(
|
||||
entries, channel_list_id, channel_list['title'])
|
||||
@@ -3,6 +3,7 @@
|
||||
|
||||
|
||||
class LiveJournalIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
|
||||
|
||||
@@ -134,7 +134,7 @@ class LRTRadioIE(LRTBaseIE):
|
||||
def _real_extract(self, url):
|
||||
video_id, path = self._match_valid_url(url).group('id', 'path')
|
||||
media = self._download_json(
|
||||
'https://www.lrt.lt/radioteka/api/media', video_id,
|
||||
'https://www.lrt.lt/rest-api/media', video_id,
|
||||
query={'url': f'/mediateka/irasas/{video_id}/{path}'})
|
||||
|
||||
return {
|
||||
|
||||
@@ -16,91 +16,103 @@ class MainStreamingIE(InfoExtractor):
|
||||
_EMBED_REGEX = [rf'<iframe[^>]+?src=["\']?(?P<url>{_VALID_URL})["\']?']
|
||||
IE_DESC = 'MainStreaming Player'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
# Live stream offline, has alternative content id
|
||||
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/53EN6GxbWaJC',
|
||||
'info_dict': {
|
||||
'id': '53EN6GxbWaJC',
|
||||
'title': 'Diretta homepage 2021-12-31 12:00',
|
||||
'description': '',
|
||||
'live_status': 'was_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
|
||||
},
|
||||
'expected_warnings': [
|
||||
'Ignoring alternative content ID: WDAF1KOWUpH3',
|
||||
'MainStreaming said: Live event is OFFLINE',
|
||||
],
|
||||
'skip': 'live stream offline',
|
||||
}, {
|
||||
# playlist
|
||||
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/WDAF1KOWUpH3',
|
||||
'info_dict': {
|
||||
'id': 'WDAF1KOWUpH3',
|
||||
'title': 'Playlist homepage',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}, {
|
||||
# livestream
|
||||
'url': 'https://webtools-859c1818ed614cc5b0047439470927b0.msvdn.net/embed/tDoFkZD3T1Lw',
|
||||
'info_dict': {
|
||||
'id': 'tDoFkZD3T1Lw',
|
||||
'title': r're:Class CNBC Live \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
||||
'live_status': 'is_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
|
||||
},
|
||||
'skip': 'live stream',
|
||||
}, {
|
||||
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/EUlZfGWkGpOd?autoPlay=false',
|
||||
'info_dict': {
|
||||
'id': 'EUlZfGWkGpOd',
|
||||
'title': 'La Settimana ',
|
||||
'description': '03 Ottobre ore 02:00',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'not_live',
|
||||
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
|
||||
'duration': 1512,
|
||||
},
|
||||
}, {
|
||||
# video without webtools- prefix
|
||||
'url': 'https://f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/MfuWmzL2lGkA?autoplay=false&T=1635860445',
|
||||
'info_dict': {
|
||||
'id': 'MfuWmzL2lGkA',
|
||||
'title': 'TG Mattina',
|
||||
'description': '06 Ottobre ore 08:00',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'not_live',
|
||||
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
|
||||
'duration': 789.04,
|
||||
},
|
||||
}, {
|
||||
# always-on livestream with DVR
|
||||
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/HVvPMzy',
|
||||
'info_dict': {
|
||||
'id': 'HVvPMzy',
|
||||
'title': r're:^Diretta LaC News24 \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
||||
'description': 'canale all news',
|
||||
'live_status': 'is_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# no host
|
||||
'url': 'https://webtools.msvdn.net/embed/MfuWmzL2lGkA',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/amp_embed/tDoFkZD3T1Lw',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/content/tDoFkZD3T1Lw#',
|
||||
'only_matching': True,
|
||||
_TESTS = [{
|
||||
# Live stream offline, has alternative content id
|
||||
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/53EN6GxbWaJC',
|
||||
'info_dict': {
|
||||
'id': '53EN6GxbWaJC',
|
||||
'title': 'Diretta homepage 2021-12-31 12:00',
|
||||
'description': '',
|
||||
'live_status': 'was_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
|
||||
},
|
||||
]
|
||||
'expected_warnings': [
|
||||
'Ignoring alternative content ID: WDAF1KOWUpH3',
|
||||
'MainStreaming said: Live event is OFFLINE',
|
||||
],
|
||||
'skip': 'live stream offline',
|
||||
}, {
|
||||
# playlist
|
||||
'url': 'https://webtools-e18da6642b684f8aa9ae449862783a56.msvdn.net/embed/WDAF1KOWUpH3',
|
||||
'info_dict': {
|
||||
'id': 'WDAF1KOWUpH3',
|
||||
'title': 'Playlist homepage',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}, {
|
||||
# livestream
|
||||
'url': 'https://webtools-859c1818ed614cc5b0047439470927b0.msvdn.net/embed/tDoFkZD3T1Lw',
|
||||
'info_dict': {
|
||||
'id': 'tDoFkZD3T1Lw',
|
||||
'title': str,
|
||||
'live_status': 'is_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
|
||||
},
|
||||
'skip': 'live stream',
|
||||
}, {
|
||||
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/EUlZfGWkGpOd?autoPlay=false',
|
||||
'info_dict': {
|
||||
'id': 'EUlZfGWkGpOd',
|
||||
'title': 'La Settimana ',
|
||||
'description': '03 Ottobre ore 02:00',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'not_live',
|
||||
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
|
||||
'duration': 1512,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# video without webtools- prefix
|
||||
'url': 'https://f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/MfuWmzL2lGkA?autoplay=false&T=1635860445',
|
||||
'info_dict': {
|
||||
'id': 'MfuWmzL2lGkA',
|
||||
'title': 'TG Mattina',
|
||||
'description': '06 Ottobre ore 08:00',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'not_live',
|
||||
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
|
||||
'duration': 789.04,
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# always-on livestream with DVR
|
||||
'url': 'https://webtools-f5842579ff984c1c98d63b8d789673eb.msvdn.net/embed/HVvPMzy',
|
||||
'info_dict': {
|
||||
'id': 'HVvPMzy',
|
||||
'title': str,
|
||||
'description': 'canale all news',
|
||||
'live_status': 'is_live',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https?://[\w-]+\.msvdn\.net/image/\w+/poster',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
# no host
|
||||
'url': 'https://webtools.msvdn.net/embed/MfuWmzL2lGkA',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/amp_embed/tDoFkZD3T1Lw',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://859c1818ed614cc5b0047439470927b0.msvdn.net/content/tDoFkZD3T1Lw#',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Embed detection
|
||||
'url': 'https://www.lacplay.it/video/in-evidenza_728/lac-storie-p-250-i-santi-pietro-e-paolo_77297/',
|
||||
'info_dict': {
|
||||
'id': 'u7kiX5DUaHYr',
|
||||
'ext': 'mp4',
|
||||
'title': 'I Santi Pietro e Paolo',
|
||||
'description': 'md5:ff6be24916ba6b9ae990bf5f3df4911e',
|
||||
'duration': 1700.0,
|
||||
'thumbnail': r're:https?://.+',
|
||||
'tags': '06/07/2025',
|
||||
'live_status': 'not_live',
|
||||
},
|
||||
}]
|
||||
|
||||
def _playlist_entries(self, host, playlist_content):
|
||||
for entry in playlist_content:
|
||||
|
||||
@@ -11,121 +11,65 @@
|
||||
|
||||
class MediaKlikkIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?
|
||||
(?:mediaklikk|m4sport|hirado|petofilive)\.hu/.*?(?:videok?|cikk)/
|
||||
(?:mediaklikk|m4sport|hirado)\.hu/.*?(?:videok?|cikk)/
|
||||
(?:(?P<year>[0-9]{4})/(?P<month>[0-9]{1,2})/(?P<day>[0-9]{1,2})/)?
|
||||
(?P<id>[^/#?_]+)'''
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://mediaklikk.hu/filmajanlo/cikk/az-ajto/',
|
||||
# mediaklikk
|
||||
'url': 'https://mediaklikk.hu/ajanlo/video/2025/08/04/heviz-dzsungel-a-viz-alatt-ajanlo-08-10/',
|
||||
'info_dict': {
|
||||
'id': '668177',
|
||||
'title': 'Az ajtó',
|
||||
'display_id': 'az-ajto',
|
||||
'id': '8573769',
|
||||
'title': 'Hévíz - dzsungel a víz alatt – Ajánló (08.10.)',
|
||||
'display_id': 'heviz-dzsungel-a-viz-alatt-ajanlo-08-10',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2016/01/vlcsnap-2023-07-31-14h18m52s111.jpg',
|
||||
'upload_date': '20250804',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-04-13h48m24s336.jpg',
|
||||
},
|
||||
}, {
|
||||
# (old) mediaklikk. date in html.
|
||||
'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/',
|
||||
# mediaklikk - date in html
|
||||
'url': 'https://mediaklikk.hu/video/hazajaro-bilo-hegyseg-verocei-barangolas-a-drava-menten/',
|
||||
'info_dict': {
|
||||
'id': '4754129',
|
||||
'title': 'Hazajáró, DÉLNYUGAT-BÁCSKA – A Duna mentén Palánkától Doroszlóig',
|
||||
'id': '8482167',
|
||||
'title': 'Hazajáró, Bilo-hegység - Verőcei barangolás a Dráva mentén',
|
||||
'display_id': 'hazajaro-bilo-hegyseg-verocei-barangolas-a-drava-menten',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20210901',
|
||||
'thumbnail': 'http://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
|
||||
'upload_date': '20250703',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/07/2024-000307-M0010-01_3700_cover_01.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to 404 page',
|
||||
}, {
|
||||
# mediaklikk. date in html.
|
||||
'url': 'https://mediaklikk.hu/video/hazajaro-fabova-hegyseg-kishont-koronaja/',
|
||||
'info_dict': {
|
||||
'id': '6696133',
|
||||
'title': 'Hazajáró, Fabova-hegység - Kishont koronája',
|
||||
'display_id': 'hazajaro-fabova-hegyseg-kishont-koronaja',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230903',
|
||||
'thumbnail': 'https://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to 404 page',
|
||||
}, {
|
||||
# (old) m4sport
|
||||
'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/',
|
||||
'info_dict': {
|
||||
'id': '4754999',
|
||||
'title': 'Gyémánt Liga, Párizs',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20210830',
|
||||
'thumbnail': 'http://m4sport.hu/wp-content/uploads/sites/4/2021/08/vlcsnap-2021-08-30-18h21m20s10-1024x576.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to 404 page',
|
||||
}, {
|
||||
# m4sport
|
||||
'url': 'https://m4sport.hu/sportkozvetitesek/video/2023/09/08/atletika-gyemant-liga-brusszel/',
|
||||
'url': 'https://m4sport.hu/video/2025/08/07/holnap-kezdodik-a-12-vilagjatekok/',
|
||||
'info_dict': {
|
||||
'id': '6711136',
|
||||
'title': 'Atlétika – Gyémánt Liga, Brüsszel',
|
||||
'display_id': 'atletika-gyemant-liga-brusszel',
|
||||
'id': '8581887',
|
||||
'title': 'Holnap kezdődik a 12. Világjátékok',
|
||||
'display_id': 'holnap-kezdodik-a-12-vilagjatekok',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230908',
|
||||
'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-08-22h43m18s691.jpg',
|
||||
'upload_date': '20250807',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-06-20h30m48s817.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to 404 page',
|
||||
}, {
|
||||
# m4sport with *video/ url and no date
|
||||
'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/',
|
||||
'info_dict': {
|
||||
'id': '4492099',
|
||||
'title': 'Real Madrid - Chelsea 1-1',
|
||||
'display_id': 'real-madrid-chelsea-1-1',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png',
|
||||
},
|
||||
'skip': 'Webpage redirects to 404 page',
|
||||
}, {
|
||||
# (old) hirado
|
||||
'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/',
|
||||
'info_dict': {
|
||||
'id': '4760120',
|
||||
'title': 'Feltételeket szabott a főváros',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 'http://hirado.hu/wp-content/uploads/sites/4/2021/09/vlcsnap-2021-09-01-20h20m37s165.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to video list page',
|
||||
}, {
|
||||
# hirado
|
||||
'url': 'https://hirado.hu/belfold/video/2023/09/11/marad-az-eves-elszamolas-a-napelemekre-beruhazo-csaladoknal',
|
||||
'url': 'https://hirado.hu/video/2025/08/09/idojaras-jelentes-2025-augusztus-9-2230',
|
||||
'info_dict': {
|
||||
'id': '6716068',
|
||||
'title': 'Marad az éves elszámolás a napelemekre beruházó családoknál',
|
||||
'display_id': 'marad-az-eves-elszamolas-a-napelemekre-beruhazo-csaladoknal',
|
||||
'id': '8592033',
|
||||
'title': 'Időjárás-jelentés, 2025. augusztus 9. 22:30',
|
||||
'display_id': 'idojaras-jelentes-2025-augusztus-9-2230',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230911',
|
||||
'thumbnail': 'https://hirado.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-11-09h16m09s882.jpg',
|
||||
'upload_date': '20250809',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/Idojaras-jelentes-35-1.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to video list page',
|
||||
}, {
|
||||
# (old) petofilive
|
||||
'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/',
|
||||
# hirado - subcategory
|
||||
'url': 'https://hirado.hu/belfold/video/2025/08/09/nyitott-porta-napok-2025/',
|
||||
'info_dict': {
|
||||
'id': '4571948',
|
||||
'title': 'Tha Shudras az Akusztikban',
|
||||
'id': '8590581',
|
||||
'title': 'Nyitott Porta Napok 2025',
|
||||
'display_id': 'nyitott-porta-napok-2025',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20210607',
|
||||
'thumbnail': 'http://petofilive.hu/wp-content/uploads/sites/4/2021/06/vlcsnap-2021-06-07-22h14m23s915-1024x576.jpg',
|
||||
'upload_date': '20250809',
|
||||
'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2025/08/vlcsnap-2025-08-09-10h35m01s887.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to empty page',
|
||||
}, {
|
||||
# petofilive
|
||||
'url': 'https://petofilive.hu/video/2023/09/09/futball-fesztival-a-margitszigeten/',
|
||||
'info_dict': {
|
||||
'id': '6713233',
|
||||
'title': 'Futball Fesztivál a Margitszigeten',
|
||||
'display_id': 'futball-fesztival-a-margitszigeten',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230909',
|
||||
'thumbnail': 'https://petofilive.hu/wp-content/uploads/sites/4/2023/09/Clipboard11-2.jpg',
|
||||
},
|
||||
'skip': 'Webpage redirects to video list page',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -133,9 +77,8 @@ def _real_extract(self, url):
|
||||
display_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
player_data_str = self._html_search_regex(
|
||||
r'mtva_player_manager\.player\(document.getElementById\(.*\),\s?(\{.*\}).*\);', webpage, 'player data')
|
||||
player_data = self._parse_json(player_data_str, display_id, urllib.parse.unquote)
|
||||
player_data = self._search_json(
|
||||
r'loadPlayer\((?:\s*["\'][^"\']+["\']\s*,)?', webpage, 'player data', mobj)
|
||||
video_id = str(player_data['contentId'])
|
||||
title = player_data.get('title') or self._og_search_title(webpage, fatal=False) or \
|
||||
self._html_search_regex(r'<h\d+\b[^>]+\bclass="article_title">([^<]+)<', webpage, 'title')
|
||||
@@ -146,7 +89,7 @@ def _real_extract(self, url):
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
|
||||
|
||||
player_data['video'] = player_data.pop('token')
|
||||
player_data['video'] = urllib.parse.unquote(player_data.pop('token'))
|
||||
player_page = self._download_webpage(
|
||||
'https://player.mediaklikk.hu/playernew/player.php', video_id,
|
||||
query=player_data, headers={'Referer': url})
|
||||
|
||||
@@ -1,15 +1,73 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
mimetype2ext,
|
||||
parse_iso8601,
|
||||
parse_resolution,
|
||||
str_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import find_elements, traverse_obj
|
||||
|
||||
|
||||
class MedialaanIE(InfoExtractor):
|
||||
class MedialaanBaseIE(InfoExtractor):
|
||||
def _extract_from_mychannels_api(self, mychannels_id):
|
||||
webpage = self._download_webpage(
|
||||
f'https://mychannels.video/embed/{mychannels_id}', mychannels_id)
|
||||
brand_config = self._search_json(
|
||||
r'window\.mychannels\.brand_config\s*=', webpage, 'brand config', mychannels_id)
|
||||
response = self._download_json(
|
||||
f'https://api.mychannels.world/v1/embed/video/{mychannels_id}',
|
||||
mychannels_id, headers={'X-Mychannels-Brand': brand_config['brand']})
|
||||
|
||||
formats = []
|
||||
for stream in traverse_obj(response, (
|
||||
'streams', lambda _, v: url_or_none(v['url']),
|
||||
)):
|
||||
source_url = stream['url']
|
||||
ext = determine_ext(source_url)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source_url, mychannels_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
format_id = traverse_obj(stream, ('quality', {str}))
|
||||
formats.append({
|
||||
'ext': ext,
|
||||
'format_id': format_id,
|
||||
'url': source_url,
|
||||
**parse_resolution(format_id),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': mychannels_id,
|
||||
'formats': formats,
|
||||
**traverse_obj(response, {
|
||||
'title': ('title', {clean_html}),
|
||||
'description': ('description', {clean_html}, filter),
|
||||
'duration': ('durationMs', {int_or_none(scale=1000)}, {lambda x: x if x >= 0 else None}),
|
||||
'genres': ('genre', 'title', {str}, filter, all, filter),
|
||||
'is_live': ('live', {bool}),
|
||||
'release_timestamp': ('publicationTimestampMs', {int_or_none(scale=1000)}),
|
||||
'tags': ('tags', ..., 'title', {str}, filter, all, filter),
|
||||
'thumbnail': ('image', 'baseUrl', {url_or_none}),
|
||||
}),
|
||||
**traverse_obj(response, ('channel', {
|
||||
'channel': ('title', {clean_html}),
|
||||
'channel_id': ('id', {str_or_none}),
|
||||
})),
|
||||
**traverse_obj(response, ('organisation', {
|
||||
'uploader': ('title', {clean_html}),
|
||||
'uploader_id': ('id', {str_or_none}),
|
||||
})),
|
||||
**traverse_obj(response, ('show', {
|
||||
'series': ('title', {clean_html}),
|
||||
'series_id': ('id', {str_or_none}),
|
||||
})),
|
||||
}
|
||||
|
||||
|
||||
class MedialaanIE(MedialaanBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
@@ -32,7 +90,7 @@ class MedialaanIE(InfoExtractor):
|
||||
tubantia|
|
||||
volkskrant
|
||||
)\.nl
|
||||
)/video/(?:[^/]+/)*[^/?&#]+~p
|
||||
)/videos?/(?:[^/?#]+/)*[^/?&#]+(?:-|~p)
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
@@ -42,18 +100,83 @@ class MedialaanIE(InfoExtractor):
|
||||
'id': '193993',
|
||||
'ext': 'mp4',
|
||||
'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
|
||||
'timestamp': 1611663540,
|
||||
'upload_date': '20210126',
|
||||
'description': 'In een nieuwe Gegenpressing video bespreken Yadran Blanco en Dennis Kas het nieuws omrent NAC.',
|
||||
'duration': 238,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
'channel': 'BN DeStem',
|
||||
'channel_id': '418',
|
||||
'genres': ['Sports'],
|
||||
'release_date': '20210126',
|
||||
'release_timestamp': 1611663540,
|
||||
'series': 'Korte Reportage',
|
||||
'series_id': '972',
|
||||
'tags': 'count:2',
|
||||
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
|
||||
'uploader': 'BN De Stem',
|
||||
'uploader_id': '26',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
|
||||
'only_matching': True,
|
||||
'info_dict': {
|
||||
'id': '194093',
|
||||
'ext': 'mp4',
|
||||
'title': 'Noodbevel in Doetinchem: politie stuurt mensen centrum uit',
|
||||
'description': 'md5:77e85b2cb26cfff9dc1fe2b1db524001',
|
||||
'duration': 44,
|
||||
'channel': 'De Gelderlander',
|
||||
'channel_id': '320',
|
||||
'genres': ['News'],
|
||||
'release_date': '20210126',
|
||||
'release_timestamp': 1611690600,
|
||||
'series': 'Snel Nieuws',
|
||||
'series_id': '984',
|
||||
'tags': 'count:1',
|
||||
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
|
||||
'uploader': 'De Gelderlander',
|
||||
'uploader_id': '25',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
|
||||
'url': 'https://www.7sur7.be/videos/production/lla-tendance-tiktok-qui-enflamme-lespagne-707650',
|
||||
'info_dict': {
|
||||
'id': '707650',
|
||||
'ext': 'mp4',
|
||||
'title': 'La tendance TikTok qui enflamme l’Espagne',
|
||||
'description': 'md5:c7ec4cb733190f227fc8935899f533b5',
|
||||
'duration': 70,
|
||||
'channel': 'Lifestyle',
|
||||
'channel_id': '770',
|
||||
'genres': ['Beauty & Lifestyle'],
|
||||
'release_date': '20240906',
|
||||
'release_timestamp': 1725617330,
|
||||
'series': 'Lifestyle',
|
||||
'series_id': '1848',
|
||||
'tags': 'count:1',
|
||||
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
|
||||
'uploader': '7sur7',
|
||||
'uploader_id': '67',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://mychannels.video/embed/313117',
|
||||
'info_dict': {
|
||||
'id': '313117',
|
||||
'ext': 'mp4',
|
||||
'title': str,
|
||||
'description': 'md5:255e2e52f6fe8a57103d06def438f016',
|
||||
'channel': 'AD',
|
||||
'channel_id': '238',
|
||||
'genres': ['News'],
|
||||
'live_status': 'is_live',
|
||||
'release_date': '20241225',
|
||||
'release_timestamp': 1735169425,
|
||||
'series': 'Nieuws Update',
|
||||
'series_id': '3337',
|
||||
'tags': 'count:1',
|
||||
'thumbnail': r're:https?://images\.mychannels\.video/imgix/.+\.(?:jpe?g|png)',
|
||||
'uploader': 'AD',
|
||||
'uploader_id': '1',
|
||||
},
|
||||
'params': {'skip_download': 'Livestream'},
|
||||
}, {
|
||||
'url': 'https://embed.mychannels.video/sdk/production/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://embed.mychannels.video/script/production/193993',
|
||||
@@ -61,51 +184,41 @@ class MedialaanIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://embed.mychannels.video/production/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://mychannels.video/embed/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://embed.mychannels.video/embed/193993',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
'url': 'https://www.demorgen.be/snelnieuws/tom-waes-promoot-alcoholtesten-op-werchter-ik-ben-de-laatste-persoon-die-met-de-vinger-moet-wijzen~b7457c0d/',
|
||||
'info_dict': {
|
||||
'id': '1576607',
|
||||
'ext': 'mp4',
|
||||
'title': 'Tom Waes blaastest',
|
||||
'channel': 'De Morgen',
|
||||
'channel_id': '352',
|
||||
'description': 'Tom Waes werkt mee aan een alcoholcampagne op Werchter',
|
||||
'duration': 62,
|
||||
'genres': ['News'],
|
||||
'release_date': '20250705',
|
||||
'release_timestamp': 1751730795,
|
||||
'series': 'Nieuwsvideo\'s',
|
||||
'series_id': '1683',
|
||||
'tags': 'count:1',
|
||||
'thumbnail': r're:https?://video-images\.persgroep\.be/aws_generated.+\.jpg',
|
||||
'uploader': 'De Morgen',
|
||||
'uploader_id': '17',
|
||||
},
|
||||
'params': {'extractor_args': {'generic': {'impersonate': ['chrome']}}},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
entries = []
|
||||
for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
|
||||
mychannels_id = extract_attributes(element).get('data-mychannels-id')
|
||||
if mychannels_id:
|
||||
entries.append('https://mychannels.video/embed/' + mychannels_id)
|
||||
return entries
|
||||
yield from traverse_obj(webpage, (
|
||||
{find_elements(tag='div', attr='data-mychannels-type', value='video', html=True)},
|
||||
..., {extract_attributes}, 'data-mychannels-id', {str}, filter,
|
||||
{lambda x: f'https://mychannels.video/embed/{x}'}))
|
||||
|
||||
def _real_extract(self, url):
|
||||
production_id = self._match_id(url)
|
||||
production = self._download_json(
|
||||
'https://embed.mychannels.video/sdk/production/' + production_id,
|
||||
production_id, query={'options': 'UUUU_default'})['productions'][0]
|
||||
title = production['title']
|
||||
mychannels_id = self._match_id(url)
|
||||
|
||||
formats = []
|
||||
for source in (production.get('sources') or []):
|
||||
src = source.get('src')
|
||||
if not src:
|
||||
continue
|
||||
ext = mimetype2ext(source.get('type'))
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
src, production_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'ext': ext,
|
||||
'url': src,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': production_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': production.get('posterUrl'),
|
||||
'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
|
||||
'duration': int_or_none(production.get('duration')) or None,
|
||||
}
|
||||
return self._extract_from_mychannels_api(mychannels_id)
|
||||
|
||||
@@ -31,10 +31,9 @@ class MegaTVComIE(MegaTVComBaseIE):
|
||||
IE_NAME = 'megatvcom'
|
||||
IE_DESC = 'megatv.com videos'
|
||||
_VALID_URL = r'https?://(?:www\.)?megatv\.com/(?:\d{4}/\d{2}/\d{2}|[^/]+/(?P<id>\d+))/(?P<slug>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# FIXME: Unable to extract article id
|
||||
'url': 'https://www.megatv.com/2021/10/23/egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia/',
|
||||
'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
|
||||
'info_dict': {
|
||||
'id': '520979',
|
||||
'ext': 'mp4',
|
||||
@@ -43,20 +42,19 @@ class MegaTVComIE(MegaTVComBaseIE):
|
||||
'timestamp': 1634975747,
|
||||
'upload_date': '20211023',
|
||||
'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
|
||||
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
|
||||
'thumbnail': r're:https?://www\.megatv\.com/wp-content/uploads/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.megatv.com/tvshows/527800/epeisodio-65-12/',
|
||||
'md5': 'cba2085d45c1abeb8e7e9b7e1d6c0072',
|
||||
'info_dict': {
|
||||
'id': '527800',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:fc322cb51f682eecfe2f54cd5ab3a157',
|
||||
'title': 'Η Γη της Ελιάς: Επεισόδιο 65 - A\' ΚΥΚΛΟΣ ',
|
||||
'description': 'md5:b2b7ed3690a78f2a0156eb790fdc00df',
|
||||
'timestamp': 1636048859,
|
||||
'upload_date': '20211104',
|
||||
'display_id': 'epeisodio-65-12',
|
||||
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/16-1-1.jpg',
|
||||
'thumbnail': r're:https?://www\.megatv\.com/wp-content/uploads/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
@@ -104,8 +102,8 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
|
||||
IE_DESC = 'megatv.com embedded videos'
|
||||
_VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
|
||||
_EMBED_REGEX = [rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''']
|
||||
|
||||
_TESTS = [{
|
||||
# FIXME: Unable to extract article id
|
||||
'url': 'https://www.megatv.com/embed/?p=2020520979',
|
||||
'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
|
||||
'info_dict': {
|
||||
@@ -119,6 +117,7 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
|
||||
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
|
||||
},
|
||||
}, {
|
||||
# FIXME: Unable to extract article id
|
||||
'url': 'https://www.megatv.com/embed/?p=2020534081',
|
||||
'md5': '6ac8b3ce4dc6120c802f780a1e6b3812',
|
||||
'info_dict': {
|
||||
@@ -132,6 +131,15 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
|
||||
'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/Capture-266.jpg',
|
||||
},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Unable to extract article id
|
||||
'url': 'https://www.in.gr/2021/12/18/greece/apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize/',
|
||||
'info_dict': {
|
||||
'id': 'apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize',
|
||||
'title': 'md5:5e569cf996ec111057c2764ec272848f',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}]
|
||||
|
||||
def _match_canonical_url(self, webpage):
|
||||
LINK_RE = r'''(?x)
|
||||
|
||||
37
yt_dlp/extractor/mir24tv.py
Normal file
37
yt_dlp/extractor/mir24tv.py
Normal file
@@ -0,0 +1,37 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_qs, url_or_none
|
||||
from ..utils.traversal import require, traverse_obj
|
||||
|
||||
|
||||
class Mir24TvIE(InfoExtractor):
|
||||
IE_NAME = 'mir24.tv'
|
||||
_VALID_URL = r'https?://(?:www\.)?mir24\.tv/news/(?P<id>[0-9]+)/[^/?#]+'
|
||||
_TESTS = [{
|
||||
'url': 'https://mir24.tv/news/16635210/dni-kultury-rossii-otkrylis-v-uzbekistane.-na-prazdnichnom-koncerte-vystupili-zvezdy-rossijskoj-estrada',
|
||||
'info_dict': {
|
||||
'id': '16635210',
|
||||
'title': 'Дни культуры России открылись в Узбекистане. На праздничном концерте выступили звезды российской эстрады',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:https://images\.mir24\.tv/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id, impersonate=True)
|
||||
|
||||
iframe_url = self._search_regex(
|
||||
r'<iframe\b[^>]+\bsrc=["\'](https?://mir24\.tv/players/[^"\']+)',
|
||||
webpage, 'iframe URL')
|
||||
|
||||
m3u8_url = traverse_obj(iframe_url, (
|
||||
{parse_qs}, 'source', -1, {self._proto_relative_url}, {url_or_none}, {require('m3u8 URL')}))
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage, default=None) or self._html_extract_title(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
@@ -18,7 +18,7 @@ class MirrativIE(MirrativBaseIE):
|
||||
IE_NAME = 'mirrativ'
|
||||
_VALID_URL = r'https?://(?:www\.)?mirrativ\.com/live/(?P<id>[^/?#&]+)'
|
||||
|
||||
TESTS = [{
|
||||
_TESTS = [{
|
||||
'url': 'https://mirrativ.com/live/UQomuS7EMgHoxRHjEhNiHw',
|
||||
'info_dict': {
|
||||
'id': 'UQomuS7EMgHoxRHjEhNiHw',
|
||||
|
||||
@@ -79,7 +79,7 @@ class MiTeleIE(TelecincoBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_akamai_webpage(url, display_id)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
pre_player = self._search_json(
|
||||
r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
|
||||
webpage, 'Pre Player', display_id)['prePlayer']
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user