mirror of
https://github.com/yt-dlp/yt-dlp
synced 2025-12-17 06:35:42 +07:00
Compare commits
35 Commits
2023.06.22
...
2023.07.06
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cc0619f62d | ||
|
|
b532a34810 | ||
|
|
3121512228 | ||
|
|
f8b4bcc0a7 | ||
|
|
1ceb657bdd | ||
|
|
ad8902f616 | ||
|
|
94ed638a43 | ||
|
|
bc344cd456 | ||
|
|
906c0bdcd8 | ||
|
|
337734d4a8 | ||
|
|
fa44802809 | ||
|
|
47bcd43724 | ||
|
|
662ef1e910 | ||
|
|
6355b5f1e1 | ||
|
|
90db9a3c00 | ||
|
|
49296437a8 | ||
|
|
1cffd621cb | ||
|
|
3b7f5300c5 | ||
|
|
4dc4d8473c | ||
|
|
8776349ef6 | ||
|
|
af1fd12f67 | ||
|
|
fcbc9ed760 | ||
|
|
a2be9781fb | ||
|
|
8f05fbae2a | ||
|
|
5b4b92769a | ||
|
|
91302ed349 | ||
|
|
f393bbe724 | ||
|
|
8a8af356e3 | ||
|
|
d949c10c45 | ||
|
|
ef8509c300 | ||
|
|
5e16cf92eb | ||
|
|
f0a1ff1181 | ||
|
|
58786a10f2 | ||
|
|
e59e20744e | ||
|
|
89bed01374 |
8
.github/ISSUE_TEMPLATE/1_broken_site.yml
vendored
8
.github/ISSUE_TEMPLATE/1_broken_site.yml
vendored
@@ -18,7 +18,7 @@ body:
|
||||
options:
|
||||
- label: I'm reporting that yt-dlp is broken on a **supported** site
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
|
||||
required: true
|
||||
@@ -64,7 +64,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -72,8 +72,8 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
validations:
|
||||
|
||||
@@ -18,7 +18,7 @@ body:
|
||||
options:
|
||||
- label: I'm reporting a new site support request
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
|
||||
required: true
|
||||
@@ -76,7 +76,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -84,8 +84,8 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
validations:
|
||||
|
||||
@@ -18,7 +18,7 @@ body:
|
||||
options:
|
||||
- label: I'm requesting a site-specific feature
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
|
||||
required: true
|
||||
@@ -72,7 +72,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -80,8 +80,8 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
validations:
|
||||
|
||||
8
.github/ISSUE_TEMPLATE/4_bug_report.yml
vendored
8
.github/ISSUE_TEMPLATE/4_bug_report.yml
vendored
@@ -18,7 +18,7 @@ body:
|
||||
options:
|
||||
- label: I'm reporting a bug unrelated to a specific site
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
|
||||
required: true
|
||||
@@ -57,7 +57,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -65,8 +65,8 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
validations:
|
||||
|
||||
8
.github/ISSUE_TEMPLATE/5_feature_request.yml
vendored
8
.github/ISSUE_TEMPLATE/5_feature_request.yml
vendored
@@ -20,7 +20,7 @@ body:
|
||||
required: true
|
||||
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
|
||||
required: true
|
||||
@@ -53,7 +53,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -61,7 +61,7 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
|
||||
8
.github/ISSUE_TEMPLATE/6_question.yml
vendored
8
.github/ISSUE_TEMPLATE/6_question.yml
vendored
@@ -26,7 +26,7 @@ body:
|
||||
required: true
|
||||
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
|
||||
required: true
|
||||
- label: I've verified that I'm running yt-dlp version **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
- label: I've verified that I'm running yt-dlp version **2023.07.06** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
|
||||
required: true
|
||||
- label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
|
||||
required: true
|
||||
@@ -59,7 +59,7 @@ body:
|
||||
[debug] Command-line config: ['-vU', 'test:youtube']
|
||||
[debug] Portable config "yt-dlp.conf": ['-i']
|
||||
[debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
|
||||
[debug] yt-dlp version 2023.06.22 [9d339c4] (win32_exe)
|
||||
[debug] yt-dlp version 2023.07.06 [9d339c4] (win32_exe)
|
||||
[debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
|
||||
[debug] Checking exe version: ffmpeg -bsfs
|
||||
[debug] Checking exe version: ffprobe -bsfs
|
||||
@@ -67,7 +67,7 @@ body:
|
||||
[debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
|
||||
[debug] Proxy map: {}
|
||||
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
|
||||
Latest version: 2023.06.22, Current version: 2023.06.22
|
||||
yt-dlp is up to date (2023.06.22)
|
||||
Latest version: 2023.07.06, Current version: 2023.07.06
|
||||
yt-dlp is up to date (2023.07.06)
|
||||
<more lines>
|
||||
render: shell
|
||||
|
||||
65
.github/workflows/codeql.yml
vendored
Normal file
65
.github/workflows/codeql.yml
vendored
Normal file
@@ -0,0 +1,65 @@
|
||||
name: "CodeQL"
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ 'master', 'gh-pages', 'release' ]
|
||||
pull_request:
|
||||
# The branches below must be a subset of the branches above
|
||||
branches: [ 'master' ]
|
||||
schedule:
|
||||
- cron: '59 11 * * 5'
|
||||
|
||||
jobs:
|
||||
analyze:
|
||||
name: Analyze
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
actions: read
|
||||
contents: read
|
||||
security-events: write
|
||||
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
language: [ 'python' ]
|
||||
# CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
|
||||
# Use only 'java' to analyze code written in Java, Kotlin or both
|
||||
# Use only 'javascript' to analyze code written in JavaScript, TypeScript or both
|
||||
# Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v3
|
||||
|
||||
# Initializes the CodeQL tools for scanning.
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# If you wish to specify custom queries, you can do so here or in a config file.
|
||||
# By default, queries listed here will override any specified in a config file.
|
||||
# Prefix the list here with "+" to use these queries and those in the config file.
|
||||
|
||||
# For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
|
||||
# queries: security-extended,security-and-quality
|
||||
|
||||
|
||||
# Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
|
||||
# If this step fails, then you should remove it and run the build manually (see below)
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@v2
|
||||
|
||||
# ℹ️ Command-line programs to run using the OS shell.
|
||||
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
|
||||
|
||||
# If the Autobuild fails above, remove it and uncomment the following three lines.
|
||||
# modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
|
||||
|
||||
# - run: |
|
||||
# echo "Run, Build Application using script"
|
||||
# ./location_of_script_within_repo/buildscript.sh
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v2
|
||||
with:
|
||||
category: "/language:${{matrix.language}}"
|
||||
@@ -460,3 +460,10 @@ berkanteber
|
||||
OverlordQ
|
||||
rexlambert22
|
||||
Ti4eeT4e
|
||||
AmanSal1
|
||||
bbilly1
|
||||
meliber
|
||||
nnoboa
|
||||
rdamas
|
||||
RfadnjdExt
|
||||
urectanc
|
||||
|
||||
58
Changelog.md
58
Changelog.md
@@ -4,11 +4,65 @@ # Changelog
|
||||
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
|
||||
-->
|
||||
|
||||
### 2023.07.06
|
||||
|
||||
#### Important changes
|
||||
- Security: [[CVE-2023-35934](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-35934)] Fix [Cookie leak](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj)
|
||||
- `--add-header Cookie:` is deprecated and auto-scoped to input URL domains
|
||||
- Cookies are scoped when passed to external downloaders
|
||||
- Add `cookie` field to info.json and deprecate `http_headers.Cookie`
|
||||
|
||||
#### Core changes
|
||||
- [Allow extractors to mark formats as potentially DRM](https://github.com/yt-dlp/yt-dlp/commit/bc344cd456380999c1ee74554dfd432a38f32ec7) ([#7396](https://github.com/yt-dlp/yt-dlp/issues/7396)) by [pukkandan](https://github.com/pukkandan)
|
||||
- [Bugfix for b4e0d75848e9447cee2cd3646ce54d4744a7ff56](https://github.com/yt-dlp/yt-dlp/commit/e59e20744eb32ce4b6ea0dece7c673be8376a710) by [pukkandan](https://github.com/pukkandan)
|
||||
- [Change how `Cookie` headers are handled](https://github.com/yt-dlp/yt-dlp/commit/3121512228487c9c690d3d39bfd2579addf96e07) by [Grub4K](https://github.com/Grub4K)
|
||||
- [Prevent `Cookie` leaks on HTTP redirect](https://github.com/yt-dlp/yt-dlp/commit/f8b4bcc0a791274223723488bfbfc23ea3276641) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- **formats**: [Fix best fallback for storyboards](https://github.com/yt-dlp/yt-dlp/commit/906c0bdcd8974340d619e99ccd613c163eb0d0c2) by [pukkandan](https://github.com/pukkandan)
|
||||
- **outtmpl**: [Pad `playlist_index` etc even when with internal formatting](https://github.com/yt-dlp/yt-dlp/commit/47bcd437247152e0af5b3ebc5592db7bb66855c2) by [pukkandan](https://github.com/pukkandan)
|
||||
- **utils**: clean_podcast_url: [Handle protocol in redirect URL](https://github.com/yt-dlp/yt-dlp/commit/91302ed349f34dc26cc1d661bb45a4b71f4417f7) by [pukkandan](https://github.com/pukkandan)
|
||||
|
||||
#### Extractor changes
|
||||
- **abc**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/8f05fbae2a79ce0713077ccc68b354e63216bf20) ([#7434](https://github.com/yt-dlp/yt-dlp/issues/7434)) by [meliber](https://github.com/meliber)
|
||||
- **AdultSwim**: [Extract subtitles from m3u8](https://github.com/yt-dlp/yt-dlp/commit/5e16cf92eb496b7c1541a6b1d727cb87542984db) ([#7421](https://github.com/yt-dlp/yt-dlp/issues/7421)) by [nnoboa](https://github.com/nnoboa)
|
||||
- **crunchyroll**: music: [Fix `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/5b4b92769afcc398475e481bfa839f1158902fe9) ([#7439](https://github.com/yt-dlp/yt-dlp/issues/7439)) by [AmanSal1](https://github.com/AmanSal1), [rdamas](https://github.com/rdamas)
|
||||
- **Douyin**: [Fix extraction from webpage](https://github.com/yt-dlp/yt-dlp/commit/a2be9781fbf4d7e4db245c277ca2ecc41cf3a7b2) by [bashonly](https://github.com/bashonly)
|
||||
- **googledrive**: [Fix source format extraction](https://github.com/yt-dlp/yt-dlp/commit/3b7f5300c577fef40464d46d4e4037a69d51fe82) ([#7395](https://github.com/yt-dlp/yt-dlp/issues/7395)) by [RfadnjdExt](https://github.com/RfadnjdExt)
|
||||
- **kick**: [Fix `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/ef8509c300ea50da86aea447eb214d3d6f6db6bb) by [bashonly](https://github.com/bashonly)
|
||||
- **qdance**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/f0a1ff118145b6449982ba401f9a9f656ecd8062) ([#7420](https://github.com/yt-dlp/yt-dlp/issues/7420)) by [bashonly](https://github.com/bashonly)
|
||||
- **sbs**: [Python 3.7 compat](https://github.com/yt-dlp/yt-dlp/commit/f393bbe724b1fc6c7f754a5da507e807b2b40ad2) by [pukkandan](https://github.com/pukkandan)
|
||||
- **stacommu**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/af1fd12f675220df6793fc019dff320bc76e8080) ([#7432](https://github.com/yt-dlp/yt-dlp/issues/7432)) by [urectanc](https://github.com/urectanc)
|
||||
- **twitter**
|
||||
- [Fix unauthenticated extraction](https://github.com/yt-dlp/yt-dlp/commit/49296437a8e5fa91dacb5446e51ab588474c85d3) ([#7476](https://github.com/yt-dlp/yt-dlp/issues/7476)) by [bashonly](https://github.com/bashonly)
|
||||
- spaces: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1cffd621cb371f1563563cfb2fe37d137e8a7bee) ([#7512](https://github.com/yt-dlp/yt-dlp/issues/7512)) by [bashonly](https://github.com/bashonly)
|
||||
- **vidlii**: [Handle relative URLs](https://github.com/yt-dlp/yt-dlp/commit/ad8902f616ad2541f9b9626738f1393fad89a64c) by [pukkandan](https://github.com/pukkandan)
|
||||
- **vk**: VKPlay, VKPlayLive: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/8776349ef6b1f644584a92dfa00a05208a48edc4) ([#7358](https://github.com/yt-dlp/yt-dlp/issues/7358)) by [c-basalt](https://github.com/c-basalt)
|
||||
- **youtube**
|
||||
- [Add extractor-arg `formats`](https://github.com/yt-dlp/yt-dlp/commit/58786a10f212bd63f9ad1d0b4d9e4d31c3b385e2) by [pukkandan](https://github.com/pukkandan)
|
||||
- [Avoid false DRM detection](https://github.com/yt-dlp/yt-dlp/commit/94ed638a437fc766699d440e978982e24ce6a30a) ([#7396](https://github.com/yt-dlp/yt-dlp/issues/7396)) by [pukkandan](https://github.com/pukkandan)
|
||||
- [Fix comments' `is_favorited`](https://github.com/yt-dlp/yt-dlp/commit/89bed013741a776506f60380b7fd89d27d0710b4) ([#7390](https://github.com/yt-dlp/yt-dlp/issues/7390)) by [bbilly1](https://github.com/bbilly1)
|
||||
- [Ignore incomplete data for comment threads by default](https://github.com/yt-dlp/yt-dlp/commit/4dc4d8473c085900edc841c87c20041233d25b1f) ([#7475](https://github.com/yt-dlp/yt-dlp/issues/7475)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
- [Process `post_live` over 2 hours](https://github.com/yt-dlp/yt-dlp/commit/d949c10c45bfc359bdacd52e6a180169b8128958) by [pukkandan](https://github.com/pukkandan)
|
||||
- stories: [Remove](https://github.com/yt-dlp/yt-dlp/commit/90db9a3c00ca80492c6a58c542e4cbf4c2710866) ([#7459](https://github.com/yt-dlp/yt-dlp/issues/7459)) by [pukkandan](https://github.com/pukkandan)
|
||||
- tab: [Support shorts-only playlists](https://github.com/yt-dlp/yt-dlp/commit/fcbc9ed760be6e3455bbadfaf277b4504b06f068) ([#7425](https://github.com/yt-dlp/yt-dlp/issues/7425)) by [coletdjnz](https://github.com/coletdjnz)
|
||||
|
||||
#### Downloader changes
|
||||
- **aria2c**: [Add `--no-conf`](https://github.com/yt-dlp/yt-dlp/commit/8a8af356e3bba98a7f7d333aff0777d5d92130c8) by [pukkandan](https://github.com/pukkandan)
|
||||
- **external**: [Scope cookies](https://github.com/yt-dlp/yt-dlp/commit/1ceb657bdd254ad961489e5060f2ccc7d556b729) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz)
|
||||
- **http**: [Avoid infinite loop when no data is received](https://github.com/yt-dlp/yt-dlp/commit/662ef1e910b72e57957f06589925b2332ba52821) by [pukkandan](https://github.com/pukkandan)
|
||||
|
||||
#### Misc. changes
|
||||
- [Add CodeQL workflow](https://github.com/yt-dlp/yt-dlp/commit/6355b5f1e1e8e7f4ef866d71d51e03baf0e82f17) ([#7497](https://github.com/yt-dlp/yt-dlp/issues/7497)) by [pukkandan](https://github.com/pukkandan)
|
||||
- **cleanup**: Miscellaneous: [337734d](https://github.com/yt-dlp/yt-dlp/commit/337734d4a8a6500bc65434843db346b5cbd05e81) by [pukkandan](https://github.com/pukkandan)
|
||||
- **docs**: [Minor fixes](https://github.com/yt-dlp/yt-dlp/commit/b532a3481046e1eabb6232ee8196fb696c356ff6) by [pukkandan](https://github.com/pukkandan)
|
||||
- **make_changelog**: [Skip reverted commits](https://github.com/yt-dlp/yt-dlp/commit/fa44802809d189fca0f4782263d48d6533384503) by [pukkandan](https://github.com/pukkandan)
|
||||
|
||||
### 2023.06.22
|
||||
|
||||
#### Core changes
|
||||
- [Fix bug in db3ad8a67661d7b234a6954d9c6a4a9b1749f5eb](https://github.com/yt-dlp/yt-dlp/commit/d7cd97e8d8d42b500fea9abb2aa4ac9b0f98b2ad) by [pukkandan](https://github.com/pukkandan)
|
||||
- [Improve `--download-sections`](https://github.com/yt-dlp/yt-dlp/commit/b4e0d75848e9447cee2cd3646ce54d4744a7ff56) by [pukkandan](https://github.com/pukkandan)
|
||||
- Support negative time-ranges
|
||||
- Add `*from-url` to obey time-ranges in URL
|
||||
- [Indicate `filesize` approximated from `tbr` better](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) by [pukkandan](https://github.com/pukkandan)
|
||||
|
||||
#### Extractor changes
|
||||
@@ -19,7 +73,7 @@ #### Extractor changes
|
||||
- **nebula**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3f756c8c4095b942cf49788eb0862ceaf57847f2) ([#7156](https://github.com/yt-dlp/yt-dlp/issues/7156)) by [Lamieur](https://github.com/Lamieur), [rohieb](https://github.com/rohieb)
|
||||
- **rheinmaintv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/98cb1eda7a4cf67c96078980dbd63e6c06ad7f7c) ([#7311](https://github.com/yt-dlp/yt-dlp/issues/7311)) by [barthelmannk](https://github.com/barthelmannk)
|
||||
- **youtube**
|
||||
- [Add `ios` to default clients used](https://github.com/yt-dlp/yt-dlp/commit/1e75d97db21152acc764b30a688e516f04b8a142)
|
||||
- [Add `ios` to default clients used](https://github.com/yt-dlp/yt-dlp/commit/1e75d97db21152acc764b30a688e516f04b8a142) by [pukkandan](https://github.com/pukkandan)
|
||||
- IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively
|
||||
- IOS also has higher bit-rate 'premium' formats though they are not labeled as such
|
||||
- [Improve description parsing performance](https://github.com/yt-dlp/yt-dlp/commit/71dc18fa29263a1ff0472c23d81bfc8dd4422d48) ([#7315](https://github.com/yt-dlp/yt-dlp/issues/7315)) by [berkanteber](https://github.com/berkanteber), [pukkandan](https://github.com/pukkandan)
|
||||
@@ -27,7 +81,7 @@ #### Extractor changes
|
||||
- [Workaround 403 for android formats](https://github.com/yt-dlp/yt-dlp/commit/81ca451480051d7ce1a31c017e005358345a9149) by [pukkandan](https://github.com/pukkandan)
|
||||
|
||||
#### Misc. changes
|
||||
- [Revert "Add automatic duplicate issue detection"](https://github.com/yt-dlp/yt-dlp/commit/a4486bfc1dc7057efca9dd3fe70d7fa25c56f700)
|
||||
- [Revert "Add automatic duplicate issue detection"](https://github.com/yt-dlp/yt-dlp/commit/a4486bfc1dc7057efca9dd3fe70d7fa25c56f700) by [pukkandan](https://github.com/pukkandan)
|
||||
- **cleanup**
|
||||
- Miscellaneous
|
||||
- [7f9c6a6](https://github.com/yt-dlp/yt-dlp/commit/7f9c6a63b16e145495479e9f666f5b9e2ee69e2f) by [bashonly](https://github.com/bashonly)
|
||||
|
||||
20
README.md
20
README.md
@@ -12,7 +12,7 @@
|
||||
[](LICENSE "License")
|
||||
[](https://github.com/yt-dlp/yt-dlp/actions "CI Status")
|
||||
[](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
|
||||
[](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
|
||||
[](https://github.com/yt-dlp/yt-dlp/pulse/monthly "Last activity")
|
||||
|
||||
</div>
|
||||
<!-- MANPAGE: END EXCLUDED SECTION -->
|
||||
@@ -76,7 +76,7 @@
|
||||
|
||||
# NEW FEATURES
|
||||
|
||||
* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@42f2d4**](https://github.com/yt-dlp/yt-dlp/commit/42f2d4) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))
|
||||
* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@42f2d4**](https://github.com/ytdl-org/youtube-dl/commit/07af47960f3bb262ead02490ce65c8c45c01741e) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))
|
||||
|
||||
* **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in YouTube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
|
||||
|
||||
@@ -1323,7 +1323,7 @@ # OUTPUT TEMPLATE
|
||||
- `extractor` (string): Name of the extractor
|
||||
- `extractor_key` (string): Key name of the extractor
|
||||
- `epoch` (numeric): Unix epoch of when the information extraction was completed
|
||||
- `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`
|
||||
- `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`, padded with leading zeros to 5 digits
|
||||
- `video_autonumber` (numeric): Number that will be increased with each video
|
||||
- `n_entries` (numeric): Total number of extracted items in the playlist
|
||||
- `playlist_id` (string): Identifier of the playlist that contains the video
|
||||
@@ -1509,7 +1509,7 @@ # FORMAT SELECTION
|
||||
|
||||
## Filtering Formats
|
||||
|
||||
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
|
||||
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"` since filters without a selector are interpreted as `best`).
|
||||
|
||||
The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
|
||||
|
||||
@@ -1545,7 +1545,7 @@ ## Filtering Formats
|
||||
|
||||
**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
|
||||
|
||||
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
|
||||
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
|
||||
|
||||
Format selectors can also be grouped using parentheses; e.g. `-f "(mp4,webm)[height<480]"` will download the best pre-merged mp4 and webm formats with a height lower than 480.
|
||||
|
||||
@@ -1805,8 +1805,7 @@ #### youtube
|
||||
* `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
|
||||
* `include_duplicate_formats`: Extract formats with identical content but different URLs or protocol. This is useful if some of the formats are unavailable or throttled.
|
||||
* `include_incomplete_formats`: Extract formats that cannot be downloaded completely (live dash and post-live m3u8)
|
||||
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
|
||||
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
|
||||
* `innertube_key`: Innertube API key to use for all API requests
|
||||
|
||||
@@ -1853,10 +1852,7 @@ #### tiktok
|
||||
#### rokfinchannel
|
||||
* `tab`: Which tab to download - one of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks`
|
||||
|
||||
#### twitter
|
||||
* `legacy_api`: Force usage of the legacy Twitter API instead of the GraphQL API for tweet extraction. Has no effect if login cookies are passed
|
||||
|
||||
#### wrestleuniverse
|
||||
#### stacommu, wrestleuniverse
|
||||
* `device_id`: UUID value assigned by the website and used to enforce device limits for paid livestream content. Can be found in browser local storage
|
||||
|
||||
#### twitch
|
||||
@@ -1954,7 +1950,7 @@ # EMBEDDING YT-DLP
|
||||
ydl.download(URLS)
|
||||
```
|
||||
|
||||
Most likely, you'll want to use various options. For a list of options available, have a look at [`yt_dlp/YoutubeDL.py`](yt_dlp/YoutubeDL.py#L184).
|
||||
Most likely, you'll want to use various options. For a list of options available, have a look at [`yt_dlp/YoutubeDL.py`](yt_dlp/YoutubeDL.py#L183) or `help(yt_dlp.YoutubeDL)` in a Python shell. If you are already familiar with the CLI, you can use [`devscripts/cli_to_api.py`](https://github.com/yt-dlp/yt-dlp/blob/master/devscripts/cli_to_api.py) to translate any CLI switches to `YoutubeDL` params.
|
||||
|
||||
**Tip**: If you are porting your code from youtube-dl to yt-dlp, one important point to look out for is that we do not guarantee the return value of `YoutubeDL.extract_info` to be json serializable, or even be a dictionary. It will be dictionary-like, but if you want to ensure it is a serializable dictionary, pass it through `YoutubeDL.sanitize_info` as shown in the [example below](#extracting-information)
|
||||
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
[
|
||||
{
|
||||
"action": "add",
|
||||
"when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
|
||||
"when": "29cb20bd563c02671b31dd840139e93dd37150a1",
|
||||
"short": "[priority] **A new release type has been added!**\n * [`nightly`](https://github.com/yt-dlp/yt-dlp/releases/tag/nightly) builds will be made after each push, containing the latest fixes (but also possibly bugs).\n * When using `--update`/`-U`, a release binary will only update to its current channel (either `stable` or `nightly`).\n * The `--update-to` option has been added allowing the user more control over program upgrades (or downgrades).\n * `--update-to` can change the release channel (`stable`, `nightly`) and also upgrade or downgrade to specific tags.\n * **Usage**: `--update-to CHANNEL`, `--update-to TAG`, `--update-to CHANNEL@TAG`"
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
|
||||
"when": "5038f6d713303e0967d002216e7a88652401c22a",
|
||||
"short": "[priority] **YouTube throttling fixes!**"
|
||||
},
|
||||
{
|
||||
@@ -38,13 +38,15 @@
|
||||
},
|
||||
{
|
||||
"action": "change",
|
||||
"when": "7b37e8b23691613f331bd4ebc9d639dd6f93c972",
|
||||
"short": "Improve `--download-sections`\n - Support negative time-ranges\n - Add `*from-url` to obey time-ranges in URL"
|
||||
"when": "b4e0d75848e9447cee2cd3646ce54d4744a7ff56",
|
||||
"short": "Improve `--download-sections`\n - Support negative time-ranges\n - Add `*from-url` to obey time-ranges in URL",
|
||||
"authors": ["pukkandan"]
|
||||
},
|
||||
{
|
||||
"action": "change",
|
||||
"when": "1e75d97db21152acc764b30a688e516f04b8a142",
|
||||
"short": "[extractor/youtube] Add `ios` to default clients used\n - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively\n - IOS also has higher bit-rate 'premium' formats though they are not labeled as such"
|
||||
"short": "[extractor/youtube] Add `ios` to default clients used\n - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively\n - IOS also has higher bit-rate 'premium' formats though they are not labeled as such",
|
||||
"authors": ["pukkandan"]
|
||||
},
|
||||
{
|
||||
"action": "change",
|
||||
@@ -55,6 +57,12 @@
|
||||
{
|
||||
"action": "change",
|
||||
"when": "a4486bfc1dc7057efca9dd3fe70d7fa25c56f700",
|
||||
"short": "[misc] Revert \"Add automatic duplicate issue detection\""
|
||||
"short": "[misc] Revert \"Add automatic duplicate issue detection\"",
|
||||
"authors": ["pukkandan"]
|
||||
},
|
||||
{
|
||||
"action": "add",
|
||||
"when": "1ceb657bdd254ad961489e5060f2ccc7d556b729",
|
||||
"short": "[priority] Security: [[CVE-2023-35934](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-35934)] Fix [Cookie leak](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj)\n - `--add-header Cookie:` is deprecated and auto-scoped to input URL domains\n - Cookies are scoped when passed to external downloaders\n - Add `cookie` field to info.json and deprecate `http_headers.Cookie`"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -55,6 +55,7 @@ def commit_lookup(cls):
|
||||
'dependencies',
|
||||
'jsinterp',
|
||||
'outtmpl',
|
||||
'formats',
|
||||
'plugins',
|
||||
'update',
|
||||
'upstream',
|
||||
@@ -68,9 +69,9 @@ def commit_lookup(cls):
|
||||
'misc',
|
||||
'test',
|
||||
},
|
||||
cls.EXTRACTOR: {'extractor'},
|
||||
cls.DOWNLOADER: {'downloader'},
|
||||
cls.POSTPROCESSOR: {'postprocessor'},
|
||||
cls.EXTRACTOR: {'extractor', 'ie'},
|
||||
cls.DOWNLOADER: {'downloader', 'fd'},
|
||||
cls.POSTPROCESSOR: {'postprocessor', 'pp'},
|
||||
}.items()
|
||||
for name in names
|
||||
}
|
||||
@@ -252,6 +253,7 @@ class CommitRange:
|
||||
(?:\ \((?P<issues>\#\d+(?:,\ \#\d+)*)\))?
|
||||
''', re.VERBOSE | re.DOTALL)
|
||||
EXTRACTOR_INDICATOR_RE = re.compile(r'(?:Fix|Add)\s+Extractors?', re.IGNORECASE)
|
||||
REVERT_RE = re.compile(r'(?i:Revert)\s+([\da-f]{40})')
|
||||
FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert)\s+([\da-f]{40})')
|
||||
UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
|
||||
|
||||
@@ -279,7 +281,7 @@ def _get_commits_and_fixes(self, default_author):
|
||||
self.COMMAND, 'log', f'--format=%H%n%s%n%b%n{self.COMMIT_SEPARATOR}',
|
||||
f'{self._start}..{self._end}' if self._start else self._end).stdout
|
||||
|
||||
commits = {}
|
||||
commits, reverts = {}, {}
|
||||
fixes = defaultdict(list)
|
||||
lines = iter(result.splitlines(False))
|
||||
for i, commit_hash in enumerate(lines):
|
||||
@@ -300,6 +302,11 @@ def _get_commits_and_fixes(self, default_author):
|
||||
logger.debug(f'Reached Release commit, breaking: {commit}')
|
||||
break
|
||||
|
||||
revert_match = self.REVERT_RE.fullmatch(commit.short)
|
||||
if revert_match:
|
||||
reverts[revert_match.group(1)] = commit
|
||||
continue
|
||||
|
||||
fix_match = self.FIXES_RE.search(commit.short)
|
||||
if fix_match:
|
||||
commitish = fix_match.group(1)
|
||||
@@ -307,6 +314,13 @@ def _get_commits_and_fixes(self, default_author):
|
||||
|
||||
commits[commit.hash] = commit
|
||||
|
||||
for commitish, revert_commit in reverts.items():
|
||||
reverted = commits.pop(commitish, None)
|
||||
if reverted:
|
||||
logger.debug(f'{commit} fully reverted {reverted}')
|
||||
else:
|
||||
commits[revert_commit.hash] = revert_commit
|
||||
|
||||
for commitish, fix_commits in fixes.items():
|
||||
if commitish in commits:
|
||||
hashes = ', '.join(commit.hash[:HASH_LENGTH] for commit in fix_commits)
|
||||
|
||||
@@ -8,7 +8,6 @@ ignore = E402,E501,E731,E741,W503
|
||||
max_line_length = 120
|
||||
per_file_ignores =
|
||||
devscripts/lazy_load_template.py: F401
|
||||
yt_dlp/utils/__init__.py: F401, F403
|
||||
|
||||
|
||||
[autoflake]
|
||||
|
||||
@@ -1136,6 +1136,7 @@ # Supported sites
|
||||
- **puhutv:serie**
|
||||
- **Puls4**
|
||||
- **Pyvideo**
|
||||
- **QDance**: [*qdance*](## "netrc machine")
|
||||
- **QingTing**
|
||||
- **qqmusic**: QQ音乐
|
||||
- **qqmusic:album**: QQ音乐 - 专辑
|
||||
@@ -1363,6 +1364,8 @@ # Supported sites
|
||||
- **sr:mediathek**: Saarländischer Rundfunk
|
||||
- **SRGSSR**
|
||||
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
|
||||
- **StacommuLive**: [*stacommu*](## "netrc machine")
|
||||
- **StacommuVOD**: [*stacommu*](## "netrc machine")
|
||||
- **StagePlusVODConcert**: [*stageplus*](## "netrc machine")
|
||||
- **stanfordoc**: Stanford Open ClassRoom
|
||||
- **StarTrek**
|
||||
@@ -1647,6 +1650,8 @@ # Supported sites
|
||||
- **vk**: [*vk*](## "netrc machine") VK
|
||||
- **vk:uservideos**: [*vk*](## "netrc machine") VK - User's Videos
|
||||
- **vk:wallpost**: [*vk*](## "netrc machine")
|
||||
- **VKPlay**
|
||||
- **VKPlayLive**
|
||||
- **vm.tiktok**
|
||||
- **Vocaroo**
|
||||
- **Vodlocker**
|
||||
@@ -1800,7 +1805,6 @@ # Supported sites
|
||||
- **youtube:search:date**: YouTube search, newest videos first; "ytsearchdate:" prefix
|
||||
- **youtube:search_url**: YouTube search URLs with sorting and filter support
|
||||
- **youtube:shorts:pivot:audio**: YouTube Shorts audio pivot (Shorts using audio of a given video)
|
||||
- **youtube:stories**: YouTube channel stories; "ytstories:" prefix
|
||||
- **youtube:subscriptions**: YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)
|
||||
- **youtube:tab**: YouTube Tabs
|
||||
- **youtube:user**: YouTube user videos; "ytuser:" prefix
|
||||
|
||||
@@ -684,7 +684,7 @@ def test(tmpl, expected, *, info=None, **params):
|
||||
test('%(id)s.%(ext)s', '1234.mp4')
|
||||
test('%(duration_string)s', ('27:46:40', '27-46-40'))
|
||||
test('%(resolution)s', '1080p')
|
||||
test('%(playlist_index)s', '001')
|
||||
test('%(playlist_index|)s', '001')
|
||||
test('%(playlist_autonumber)s', '02')
|
||||
test('%(autonumber)s', '00001')
|
||||
test('%(autonumber+2)03d', '005', autonumber_start=3)
|
||||
@@ -1213,6 +1213,62 @@ def _real_extract(self, url):
|
||||
self.assertEqual(downloaded['extractor'], 'Video')
|
||||
self.assertEqual(downloaded['extractor_key'], 'Video')
|
||||
|
||||
def test_header_cookies(self):
|
||||
from http.cookiejar import Cookie
|
||||
|
||||
ydl = FakeYDL()
|
||||
ydl.report_warning = lambda *_, **__: None
|
||||
|
||||
def cookie(name, value, version=None, domain='', path='', secure=False, expires=None):
|
||||
return Cookie(
|
||||
version or 0, name, value, None, False,
|
||||
domain, bool(domain), bool(domain), path, bool(path),
|
||||
secure, expires, False, None, None, rest={})
|
||||
|
||||
_test_url = 'https://yt.dlp/test'
|
||||
|
||||
def test(encoded_cookies, cookies, headers=False, round_trip=None, error=None):
|
||||
def _test():
|
||||
ydl.cookiejar.clear()
|
||||
ydl._load_cookies(encoded_cookies, from_headers=headers)
|
||||
if headers:
|
||||
ydl._apply_header_cookies(_test_url)
|
||||
data = {'url': _test_url}
|
||||
ydl._calc_headers(data)
|
||||
self.assertCountEqual(
|
||||
map(vars, ydl.cookiejar), map(vars, cookies),
|
||||
'Extracted cookiejar.Cookie is not the same')
|
||||
if not headers:
|
||||
self.assertEqual(
|
||||
data.get('cookies'), round_trip or encoded_cookies,
|
||||
'Cookie is not the same as round trip')
|
||||
ydl.__dict__['_YoutubeDL__header_cookies'] = []
|
||||
|
||||
with self.subTest(msg=encoded_cookies):
|
||||
if not error:
|
||||
_test()
|
||||
return
|
||||
with self.assertRaisesRegex(Exception, error):
|
||||
_test()
|
||||
|
||||
test('test=value; Domain=.yt.dlp', [cookie('test', 'value', domain='.yt.dlp')])
|
||||
test('test=value', [cookie('test', 'value')], error='Unscoped cookies are not allowed')
|
||||
test('cookie1=value1; Domain=.yt.dlp; Path=/test; cookie2=value2; Domain=.yt.dlp; Path=/', [
|
||||
cookie('cookie1', 'value1', domain='.yt.dlp', path='/test'),
|
||||
cookie('cookie2', 'value2', domain='.yt.dlp', path='/')])
|
||||
test('test=value; Domain=.yt.dlp; Path=/test; Secure; Expires=9999999999', [
|
||||
cookie('test', 'value', domain='.yt.dlp', path='/test', secure=True, expires=9999999999)])
|
||||
test('test="value; "; path=/test; domain=.yt.dlp', [
|
||||
cookie('test', 'value; ', domain='.yt.dlp', path='/test')],
|
||||
round_trip='test="value\\073 "; Domain=.yt.dlp; Path=/test')
|
||||
test('name=; Domain=.yt.dlp', [cookie('name', '', domain='.yt.dlp')],
|
||||
round_trip='name=""; Domain=.yt.dlp')
|
||||
|
||||
test('test=value', [cookie('test', 'value', domain='.yt.dlp')], headers=True)
|
||||
test('cookie1=value; Domain=.yt.dlp; cookie2=value', [], headers=True, error='Invalid syntax')
|
||||
ydl.deprecated_feature = ydl.report_error
|
||||
test('test=value', [], headers=True, error='Passing cookies as a header is a potential security risk')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
133
test/test_downloader_external.py
Normal file
133
test/test_downloader_external.py
Normal file
@@ -0,0 +1,133 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
import http.cookiejar
|
||||
|
||||
from test.helper import FakeYDL
|
||||
from yt_dlp.downloader.external import (
|
||||
Aria2cFD,
|
||||
AxelFD,
|
||||
CurlFD,
|
||||
FFmpegFD,
|
||||
HttpieFD,
|
||||
WgetFD,
|
||||
)
|
||||
|
||||
TEST_COOKIE = {
|
||||
'version': 0,
|
||||
'name': 'test',
|
||||
'value': 'ytdlp',
|
||||
'port': None,
|
||||
'port_specified': False,
|
||||
'domain': '.example.com',
|
||||
'domain_specified': True,
|
||||
'domain_initial_dot': False,
|
||||
'path': '/',
|
||||
'path_specified': True,
|
||||
'secure': False,
|
||||
'expires': None,
|
||||
'discard': False,
|
||||
'comment': None,
|
||||
'comment_url': None,
|
||||
'rest': {},
|
||||
}
|
||||
|
||||
TEST_INFO = {'url': 'http://www.example.com/'}
|
||||
|
||||
|
||||
class TestHttpieFD(unittest.TestCase):
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = HttpieFD(ydl, {})
|
||||
self.assertEqual(
|
||||
downloader._make_cmd('test', TEST_INFO),
|
||||
['http', '--download', '--output', 'test', 'http://www.example.com/'])
|
||||
|
||||
# Test cookie header is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
self.assertEqual(
|
||||
downloader._make_cmd('test', TEST_INFO),
|
||||
['http', '--download', '--output', 'test', 'http://www.example.com/', 'Cookie:test=ytdlp'])
|
||||
|
||||
|
||||
class TestAxelFD(unittest.TestCase):
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = AxelFD(ydl, {})
|
||||
self.assertEqual(
|
||||
downloader._make_cmd('test', TEST_INFO),
|
||||
['axel', '-o', 'test', '--', 'http://www.example.com/'])
|
||||
|
||||
# Test cookie header is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
self.assertEqual(
|
||||
downloader._make_cmd('test', TEST_INFO),
|
||||
['axel', '-o', 'test', 'Cookie: test=ytdlp', '--max-redirect=0', '--', 'http://www.example.com/'])
|
||||
|
||||
|
||||
class TestWgetFD(unittest.TestCase):
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = WgetFD(ydl, {})
|
||||
self.assertNotIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
|
||||
# Test cookiejar tempfile arg is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
self.assertIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
|
||||
|
||||
|
||||
class TestCurlFD(unittest.TestCase):
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = CurlFD(ydl, {})
|
||||
self.assertNotIn('--cookie-jar', downloader._make_cmd('test', TEST_INFO))
|
||||
# Test cookiejar tempfile arg is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
self.assertIn('--cookie-jar', downloader._make_cmd('test', TEST_INFO))
|
||||
|
||||
|
||||
class TestAria2cFD(unittest.TestCase):
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = Aria2cFD(ydl, {})
|
||||
downloader._make_cmd('test', TEST_INFO)
|
||||
self.assertFalse(hasattr(downloader, '_cookies_tempfile'))
|
||||
|
||||
# Test cookiejar tempfile arg is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
cmd = downloader._make_cmd('test', TEST_INFO)
|
||||
self.assertIn(f'--load-cookies={downloader._cookies_tempfile}', cmd)
|
||||
|
||||
|
||||
@unittest.skipUnless(FFmpegFD.available(), 'ffmpeg not found')
|
||||
class TestFFmpegFD(unittest.TestCase):
|
||||
_args = []
|
||||
|
||||
def _test_cmd(self, args):
|
||||
self._args = args
|
||||
|
||||
def test_make_cmd(self):
|
||||
with FakeYDL() as ydl:
|
||||
downloader = FFmpegFD(ydl, {})
|
||||
downloader._debug_cmd = self._test_cmd
|
||||
|
||||
downloader._call_downloader('test', {**TEST_INFO, 'ext': 'mp4'})
|
||||
self.assertEqual(self._args, [
|
||||
'ffmpeg', '-y', '-hide_banner', '-i', 'http://www.example.com/',
|
||||
'-c', 'copy', '-f', 'mp4', 'file:test'])
|
||||
|
||||
# Test cookies arg is added
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(**TEST_COOKIE))
|
||||
downloader._call_downloader('test', {**TEST_INFO, 'ext': 'mp4'})
|
||||
self.assertEqual(self._args, [
|
||||
'ffmpeg', '-y', '-hide_banner', '-cookies', 'test=ytdlp; path=/; domain=.example.com;\r\n',
|
||||
'-i', 'http://www.example.com/', '-c', 'copy', '-f', 'mp4', 'file:test'])
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@@ -132,6 +132,11 @@ def do_GET(self):
|
||||
self._method('GET')
|
||||
elif self.path.startswith('/headers'):
|
||||
self._headers()
|
||||
elif self.path.startswith('/308-to-headers'):
|
||||
self.send_response(308)
|
||||
self.send_header('Location', '/headers')
|
||||
self.send_header('Content-Length', '0')
|
||||
self.end_headers()
|
||||
elif self.path == '/trailing_garbage':
|
||||
payload = b'<html><video src="/vid.mp4" /></html>'
|
||||
self.send_response(200)
|
||||
@@ -270,6 +275,7 @@ def do_req(redirect_status, method):
|
||||
self.assertEqual(do_req(303, 'PUT'), ('', 'GET'))
|
||||
|
||||
# 301 and 302 turn POST only into a GET
|
||||
# XXX: we should also test if the Content-Type and Content-Length headers are removed
|
||||
self.assertEqual(do_req(301, 'POST'), ('', 'GET'))
|
||||
self.assertEqual(do_req(301, 'HEAD'), ('', 'HEAD'))
|
||||
self.assertEqual(do_req(302, 'POST'), ('', 'GET'))
|
||||
@@ -313,6 +319,31 @@ def test_cookiejar(self):
|
||||
data = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
|
||||
self.assertIn(b'Cookie: test=ytdlp', data)
|
||||
|
||||
def test_passed_cookie_header(self):
|
||||
# We should accept a Cookie header being passed as in normal headers and handle it appropriately.
|
||||
with FakeYDL() as ydl:
|
||||
# Specified Cookie header should be used
|
||||
res = ydl.urlopen(
|
||||
sanitized_Request(f'http://127.0.0.1:{self.http_port}/headers',
|
||||
headers={'Cookie': 'test=test'})).read().decode('utf-8')
|
||||
self.assertIn('Cookie: test=test', res)
|
||||
|
||||
# Specified Cookie header should be removed on any redirect
|
||||
res = ydl.urlopen(
|
||||
sanitized_Request(f'http://127.0.0.1:{self.http_port}/308-to-headers', headers={'Cookie': 'test=test'})).read().decode('utf-8')
|
||||
self.assertNotIn('Cookie: test=test', res)
|
||||
|
||||
# Specified Cookie header should override global cookiejar for that request
|
||||
ydl.cookiejar.set_cookie(http.cookiejar.Cookie(
|
||||
version=0, name='test', value='ytdlp', port=None, port_specified=False,
|
||||
domain='127.0.0.1', domain_specified=True, domain_initial_dot=False, path='/',
|
||||
path_specified=True, secure=False, expires=None, discard=False, comment=None,
|
||||
comment_url=None, rest={}))
|
||||
|
||||
data = ydl.urlopen(sanitized_Request(f'http://127.0.0.1:{self.http_port}/headers', headers={'Cookie': 'test=test'})).read()
|
||||
self.assertNotIn(b'Cookie: test=ytdlp', data)
|
||||
self.assertIn(b'Cookie: test=test', data)
|
||||
|
||||
def test_no_compression_compat_header(self):
|
||||
with FakeYDL() as ydl:
|
||||
data = ydl.urlopen(
|
||||
|
||||
@@ -1,9 +1,11 @@
|
||||
import collections
|
||||
import contextlib
|
||||
import copy
|
||||
import datetime
|
||||
import errno
|
||||
import fileinput
|
||||
import functools
|
||||
import http.cookiejar
|
||||
import io
|
||||
import itertools
|
||||
import json
|
||||
@@ -25,7 +27,7 @@
|
||||
from .cache import Cache
|
||||
from .compat import urllib # isort: split
|
||||
from .compat import compat_os_name, compat_shlex_quote
|
||||
from .cookies import load_cookies
|
||||
from .cookies import LenientSimpleCookie, load_cookies
|
||||
from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
|
||||
from .downloader.rtmp import rtmpdump_version
|
||||
from .extractor import gen_extractor_classes, get_info_extractor
|
||||
@@ -673,6 +675,9 @@ def process_color_policy(stream):
|
||||
if auto_init and auto_init != 'no_verbose_header':
|
||||
self.print_debug_header()
|
||||
|
||||
self.__header_cookies = []
|
||||
self._load_cookies(traverse_obj(self.params.get('http_headers'), 'cookie', casesense=False)) # compat
|
||||
|
||||
def check_deprecated(param, option, suggestion):
|
||||
if self.params.get(param) is not None:
|
||||
self.report_warning(f'{option} is deprecated. Use {suggestion} instead')
|
||||
@@ -983,6 +988,7 @@ def trouble(self, message=None, tb=None, is_error=True):
|
||||
ID='green',
|
||||
DELIM='blue',
|
||||
ERROR='red',
|
||||
BAD_FORMAT='light red',
|
||||
WARNING='yellow',
|
||||
SUPPRESS='light black',
|
||||
)
|
||||
@@ -1271,21 +1277,20 @@ def create_key(outer_mobj):
|
||||
return outer_mobj.group(0)
|
||||
key = outer_mobj.group('key')
|
||||
mobj = re.match(INTERNAL_FORMAT_RE, key)
|
||||
initial_field = mobj.group('fields') if mobj else ''
|
||||
value, replacement, default = None, None, na
|
||||
value, replacement, default, last_field = None, None, na, ''
|
||||
while mobj:
|
||||
mobj = mobj.groupdict()
|
||||
default = mobj['default'] if mobj['default'] is not None else default
|
||||
value = get_value(mobj)
|
||||
replacement = mobj['replacement']
|
||||
last_field, replacement = mobj['fields'], mobj['replacement']
|
||||
if value is None and mobj['alternate']:
|
||||
mobj = re.match(INTERNAL_FORMAT_RE, mobj['remaining'][1:])
|
||||
else:
|
||||
break
|
||||
|
||||
fmt = outer_mobj.group('format')
|
||||
if fmt == 's' and value is not None and key in field_size_compat_map.keys():
|
||||
fmt = f'0{field_size_compat_map[key]:d}d'
|
||||
if fmt == 's' and value is not None and last_field in field_size_compat_map.keys():
|
||||
fmt = f'0{field_size_compat_map[last_field]:d}d'
|
||||
|
||||
if None not in (value, replacement):
|
||||
try:
|
||||
@@ -1322,7 +1327,7 @@ def create_key(outer_mobj):
|
||||
value = format_decimal_suffix(value, f'%{num_fmt}f%s' if num_fmt else '%d%s',
|
||||
factor=1024 if '#' in flags else 1000)
|
||||
elif fmt[-1] == 'S': # filename sanitization
|
||||
value, fmt = filename_sanitizer(initial_field, value, restricted='#' in flags), str_fmt
|
||||
value, fmt = filename_sanitizer(last_field, value, restricted='#' in flags), str_fmt
|
||||
elif fmt[-1] == 'c':
|
||||
if value:
|
||||
value = str(value)[0]
|
||||
@@ -1341,7 +1346,7 @@ def create_key(outer_mobj):
|
||||
elif fmt[-1] == 'a':
|
||||
value, fmt = ascii(value), str_fmt
|
||||
if fmt[-1] in 'csra':
|
||||
value = sanitizer(initial_field, value)
|
||||
value = sanitizer(last_field, value)
|
||||
|
||||
key = '%s\0%s' % (key.replace('%', '%\0'), outer_mobj.group('format'))
|
||||
TMPL_DICT[key] = value
|
||||
@@ -1625,8 +1630,60 @@ def progress(msg):
|
||||
self.to_screen('')
|
||||
raise
|
||||
|
||||
def _load_cookies(self, data, *, from_headers=True):
|
||||
"""Loads cookies from a `Cookie` header
|
||||
|
||||
This tries to work around the security vulnerability of passing cookies to every domain.
|
||||
See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
|
||||
The unscoped cookies are saved for later to be stored in the jar with a limited scope.
|
||||
|
||||
@param data The Cookie header as string to load the cookies from
|
||||
@param from_headers If `False`, allows Set-Cookie syntax in the cookie string (at least a domain will be required)
|
||||
"""
|
||||
for cookie in LenientSimpleCookie(data).values():
|
||||
if from_headers and any(cookie.values()):
|
||||
raise ValueError('Invalid syntax in Cookie Header')
|
||||
|
||||
domain = cookie.get('domain') or ''
|
||||
expiry = cookie.get('expires')
|
||||
if expiry == '': # 0 is valid
|
||||
expiry = None
|
||||
prepared_cookie = http.cookiejar.Cookie(
|
||||
cookie.get('version') or 0, cookie.key, cookie.value, None, False,
|
||||
domain, True, True, cookie.get('path') or '', bool(cookie.get('path')),
|
||||
cookie.get('secure') or False, expiry, False, None, None, {})
|
||||
|
||||
if domain:
|
||||
self.cookiejar.set_cookie(prepared_cookie)
|
||||
elif from_headers:
|
||||
self.deprecated_feature(
|
||||
'Passing cookies as a header is a potential security risk; '
|
||||
'they will be scoped to the domain of the downloaded urls. '
|
||||
'Please consider loading cookies from a file or browser instead.')
|
||||
self.__header_cookies.append(prepared_cookie)
|
||||
else:
|
||||
self.report_error('Unscoped cookies are not allowed; please specify some sort of scoping',
|
||||
tb=False, is_error=False)
|
||||
|
||||
def _apply_header_cookies(self, url):
|
||||
"""Applies stray header cookies to the provided url
|
||||
|
||||
This loads header cookies and scopes them to the domain provided in `url`.
|
||||
While this is not ideal, it helps reduce the risk of them being sent
|
||||
to an unintended destination while mostly maintaining compatibility.
|
||||
"""
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
if not parsed.hostname:
|
||||
return
|
||||
|
||||
for cookie in map(copy.copy, self.__header_cookies):
|
||||
cookie.domain = f'.{parsed.hostname}'
|
||||
self.cookiejar.set_cookie(cookie)
|
||||
|
||||
@_handle_extraction_exceptions
|
||||
def __extract_info(self, url, ie, download, extra_info, process):
|
||||
self._apply_header_cookies(url)
|
||||
|
||||
try:
|
||||
ie_result = ie.extract(url)
|
||||
except UserNotLive as e:
|
||||
@@ -2086,8 +2143,6 @@ def syntax_error(note, start):
|
||||
allow_multiple_streams = {'audio': self.params.get('allow_multiple_audio_streams', False),
|
||||
'video': self.params.get('allow_multiple_video_streams', False)}
|
||||
|
||||
check_formats = self.params.get('check_formats') == 'selected'
|
||||
|
||||
def _parse_filter(tokens):
|
||||
filter_parts = []
|
||||
for type, string_, start, _, _ in tokens:
|
||||
@@ -2260,10 +2315,19 @@ def _merge(formats_pair):
|
||||
return new_dict
|
||||
|
||||
def _check_formats(formats):
|
||||
if not check_formats:
|
||||
if (self.params.get('check_formats') is not None
|
||||
or self.params.get('allow_unplayable_formats')):
|
||||
yield from formats
|
||||
return
|
||||
yield from self._check_formats(formats)
|
||||
elif self.params.get('check_formats') == 'selected':
|
||||
yield from self._check_formats(formats)
|
||||
return
|
||||
|
||||
for f in formats:
|
||||
if f.get('has_drm'):
|
||||
yield from self._check_formats([f])
|
||||
else:
|
||||
yield f
|
||||
|
||||
def _build_selector_function(selector):
|
||||
if isinstance(selector, list): # ,
|
||||
@@ -2407,9 +2471,24 @@ def _calc_headers(self, info_dict):
|
||||
if 'Youtubedl-No-Compression' in res: # deprecated
|
||||
res.pop('Youtubedl-No-Compression', None)
|
||||
res['Accept-Encoding'] = 'identity'
|
||||
cookies = self.cookiejar.get_cookie_header(info_dict['url'])
|
||||
cookies = self.cookiejar.get_cookies_for_url(info_dict['url'])
|
||||
if cookies:
|
||||
res['Cookie'] = cookies
|
||||
encoder = LenientSimpleCookie()
|
||||
values = []
|
||||
for cookie in cookies:
|
||||
_, value = encoder.value_encode(cookie.value)
|
||||
values.append(f'{cookie.name}={value}')
|
||||
if cookie.domain:
|
||||
values.append(f'Domain={cookie.domain}')
|
||||
if cookie.path:
|
||||
values.append(f'Path={cookie.path}')
|
||||
if cookie.secure:
|
||||
values.append('Secure')
|
||||
if cookie.expires:
|
||||
values.append(f'Expires={cookie.expires}')
|
||||
if cookie.version:
|
||||
values.append(f'Version={cookie.version}')
|
||||
info_dict['cookies'] = '; '.join(values)
|
||||
|
||||
if 'X-Forwarded-For' not in res:
|
||||
x_forwarded_for_ip = info_dict.get('__x_forwarded_for_ip')
|
||||
@@ -2615,10 +2694,10 @@ def sanitize_numeric_fields(info):
|
||||
if field_preference:
|
||||
info_dict['_format_sort_fields'] = field_preference
|
||||
|
||||
# or None ensures --clean-infojson removes it
|
||||
info_dict['_has_drm'] = any(f.get('has_drm') for f in formats) or None
|
||||
info_dict['_has_drm'] = any( # or None ensures --clean-infojson removes it
|
||||
f.get('has_drm') and f['has_drm'] != 'maybe' for f in formats) or None
|
||||
if not self.params.get('allow_unplayable_formats'):
|
||||
formats = [f for f in formats if not f.get('has_drm')]
|
||||
formats = [f for f in formats if not f.get('has_drm') or f['has_drm'] == 'maybe']
|
||||
|
||||
if formats and all(f.get('acodec') == f.get('vcodec') == 'none' for f in formats):
|
||||
self.report_warning(
|
||||
@@ -2767,11 +2846,8 @@ def is_wellformed(f):
|
||||
formats_to_download = list(format_selector({
|
||||
'formats': formats,
|
||||
'has_merged_format': any('none' not in (f.get('acodec'), f.get('vcodec')) for f in formats),
|
||||
'incomplete_formats': (
|
||||
# All formats are video-only or
|
||||
all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats)
|
||||
# all formats are audio-only
|
||||
or all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats)),
|
||||
'incomplete_formats': (all(f.get('vcodec') == 'none' for f in formats) # No formats with video
|
||||
or all(f.get('acodec') == 'none' for f in formats)), # OR, No formats with audio
|
||||
}))
|
||||
if interactive_format_selection and not formats_to_download:
|
||||
self.report_error('Requested format is not available', tb=False, is_error=False)
|
||||
@@ -3419,6 +3495,8 @@ def download_with_info_file(self, info_filename):
|
||||
infos = [self.sanitize_info(info, self.params.get('clean_infojson', True))
|
||||
for info in variadic(json.loads('\n'.join(f)))]
|
||||
for info in infos:
|
||||
self._load_cookies(info.get('cookies'), from_headers=False)
|
||||
self._load_cookies(traverse_obj(info.get('http_headers'), 'Cookie', casesense=False)) # compat
|
||||
try:
|
||||
self.__download_wrapper(self.process_ie_result)(info, download=True)
|
||||
except (DownloadError, EntryNotInPlaylist, ReExtractInfo) as e:
|
||||
@@ -3688,7 +3766,7 @@ def render_formats_table(self, info_dict):
|
||||
|
||||
def simplified_codec(f, field):
|
||||
assert field in ('acodec', 'vcodec')
|
||||
codec = f.get(field, 'unknown')
|
||||
codec = f.get(field)
|
||||
if not codec:
|
||||
return 'unknown'
|
||||
elif codec != 'none':
|
||||
@@ -3723,14 +3801,13 @@ def simplified_codec(f, field):
|
||||
simplified_codec(f, 'acodec'),
|
||||
format_field(f, 'abr', '\t%dk', func=round),
|
||||
format_field(f, 'asr', '\t%s', func=format_decimal_suffix),
|
||||
join_nonempty(
|
||||
self._format_out('UNSUPPORTED', 'light red') if f.get('ext') in ('f4f', 'f4m') else None,
|
||||
self._format_out('DRM', 'light red') if f.get('has_drm') else None,
|
||||
format_field(f, 'language', '[%s]'),
|
||||
join_nonempty(format_field(f, 'format_note'),
|
||||
format_field(f, 'container', ignore=(None, f.get('ext'))),
|
||||
delim=', '),
|
||||
delim=' '),
|
||||
join_nonempty(format_field(f, 'language', '[%s]'), join_nonempty(
|
||||
self._format_out('UNSUPPORTED', self.Styles.BAD_FORMAT) if f.get('ext') in ('f4f', 'f4m') else None,
|
||||
(self._format_out('Maybe DRM', self.Styles.WARNING) if f.get('has_drm') == 'maybe'
|
||||
else self._format_out('DRM', self.Styles.BAD_FORMAT) if f.get('has_drm') else None),
|
||||
format_field(f, 'format_note'),
|
||||
format_field(f, 'container', ignore=(None, f.get('ext'))),
|
||||
delim=', '), delim=' '),
|
||||
] for f in formats if f.get('preference') is None or f['preference'] >= -1000]
|
||||
header_line = self._list_format_headers(
|
||||
'ID', 'EXT', 'RESOLUTION', '\tFPS', 'HDR', 'CH', delim, '\tFILESIZE', '\tTBR', 'PROTO',
|
||||
|
||||
@@ -1327,6 +1327,13 @@ def get_cookie_header(self, url):
|
||||
self.add_cookie_header(cookie_req)
|
||||
return cookie_req.get_header('Cookie')
|
||||
|
||||
def get_cookies_for_url(self, url):
|
||||
"""Generate a list of Cookie objects for a given url"""
|
||||
# Policy `_now` attribute must be set before calling `_cookies_for_request`
|
||||
# Ref: https://github.com/python/cpython/blob/3.7/Lib/http/cookiejar.py#L1360
|
||||
self._policy._now = self._now = int(time.time())
|
||||
return self._cookies_for_request(urllib.request.Request(escape_url(sanitize_url(url))))
|
||||
|
||||
def clear(self, *args, **kwargs):
|
||||
with contextlib.suppress(KeyError):
|
||||
return super().clear(*args, **kwargs)
|
||||
|
||||
@@ -32,6 +32,7 @@
|
||||
timetuple_from_msec,
|
||||
try_call,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FileDownloader:
|
||||
@@ -255,7 +256,8 @@ def sanitize_open(self, filename, open_mode):
|
||||
|
||||
@wrap_file_access('remove')
|
||||
def try_remove(self, filename):
|
||||
os.remove(filename)
|
||||
if os.path.isfile(filename):
|
||||
os.remove(filename)
|
||||
|
||||
@wrap_file_access('rename')
|
||||
def try_rename(self, old_filename, new_filename):
|
||||
@@ -418,7 +420,6 @@ def download(self, filename, info_dict, subtitle=False):
|
||||
"""Download to a filename using the info from info_dict
|
||||
Return True on success and False otherwise
|
||||
"""
|
||||
|
||||
nooverwrites_and_exists = (
|
||||
not self.params.get('overwrites', True)
|
||||
and os.path.exists(encodeFilename(filename))
|
||||
@@ -452,6 +453,11 @@ def download(self, filename, info_dict, subtitle=False):
|
||||
self.to_screen(f'[download] Sleeping {sleep_interval:.2f} seconds ...')
|
||||
time.sleep(sleep_interval)
|
||||
|
||||
# Filter the `Cookie` header from the info_dict to prevent leaks.
|
||||
# See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
|
||||
info_dict['http_headers'] = dict(traverse_obj(info_dict, (
|
||||
'http_headers', {dict.items}, lambda _, pair: pair[0].lower() != 'cookie'))) or None
|
||||
|
||||
ret = self.real_download(filename, info_dict)
|
||||
self._finish_multiline_status()
|
||||
return ret, True
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
import enum
|
||||
import json
|
||||
import os.path
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
import uuid
|
||||
|
||||
@@ -42,6 +43,7 @@ class ExternalFD(FragmentFD):
|
||||
def real_download(self, filename, info_dict):
|
||||
self.report_destination(filename)
|
||||
tmpfilename = self.temp_name(filename)
|
||||
self._cookies_tempfile = None
|
||||
|
||||
try:
|
||||
started = time.time()
|
||||
@@ -54,6 +56,9 @@ def real_download(self, filename, info_dict):
|
||||
# should take place
|
||||
retval = 0
|
||||
self.to_screen('[%s] Interrupted by user' % self.get_basename())
|
||||
finally:
|
||||
if self._cookies_tempfile:
|
||||
self.try_remove(self._cookies_tempfile)
|
||||
|
||||
if retval == 0:
|
||||
status = {
|
||||
@@ -125,6 +130,16 @@ def _configuration_args(self, keys=None, *args, **kwargs):
|
||||
self.get_basename(), self.params.get('external_downloader_args'), self.EXE_NAME,
|
||||
keys, *args, **kwargs)
|
||||
|
||||
def _write_cookies(self):
|
||||
if not self.ydl.cookiejar.filename:
|
||||
tmp_cookies = tempfile.NamedTemporaryFile(suffix='.cookies', delete=False)
|
||||
tmp_cookies.close()
|
||||
self._cookies_tempfile = tmp_cookies.name
|
||||
self.to_screen(f'[download] Writing temporary cookies file to "{self._cookies_tempfile}"')
|
||||
# real_download resets _cookies_tempfile; if it's None then save() will write to cookiejar.filename
|
||||
self.ydl.cookiejar.save(self._cookies_tempfile)
|
||||
return self.ydl.cookiejar.filename or self._cookies_tempfile
|
||||
|
||||
def _call_downloader(self, tmpfilename, info_dict):
|
||||
""" Either overwrite this or implement _make_cmd """
|
||||
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
|
||||
@@ -184,6 +199,8 @@ class CurlFD(ExternalFD):
|
||||
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [self.exe, '--location', '-o', tmpfilename, '--compressed']
|
||||
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
|
||||
cmd += ['--cookie-jar', self._write_cookies()]
|
||||
if info_dict.get('http_headers') is not None:
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', f'{key}: {val}']
|
||||
@@ -214,6 +231,9 @@ def _make_cmd(self, tmpfilename, info_dict):
|
||||
if info_dict.get('http_headers') is not None:
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['-H', f'{key}: {val}']
|
||||
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
|
||||
if cookie_header:
|
||||
cmd += [f'Cookie: {cookie_header}', '--max-redirect=0']
|
||||
cmd += self._configuration_args()
|
||||
cmd += ['--', info_dict['url']]
|
||||
return cmd
|
||||
@@ -223,7 +243,9 @@ class WgetFD(ExternalFD):
|
||||
AVAILABLE_OPT = '--version'
|
||||
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies', '--compression=auto']
|
||||
cmd = [self.exe, '-O', tmpfilename, '-nv', '--compression=auto']
|
||||
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
|
||||
cmd += ['--load-cookies', self._write_cookies()]
|
||||
if info_dict.get('http_headers') is not None:
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', f'{key}: {val}']
|
||||
@@ -271,7 +293,7 @@ def _call_downloader(self, tmpfilename, info_dict):
|
||||
return super()._call_downloader(tmpfilename, info_dict)
|
||||
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [self.exe, '-c',
|
||||
cmd = [self.exe, '-c', '--no-conf',
|
||||
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
|
||||
'--http-accept-gzip=true', '--file-allocation=none', '-x16', '-j16', '-s16']
|
||||
if 'fragments' in info_dict:
|
||||
@@ -279,6 +301,8 @@ def _make_cmd(self, tmpfilename, info_dict):
|
||||
else:
|
||||
cmd += ['--min-split-size', '1M']
|
||||
|
||||
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
|
||||
cmd += [f'--load-cookies={self._write_cookies()}']
|
||||
if info_dict.get('http_headers') is not None:
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', f'{key}: {val}']
|
||||
@@ -417,6 +441,14 @@ def _make_cmd(self, tmpfilename, info_dict):
|
||||
if info_dict.get('http_headers') is not None:
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += [f'{key}:{val}']
|
||||
|
||||
# httpie 3.1.0+ removes the Cookie header on redirect, so this should be safe for now. [1]
|
||||
# If we ever need cookie handling for redirects, we can export the cookiejar into a session. [2]
|
||||
# 1: https://github.com/httpie/httpie/security/advisories/GHSA-9w4w-cpc8-h2fq
|
||||
# 2: https://httpie.io/docs/cli/sessions
|
||||
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
|
||||
if cookie_header:
|
||||
cmd += [f'Cookie:{cookie_header}']
|
||||
return cmd
|
||||
|
||||
|
||||
@@ -527,6 +559,11 @@ def _call_downloader(self, tmpfilename, info_dict):
|
||||
|
||||
selected_formats = info_dict.get('requested_formats') or [info_dict]
|
||||
for i, fmt in enumerate(selected_formats):
|
||||
cookies = self.ydl.cookiejar.get_cookies_for_url(fmt['url'])
|
||||
if cookies:
|
||||
args.extend(['-cookies', ''.join(
|
||||
f'{cookie.name}={cookie.value}; path={cookie.path}; domain={cookie.domain};\r\n'
|
||||
for cookie in cookies)])
|
||||
if fmt.get('http_headers') and re.match(r'^https?://', fmt['url']):
|
||||
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
|
||||
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
|
||||
|
||||
@@ -300,9 +300,7 @@ def frag_progress_hook(s):
|
||||
def _finish_frag_download(self, ctx, info_dict):
|
||||
ctx['dest_stream'].close()
|
||||
if self.__do_ytdl_file(ctx):
|
||||
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
|
||||
if os.path.isfile(ytdl_filename):
|
||||
self.try_remove(ytdl_filename)
|
||||
self.try_remove(self.ytdl_filename(ctx['filename']))
|
||||
elapsed = time.time() - ctx['started']
|
||||
|
||||
to_file = ctx['tmpfilename'] != '-'
|
||||
|
||||
@@ -28,7 +28,16 @@ class HlsFD(FragmentFD):
|
||||
FD_NAME = 'hlsnative'
|
||||
|
||||
@staticmethod
|
||||
def can_download(manifest, info_dict, allow_unplayable_formats=False):
|
||||
def _has_drm(manifest): # TODO: https://github.com/yt-dlp/yt-dlp/pull/5039
|
||||
return bool(re.search('|'.join((
|
||||
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
|
||||
r'#EXT-X-(?:SESSION-)?KEY:.*?KEYFORMAT="com\.apple\.streamingkeydelivery"', # Apple FairPlay
|
||||
r'#EXT-X-(?:SESSION-)?KEY:.*?KEYFORMAT="com\.microsoft\.playready"', # Microsoft PlayReady
|
||||
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
|
||||
)), manifest))
|
||||
|
||||
@classmethod
|
||||
def can_download(cls, manifest, info_dict, allow_unplayable_formats=False):
|
||||
UNSUPPORTED_FEATURES = [
|
||||
# r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
|
||||
|
||||
@@ -50,13 +59,15 @@ def can_download(manifest, info_dict, allow_unplayable_formats=False):
|
||||
]
|
||||
if not allow_unplayable_formats:
|
||||
UNSUPPORTED_FEATURES += [
|
||||
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
|
||||
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1], but not necessarily DRM
|
||||
]
|
||||
|
||||
def check_results():
|
||||
yield not info_dict.get('is_live')
|
||||
for feature in UNSUPPORTED_FEATURES:
|
||||
yield not re.search(feature, manifest)
|
||||
if not allow_unplayable_formats:
|
||||
yield not cls._has_drm(manifest)
|
||||
return all(check_results())
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
@@ -81,14 +92,13 @@ def real_download(self, filename, info_dict):
|
||||
message = ('Live HLS streams are not supported by the native downloader. If this is a livestream, '
|
||||
f'please {install_ffmpeg}add "--downloader ffmpeg --hls-use-mpegts" to your command')
|
||||
if not can_download:
|
||||
has_drm = re.search('|'.join([
|
||||
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
|
||||
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
|
||||
]), s)
|
||||
if has_drm and not self.params.get('allow_unplayable_formats'):
|
||||
self.report_error(
|
||||
'This video is DRM protected; Try selecting another format with --format or '
|
||||
'add --check-formats to automatically fallback to the next best format')
|
||||
if self._has_drm(s) and not self.params.get('allow_unplayable_formats'):
|
||||
if info_dict.get('has_drm') and self.params.get('test'):
|
||||
self.to_screen(f'[{self.FD_NAME}] This format is DRM protected', skip_eol=True)
|
||||
else:
|
||||
self.report_error(
|
||||
'This format is DRM protected; Try selecting another format with --format or '
|
||||
'add --check-formats to automatically fallback to the next best format', tb=False)
|
||||
return False
|
||||
message = message or 'Unsupported features have been detected'
|
||||
fd = FFmpegFD(self.ydl, self.params)
|
||||
|
||||
@@ -339,15 +339,15 @@ def retry(e):
|
||||
elif speed:
|
||||
ctx.throttle_start = None
|
||||
|
||||
if not is_test and ctx.chunk_size and ctx.content_len is not None and byte_counter < ctx.content_len:
|
||||
ctx.resume_len = byte_counter
|
||||
# ctx.block_size = block_size
|
||||
raise NextFragment()
|
||||
|
||||
if ctx.stream is None:
|
||||
self.to_stderr('\n')
|
||||
self.report_error('Did not get any data blocks')
|
||||
return False
|
||||
|
||||
if not is_test and ctx.chunk_size and ctx.content_len is not None and byte_counter < ctx.content_len:
|
||||
ctx.resume_len = byte_counter
|
||||
raise NextFragment()
|
||||
|
||||
if ctx.tmpfilename != '-':
|
||||
ctx.stream.close()
|
||||
|
||||
|
||||
@@ -15,7 +15,6 @@
|
||||
YoutubeSearchURLIE,
|
||||
YoutubeMusicSearchURLIE,
|
||||
YoutubeSubscriptionsIE,
|
||||
YoutubeStoriesIE,
|
||||
YoutubeTruncatedIDIE,
|
||||
YoutubeTruncatedURLIE,
|
||||
YoutubeYtBeIE,
|
||||
@@ -1531,6 +1530,7 @@
|
||||
)
|
||||
from .puls4 import Puls4IE
|
||||
from .pyvideo import PyvideoIE
|
||||
from .qdance import QDanceIE
|
||||
from .qingting import QingTingIE
|
||||
from .qqmusic import (
|
||||
QQMusicIE,
|
||||
@@ -1854,6 +1854,10 @@
|
||||
SRGSSRPlayIE,
|
||||
)
|
||||
from .srmediathek import SRMediathekIE
|
||||
from .stacommu import (
|
||||
StacommuLiveIE,
|
||||
StacommuVODIE,
|
||||
)
|
||||
from .stanfordoc import StanfordOpenClassroomIE
|
||||
from .startv import StarTVIE
|
||||
from .steam import (
|
||||
@@ -2267,6 +2271,8 @@
|
||||
VKIE,
|
||||
VKUserVideosIE,
|
||||
VKWallPostIE,
|
||||
VKPlayIE,
|
||||
VKPlayLiveIE,
|
||||
)
|
||||
from .vocaroo import VocarooIE
|
||||
from .vodlocker import VodlockerIE
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
update_url_query,
|
||||
@@ -85,6 +86,15 @@ class ABCIE(InfoExtractor):
|
||||
'uploader': 'Behind the News',
|
||||
'uploader_id': 'behindthenews',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540',
|
||||
'info_dict': {
|
||||
'id': '102520540',
|
||||
'title': 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus',
|
||||
'ext': 'mp4',
|
||||
'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
|
||||
'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -107,7 +117,7 @@ def _real_extract(self, url):
|
||||
video = True
|
||||
|
||||
if mobj is None:
|
||||
mobj = re.search(r'(?P<type>)"sources": (?P<json_data>\[[^\]]+\]),', webpage)
|
||||
mobj = re.search(r'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])', webpage)
|
||||
if mobj is None:
|
||||
mobj = re.search(
|
||||
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
|
||||
@@ -121,7 +131,8 @@ def _real_extract(self, url):
|
||||
urls_info = self._parse_json(
|
||||
mobj.group('json_data'), video_id, transform_source=js_to_json)
|
||||
youtube = mobj.group('type') == 'YouTube'
|
||||
video = mobj.group('type') == 'Video' or urls_info[0]['contentType'] == 'video/mp4'
|
||||
video = mobj.group('type') == 'Video' or traverse_obj(
|
||||
urls_info, (0, ('contentType', 'MIMEType')), get_all=False) == 'video/mp4'
|
||||
|
||||
if not isinstance(urls_info, list):
|
||||
urls_info = [urls_info]
|
||||
|
||||
@@ -1473,7 +1473,7 @@ def extract_redirect_url(html, url=None, fatal=False):
|
||||
elif 'automatically signed in with' in provider_redirect_page:
|
||||
# Seems like comcast is rolling up new way of automatically signing customers
|
||||
oauth_redirect_url = self._html_search_regex(
|
||||
r'continue:\s*"(https://oauth.xfinity.com/oauth/authorize\?.+)"', provider_redirect_page,
|
||||
r'continue:\s*"(https://oauth\.xfinity\.com/oauth/authorize\?.+)"', provider_redirect_page,
|
||||
'oauth redirect (signed)')
|
||||
# Just need to process the request. No useful data comes back
|
||||
self._download_webpage(oauth_redirect_url, video_id, 'Confirming auto login')
|
||||
|
||||
@@ -170,8 +170,10 @@ def _real_extract(self, url):
|
||||
continue
|
||||
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
|
||||
if ext == 'm3u8':
|
||||
info['formats'].extend(self._extract_m3u8_formats(
|
||||
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
info['formats'].extend(fmts)
|
||||
self._merge_subtitles(subs, target=info['subtitles'])
|
||||
elif ext == 'f4m':
|
||||
continue
|
||||
# info['formats'].extend(self._extract_f4m_formats(
|
||||
|
||||
@@ -26,6 +26,7 @@
|
||||
from ..compat import compat_etree_fromstring, compat_expanduser, compat_os_name
|
||||
from ..cookies import LenientSimpleCookie
|
||||
from ..downloader.f4m import get_base_url, remove_encrypted_media
|
||||
from ..downloader.hls import HlsFD
|
||||
from ..utils import (
|
||||
IDENTITY,
|
||||
JSON_LD_RE,
|
||||
@@ -224,7 +225,8 @@ class InfoExtractor:
|
||||
width : height ratio as float.
|
||||
* no_resume The server does not support resuming the
|
||||
(HTTP or RTMP) download. Boolean.
|
||||
* has_drm The format has DRM and cannot be downloaded. Boolean
|
||||
* has_drm True if the format has DRM and cannot be downloaded.
|
||||
'maybe' if the format may have DRM and has to be tested before download.
|
||||
* extra_param_to_segment_url A query string to append to each
|
||||
fragment's URL, or to update each existing query string
|
||||
with. Only applied by the native HLS/DASH downloaders.
|
||||
@@ -1979,11 +1981,7 @@ def _parse_m3u8_formats_and_subtitles(
|
||||
errnote=None, fatal=True, data=None, headers={}, query={},
|
||||
video_id=None):
|
||||
formats, subtitles = [], {}
|
||||
|
||||
has_drm = re.search('|'.join([
|
||||
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
|
||||
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
|
||||
]), m3u8_doc)
|
||||
has_drm = HlsFD._has_drm(m3u8_doc)
|
||||
|
||||
def format_url(url):
|
||||
return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url)
|
||||
|
||||
@@ -490,8 +490,21 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?crunchyroll\.com/
|
||||
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
|
||||
watch/(?P<type>concert|musicvideo)/(?P<id>\w{10})'''
|
||||
watch/(?P<type>concert|musicvideo)/(?P<id>\w+)'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
'id': 'MV5B02C79',
|
||||
'display_id': 'egaono-hana',
|
||||
'title': 'Egaono Hana',
|
||||
'track': 'Egaono Hana',
|
||||
'artist': 'Goose house',
|
||||
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
||||
'genre': ['J-Pop'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C',
|
||||
'info_dict': {
|
||||
'ext': 'mp4',
|
||||
@@ -519,11 +532,14 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE):
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
|
||||
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79/egaono-hana',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135/live-is-smile-always-364joker-at-yokohama-arena',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_API_ENDPOINT = 'music'
|
||||
|
||||
|
||||
@@ -5,7 +5,9 @@
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
get_element_by_class,
|
||||
get_element_html_by_id,
|
||||
int_or_none,
|
||||
lowercase_escape,
|
||||
try_get,
|
||||
@@ -34,6 +36,7 @@ class GoogleDriveIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny.mp4',
|
||||
'duration': 45,
|
||||
'thumbnail': 'https://drive.google.com/thumbnail?id=0ByeS4oOUV-49Zzh4R1J6R09zazQ',
|
||||
}
|
||||
}, {
|
||||
# video can't be watched anonymously due to view count limit reached,
|
||||
@@ -207,10 +210,10 @@ def get_value(key):
|
||||
'export': 'download',
|
||||
})
|
||||
|
||||
def request_source_file(source_url, kind):
|
||||
def request_source_file(source_url, kind, data=None):
|
||||
return self._request_webpage(
|
||||
source_url, video_id, note='Requesting %s file' % kind,
|
||||
errnote='Unable to request %s file' % kind, fatal=False)
|
||||
errnote='Unable to request %s file' % kind, fatal=False, data=data)
|
||||
urlh = request_source_file(source_url, 'source')
|
||||
if urlh:
|
||||
def add_source_format(urlh):
|
||||
@@ -237,14 +240,10 @@ def add_source_format(urlh):
|
||||
urlh, url, video_id, note='Downloading confirmation page',
|
||||
errnote='Unable to confirm download', fatal=False)
|
||||
if confirmation_webpage:
|
||||
confirm = self._search_regex(
|
||||
r'confirm=([^&"\']+)', confirmation_webpage,
|
||||
'confirmation code', default=None)
|
||||
if confirm:
|
||||
confirmed_source_url = update_url_query(source_url, {
|
||||
'confirm': confirm,
|
||||
})
|
||||
urlh = request_source_file(confirmed_source_url, 'confirmed source')
|
||||
confirmed_source_url = extract_attributes(
|
||||
get_element_html_by_id('download-form', confirmation_webpage) or '').get('action')
|
||||
if confirmed_source_url:
|
||||
urlh = request_source_file(confirmed_source_url, 'confirmed source', data=b'')
|
||||
if urlh and urlh.headers.get('Content-Disposition'):
|
||||
add_source_format(urlh)
|
||||
else:
|
||||
|
||||
@@ -527,7 +527,7 @@ def _extract_vms_player_js(self, webpage, video_id):
|
||||
if player_js_cache:
|
||||
return player_js_cache
|
||||
webpack_js_url = self._proto_relative_url(self._search_regex(
|
||||
r'<script src="((?:https?)?//stc.iqiyipic.com/_next/static/chunks/webpack-\w+\.js)"', webpage, 'webpack URL'))
|
||||
r'<script src="((?:https?:)?//stc\.iqiyipic\.com/_next/static/chunks/webpack-\w+\.js)"', webpage, 'webpack URL'))
|
||||
webpack_js = self._download_webpage(webpack_js_url, video_id, note='Downloading webpack JS', errnote='Unable to download webpack JS')
|
||||
webpack_map = self._search_json(
|
||||
r'["\']\s*\+\s*', webpack_js, 'JS locations', video_id,
|
||||
|
||||
@@ -30,7 +30,7 @@ def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, *
|
||||
|
||||
|
||||
class KickIE(KickBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w_]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://kick.com/yuppy',
|
||||
'info_dict': {
|
||||
|
||||
150
yt_dlp/extractor/qdance.py
Normal file
150
yt_dlp/extractor/qdance.py
Normal file
@@ -0,0 +1,150 @@
|
||||
import json
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
jwt_decode_hs256,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
try_call,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class QDanceIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'qdance'
|
||||
_VALID_URL = r'https?://(?:www\.)?q-dance\.com/network/(?:library|live)/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'note': 'vod',
|
||||
'url': 'https://www.q-dance.com/network/library/146542138',
|
||||
'info_dict': {
|
||||
'id': '146542138',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sound Rush [LIVE] | Defqon.1 Weekend Festival 2022 | Friday | RED',
|
||||
'display_id': 'sound-rush-live-v3-defqon-1-weekend-festival-2022-friday-red',
|
||||
'description': 'Relive Defqon.1 - Primal Energy 2022 with the sounds of Sound Rush LIVE at the RED on Friday! 🔥',
|
||||
'season': 'Defqon.1 Weekend Festival 2022',
|
||||
'season_id': '31840632',
|
||||
'series': 'Defqon.1',
|
||||
'series_id': '31840378',
|
||||
'thumbnail': 'https://images.q-dance.network/1674829540-20220624171509-220624171509_delio_dn201093-2.jpg',
|
||||
'availability': 'premium_only',
|
||||
'duration': 1829,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'note': 'livestream',
|
||||
'url': 'https://www.q-dance.com/network/live/149170353',
|
||||
'info_dict': {
|
||||
'id': '149170353',
|
||||
'ext': 'mp4',
|
||||
'title': r're:^Defqon\.1 2023 - Friday - RED',
|
||||
'display_id': 'defqon-1-2023-friday-red',
|
||||
'description': 'md5:3c73fbbd4044e578e696adfc64019163',
|
||||
'season': 'Defqon.1 Weekend Festival 2023',
|
||||
'season_id': '141735599',
|
||||
'series': 'Defqon.1',
|
||||
'series_id': '31840378',
|
||||
'thumbnail': 'https://images.q-dance.network/1686849069-area-thumbs_red.png',
|
||||
'availability': 'subscriber_only',
|
||||
'live_status': 'is_live',
|
||||
'channel_id': 'qdancenetwork.video_149170353',
|
||||
},
|
||||
'skip': 'Completed livestream',
|
||||
}]
|
||||
|
||||
_access_token = None
|
||||
_refresh_token = None
|
||||
|
||||
def _call_login_api(self, data, note='Logging in'):
|
||||
login = self._download_json(
|
||||
'https://members.id-t.com/api/auth/login', None, note, headers={
|
||||
'content-type': 'application/json',
|
||||
'brand': 'qdance',
|
||||
'origin': 'https://www.q-dance.com',
|
||||
'referer': 'https://www.q-dance.com/',
|
||||
}, data=json.dumps(data, separators=(',', ':')).encode(),
|
||||
expected_status=lambda x: True)
|
||||
|
||||
tokens = traverse_obj(login, ('data', {
|
||||
'_id-t-accounts-token': ('accessToken', {str}),
|
||||
'_id-t-accounts-refresh': ('refreshToken', {str}),
|
||||
'_id-t-accounts-id-token': ('idToken', {str}),
|
||||
}))
|
||||
|
||||
if not tokens.get('_id-t-accounts-token'):
|
||||
error = ': '.join(traverse_obj(login, ('error', ('code', 'message'), {str})))
|
||||
if 'validation_error' not in error:
|
||||
raise ExtractorError(f'Q-Dance API said "{error}"')
|
||||
msg = 'Invalid username or password' if 'email' in data else 'Refresh token has expired'
|
||||
raise ExtractorError(msg, expected=True)
|
||||
|
||||
for name, value in tokens.items():
|
||||
self._set_cookie('.q-dance.com', name, value)
|
||||
|
||||
def _perform_login(self, username, password):
|
||||
self._call_login_api({'email': username, 'password': password})
|
||||
|
||||
def _real_initialize(self):
|
||||
cookies = self._get_cookies('https://www.q-dance.com/')
|
||||
self._refresh_token = try_call(lambda: cookies['_id-t-accounts-refresh'].value)
|
||||
self._access_token = try_call(lambda: cookies['_id-t-accounts-token'].value)
|
||||
if not self._access_token:
|
||||
self.raise_login_required()
|
||||
|
||||
def _get_auth(self):
|
||||
if (try_call(lambda: jwt_decode_hs256(self._access_token)['exp']) or 0) <= int(time.time() - 120):
|
||||
if not self._refresh_token:
|
||||
raise ExtractorError(
|
||||
'Cannot refresh access token, login with yt-dlp or refresh cookies in browser')
|
||||
self._call_login_api({'refreshToken': self._refresh_token}, note='Refreshing access token')
|
||||
self._real_initialize()
|
||||
|
||||
return {'Authorization': self._access_token}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
data = self._search_nuxt_data(webpage, video_id, traverse=('data', 0, 'data'))
|
||||
|
||||
def extract_availability(level):
|
||||
level = int_or_none(level) or 0
|
||||
return self._availability(
|
||||
needs_premium=(level >= 20), needs_subscription=(level >= 15), needs_auth=True)
|
||||
|
||||
info = traverse_obj(data, {
|
||||
'title': ('title', {str.strip}),
|
||||
'description': ('description', {str.strip}),
|
||||
'display_id': ('slug', {str}),
|
||||
'thumbnail': ('thumbnail', {url_or_none}),
|
||||
'duration': ('durationInSeconds', {int_or_none}, {lambda x: x or None}),
|
||||
'availability': ('subscription', 'level', {extract_availability}),
|
||||
'is_live': ('type', {lambda x: x.lower() == 'live'}),
|
||||
'artist': ('acts', ..., {str}),
|
||||
'series': ('event', 'title', {str.strip}),
|
||||
'series_id': ('event', 'id', {str_or_none}),
|
||||
'season': ('eventEdition', 'title', {str.strip}),
|
||||
'season_id': ('eventEdition', 'id', {str_or_none}),
|
||||
'channel_id': ('pubnub', 'channelName', {str}),
|
||||
})
|
||||
|
||||
stream = self._download_json(
|
||||
f'https://dc9h6qmsoymbq.cloudfront.net/api/content/videos/{video_id}/url',
|
||||
video_id, headers=self._get_auth(), expected_status=401)
|
||||
|
||||
m3u8_url = traverse_obj(stream, ('data', 'url', {url_or_none}))
|
||||
if not m3u8_url and traverse_obj(stream, ('error', 'code')) == 'unauthorized':
|
||||
raise ExtractorError('Your account does not have access to this content', expected=True)
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, fatal=False, live=True) if m3u8_url else []
|
||||
if not formats:
|
||||
self.raise_no_formats('No active streams found', expected=bool(info.get('is_live')))
|
||||
|
||||
return {
|
||||
**info,
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
}
|
||||
@@ -139,8 +139,8 @@ def _real_extract(self, url):
|
||||
'release_year': ('releaseYear', {int_or_none}),
|
||||
'duration': ('duration', ({float_or_none}, {parse_duration})),
|
||||
'is_live': ('liveStream', {bool}),
|
||||
'age_limit': (
|
||||
('classificationID', 'contentRating'), {str.upper}, {self._AUS_TV_PARENTAL_GUIDELINES.get}),
|
||||
'age_limit': (('classificationID', 'contentRating'), {str.upper}, {
|
||||
lambda x: self._AUS_TV_PARENTAL_GUIDELINES.get(x)}), # dict.get is unhashable in py3.7
|
||||
}, get_all=False),
|
||||
**traverse_obj(media, {
|
||||
'categories': (('genres', ...), ('taxonomy', ('genre', 'subgenre'), 'name'), {str}),
|
||||
|
||||
148
yt_dlp/extractor/stacommu.py
Normal file
148
yt_dlp/extractor/stacommu.py
Normal file
@@ -0,0 +1,148 @@
|
||||
import time
|
||||
|
||||
from .wrestleuniverse import WrestleUniverseBaseIE
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
traverse_obj,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class StacommuBaseIE(WrestleUniverseBaseIE):
|
||||
_NETRC_MACHINE = 'stacommu'
|
||||
_API_HOST = 'api.stacommu.jp'
|
||||
_LOGIN_QUERY = {'key': 'AIzaSyCR9czxhH2eWuijEhTNWBZ5MCcOYEUTAhg'}
|
||||
_LOGIN_HEADERS = {
|
||||
'Accept': '*/*',
|
||||
'Content-Type': 'application/json',
|
||||
'X-Client-Version': 'Chrome/JsCore/9.9.4/FirebaseCore-web',
|
||||
'Referer': 'https://www.stacommu.jp/',
|
||||
'Origin': 'https://www.stacommu.jp',
|
||||
}
|
||||
|
||||
@WrestleUniverseBaseIE._TOKEN.getter
|
||||
def _TOKEN(self):
|
||||
if self._REAL_TOKEN and self._TOKEN_EXPIRY <= int(time.time()):
|
||||
self._refresh_token()
|
||||
|
||||
return self._REAL_TOKEN
|
||||
|
||||
def _get_formats(self, data, path, video_id=None):
|
||||
if not traverse_obj(data, path) and not data.get('canWatch') and not self._TOKEN:
|
||||
self.raise_login_required(method='password')
|
||||
return super()._get_formats(data, path, video_id)
|
||||
|
||||
def _extract_hls_key(self, data, path, decrypt):
|
||||
encryption_data = traverse_obj(data, path)
|
||||
if traverse_obj(encryption_data, ('encryptType', {int})) == 0:
|
||||
return None
|
||||
return traverse_obj(encryption_data, {'key': ('key', {decrypt}), 'iv': ('iv', {decrypt})})
|
||||
|
||||
|
||||
class StacommuVODIE(StacommuBaseIE):
|
||||
_VALID_URL = r'https?://www\.stacommu\.jp/videos/episodes/(?P<id>[\da-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
# not encrypted
|
||||
'url': 'https://www.stacommu.jp/videos/episodes/aXcVKjHyAENEjard61soZZ',
|
||||
'info_dict': {
|
||||
'id': 'aXcVKjHyAENEjard61soZZ',
|
||||
'ext': 'mp4',
|
||||
'title': 'スタコミュAWARDの裏側、ほぼ全部見せます!〜晴れ舞台の直前ドキドキ編〜',
|
||||
'description': 'md5:6400275c57ae75c06da36b06f96beb1c',
|
||||
'timestamp': 1679652000,
|
||||
'upload_date': '20230324',
|
||||
'thumbnail': 'https://image.stacommu.jp/6eLobQan8PFtBoU4RL4uGg/6eLobQan8PFtBoU4RL4uGg',
|
||||
'cast': 'count:11',
|
||||
'duration': 250,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}, {
|
||||
# encrypted; requires a premium account
|
||||
'url': 'https://www.stacommu.jp/videos/episodes/3hybMByUvzMEqndSeu5LpD',
|
||||
'info_dict': {
|
||||
'id': '3hybMByUvzMEqndSeu5LpD',
|
||||
'ext': 'mp4',
|
||||
'title': 'スタプラフェス2023〜裏側ほぼ全部見せます〜#10',
|
||||
'description': 'md5:85494488ccf1dfa1934accdeadd7b340',
|
||||
'timestamp': 1682506800,
|
||||
'upload_date': '20230426',
|
||||
'thumbnail': 'https://image.stacommu.jp/eMdXtEefR4kEyJJMpAFi7x/eMdXtEefR4kEyJJMpAFi7x',
|
||||
'cast': 'count:55',
|
||||
'duration': 312,
|
||||
'hls_aes': {
|
||||
'key': '6bbaf241b8e1fd9f59ecf546a70e4ae7',
|
||||
'iv': '1fc9002a23166c3bb1d240b953d09de9',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}]
|
||||
|
||||
_API_PATH = 'videoEpisodes'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_info = self._download_metadata(
|
||||
url, video_id, 'ja', ('dehydratedState', 'queries', 0, 'state', 'data'))
|
||||
hls_info, decrypt = self._call_encrypted_api(
|
||||
video_id, ':watch', 'stream information', data={'method': 1})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': self._get_formats(hls_info, ('protocolHls', 'url', {url_or_none}), video_id),
|
||||
'hls_aes': self._extract_hls_key(hls_info, 'protocolHls', decrypt),
|
||||
**traverse_obj(video_info, {
|
||||
'title': ('displayName', {str}),
|
||||
'description': ('description', {str}),
|
||||
'timestamp': ('watchStartTime', {int_or_none}),
|
||||
'thumbnail': ('keyVisualUrl', {url_or_none}),
|
||||
'cast': ('casts', ..., 'displayName', {str}),
|
||||
'duration': ('duration', {int}),
|
||||
}),
|
||||
}
|
||||
|
||||
|
||||
class StacommuLiveIE(StacommuBaseIE):
|
||||
_VALID_URL = r'https?://www\.stacommu\.jp/live/(?P<id>[\da-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.stacommu.jp/live/d2FJ3zLnndegZJCAEzGM3m',
|
||||
'info_dict': {
|
||||
'id': 'd2FJ3zLnndegZJCAEzGM3m',
|
||||
'ext': 'mp4',
|
||||
'title': '仲村悠菜 2023/05/04',
|
||||
'timestamp': 1683195647,
|
||||
'upload_date': '20230504',
|
||||
'thumbnail': 'https://image.stacommu.jp/pHGF57SPEHE2ke83FS92FN/pHGF57SPEHE2ke83FS92FN',
|
||||
'duration': 5322,
|
||||
'hls_aes': {
|
||||
'key': 'efbb3ec0b8246f61adf1764c5a51213a',
|
||||
'iv': '80621d19a1f19167b64cedb415b05d1c',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}]
|
||||
|
||||
_API_PATH = 'events'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_info = self._call_api(video_id, msg='video information', query={'al': 'ja'}, auth=False)
|
||||
hls_info, decrypt = self._call_encrypted_api(
|
||||
video_id, ':watchArchive', 'stream information', data={'method': 1})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
|
||||
'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
|
||||
**traverse_obj(video_info, {
|
||||
'title': ('displayName', {str}),
|
||||
'timestamp': ('startTime', {int_or_none}),
|
||||
'thumbnail': ('keyVisualUrl', {url_or_none}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
}),
|
||||
}
|
||||
@@ -1015,18 +1015,16 @@ def _real_extract(self, url):
|
||||
self.to_screen(f'{e}; trying with webpage')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
render_data_json = self._search_regex(
|
||||
r'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^>]*>(%7B.+%7D)</script>',
|
||||
webpage, 'render data', default=None)
|
||||
if not render_data_json:
|
||||
render_data = self._search_json(
|
||||
r'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^>]*>', webpage, 'render data', video_id,
|
||||
contains_pattern=r'%7B(?s:.+)%7D', fatal=False, transform_source=compat_urllib_parse_unquote)
|
||||
if not render_data:
|
||||
# TODO: Run verification challenge code to generate signature cookies
|
||||
cookies = self._get_cookies(self._WEBPAGE_HOST)
|
||||
expected = not cookies.get('s_v_web_id') or not cookies.get('ttwid')
|
||||
raise ExtractorError(
|
||||
'Fresh cookies (not necessarily logged in) are needed', expected=expected)
|
||||
|
||||
render_data = self._parse_json(
|
||||
render_data_json, video_id, transform_source=compat_urllib_parse_unquote)
|
||||
return self._parse_aweme_video_web(get_first(render_data, ('aweme', 'detail')), url, video_id)
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import json
|
||||
import re
|
||||
import urllib.error
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .periscope import PeriscopeBaseIE, PeriscopeIE
|
||||
@@ -34,7 +35,6 @@ class TwitterBaseIE(InfoExtractor):
|
||||
_GRAPHQL_API_BASE = 'https://twitter.com/i/api/graphql/'
|
||||
_BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?(?:twitter\.com|twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid\.onion)/'
|
||||
_AUTH = {'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'}
|
||||
_guest_token = None
|
||||
_flow_token = None
|
||||
|
||||
_LOGIN_INIT_DATA = json.dumps({
|
||||
@@ -145,14 +145,6 @@ def _search_dimensions_in_video_url(a_format, video_url):
|
||||
def is_logged_in(self):
|
||||
return bool(self._get_cookies(self._API_BASE).get('auth_token'))
|
||||
|
||||
def _fetch_guest_token(self, headers, display_id):
|
||||
headers.pop('x-guest-token', None)
|
||||
self._guest_token = traverse_obj(self._download_json(
|
||||
f'{self._API_BASE}guest/activate.json', display_id,
|
||||
'Downloading guest token', data=b'', headers=headers), 'guest_token')
|
||||
if not self._guest_token:
|
||||
raise ExtractorError('Could not retrieve guest token')
|
||||
|
||||
def _set_base_headers(self):
|
||||
headers = self._AUTH.copy()
|
||||
csrf_token = try_call(lambda: self._get_cookies(self._API_BASE)['ct0'].value)
|
||||
@@ -183,12 +175,15 @@ def _perform_login(self, username, password):
|
||||
if self.is_logged_in:
|
||||
return
|
||||
|
||||
self._request_webpage('https://twitter.com/', None, 'Requesting cookies')
|
||||
webpage = self._download_webpage('https://twitter.com/', None, 'Downloading login page')
|
||||
headers = self._set_base_headers()
|
||||
self._fetch_guest_token(headers, None)
|
||||
guest_token = self._search_regex(
|
||||
r'\.cookie\s*=\s*["\']gt=(\d+);', webpage, 'gt', default=None) or self._download_json(
|
||||
f'{self._API_BASE}guest/activate.json', None, 'Downloading guest token',
|
||||
data=b'', headers=headers)['guest_token']
|
||||
headers.update({
|
||||
'content-type': 'application/json',
|
||||
'x-guest-token': self._guest_token,
|
||||
'x-guest-token': guest_token,
|
||||
'x-twitter-client-language': 'en',
|
||||
'x-twitter-active-user': 'yes',
|
||||
'Referer': 'https://twitter.com/',
|
||||
@@ -285,37 +280,24 @@ def input_dict(subtask_id, text):
|
||||
self.report_login()
|
||||
|
||||
def _call_api(self, path, video_id, query={}, graphql=False):
|
||||
headers = self._set_base_headers()
|
||||
if self.is_logged_in:
|
||||
headers.update({
|
||||
if not self.is_logged_in:
|
||||
self.raise_login_required()
|
||||
|
||||
result = self._download_json(
|
||||
(self._GRAPHQL_API_BASE if graphql else self._API_BASE) + path, video_id,
|
||||
f'Downloading {"GraphQL" if graphql else "legacy API"} JSON', headers={
|
||||
**self._set_base_headers(),
|
||||
'x-twitter-auth-type': 'OAuth2Session',
|
||||
'x-twitter-client-language': 'en',
|
||||
'x-twitter-active-user': 'yes',
|
||||
})
|
||||
}, query=query, expected_status={400, 401, 403, 404} if graphql else {403})
|
||||
|
||||
for first_attempt in (True, False):
|
||||
if not self.is_logged_in:
|
||||
if not self._guest_token:
|
||||
self._fetch_guest_token(headers, video_id)
|
||||
headers['x-guest-token'] = self._guest_token
|
||||
if result.get('errors'):
|
||||
errors = ', '.join(set(traverse_obj(result, ('errors', ..., 'message', {str}))))
|
||||
raise ExtractorError(
|
||||
f'Error(s) while querying API: {errors or "Unknown error"}', expected=True)
|
||||
|
||||
allowed_status = {400, 401, 403, 404} if graphql else {403}
|
||||
result = self._download_json(
|
||||
(self._GRAPHQL_API_BASE if graphql else self._API_BASE) + path,
|
||||
video_id, headers=headers, query=query, expected_status=allowed_status,
|
||||
note=f'Downloading {"GraphQL" if graphql else "legacy API"} JSON')
|
||||
|
||||
if result.get('errors'):
|
||||
errors = ', '.join(set(traverse_obj(result, ('errors', ..., 'message', {str}))))
|
||||
if not self.is_logged_in and first_attempt and 'bad guest token' in errors.lower():
|
||||
self.to_screen('Guest token has expired. Refreshing guest token')
|
||||
self._guest_token = None
|
||||
continue
|
||||
|
||||
raise ExtractorError(
|
||||
f'Error(s) while querying API: {errors or "Unknown error"}', expected=True)
|
||||
|
||||
return result
|
||||
return result
|
||||
|
||||
def _build_graphql_query(self, media_id):
|
||||
raise NotImplementedError('Method must be implemented to support GraphQL')
|
||||
@@ -457,6 +439,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
_VALID_URL = TwitterBaseIE._BASE_REGEX + r'(?:(?:i/web|[^/]+)/status|statuses)/(?P<id>\d+)(?:/(?:video|photo)/(?P<index>\d+))?'
|
||||
|
||||
_TESTS = [{
|
||||
# comment_count, repost_count, view_count are only available with auth (applies to all tests)
|
||||
'url': 'https://twitter.com/freethenipple/status/643211948184596480',
|
||||
'info_dict': {
|
||||
'id': '643211870443208704',
|
||||
@@ -471,10 +454,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1442188653,
|
||||
'upload_date': '20150913',
|
||||
'uploader_url': 'https://twitter.com/freethenipple',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 18,
|
||||
},
|
||||
@@ -505,8 +485,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1447395772,
|
||||
'upload_date': '20151113',
|
||||
'uploader_url': 'https://twitter.com/starwars',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'tags': ['TV', 'StarWars', 'TheForceAwakens'],
|
||||
'age_limit': 0,
|
||||
@@ -550,10 +528,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1455777459,
|
||||
'upload_date': '20160218',
|
||||
'uploader_url': 'https://twitter.com/jaydingeer',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': ['Damndaniel'],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -591,10 +566,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'upload_date': '20160412',
|
||||
'uploader_url': 'https://twitter.com/CaptainAmerica',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -641,10 +613,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1505803395,
|
||||
'upload_date': '20170919',
|
||||
'uploader_url': 'https://twitter.com/Prefet971',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': ['Maria'],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -667,10 +636,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1527623489,
|
||||
'upload_date': '20180529',
|
||||
'uploader_url': 'https://twitter.com/LisPower1',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -692,10 +658,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1548184644,
|
||||
'upload_date': '20190122',
|
||||
'uploader_url': 'https://twitter.com/Twitter',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -713,6 +676,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'view_count': int,
|
||||
},
|
||||
'add_ie': ['TwitterBroadcast'],
|
||||
'skip': 'Requires authentication',
|
||||
}, {
|
||||
# unified card
|
||||
'url': 'https://twitter.com/BrooklynNets/status/1349794411333394432?s=20',
|
||||
@@ -729,8 +693,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1610651040,
|
||||
'upload_date': '20210114',
|
||||
'uploader_url': 'https://twitter.com/BrooklynNets',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
@@ -753,10 +715,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'duration': 30.03,
|
||||
'timestamp': 1665025050,
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -765,15 +724,13 @@ class TwitterIE(TwitterBaseIE):
|
||||
'url': 'https://twitter.com/UltimaShadowX/status/1577719286659006464',
|
||||
'info_dict': {
|
||||
'id': '1577719286659006464',
|
||||
'title': 'Ultima | #\u0432\u029f\u043c - Test',
|
||||
'title': 'Ultima📛 | #вʟм - Test',
|
||||
'description': 'Test https://t.co/Y3KEZD7Dad',
|
||||
'uploader': 'Ultima | #\u0432\u029f\u043c',
|
||||
'uploader': 'Ultima📛 | #вʟм',
|
||||
'uploader_id': 'UltimaShadowX',
|
||||
'uploader_url': 'https://twitter.com/UltimaShadowX',
|
||||
'upload_date': '20221005',
|
||||
'timestamp': 1664992565,
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'tags': [],
|
||||
'age_limit': 0,
|
||||
@@ -795,10 +752,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'duration': 21.321,
|
||||
'timestamp': 1664477766,
|
||||
'upload_date': '20220929',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'tags': ['HurricaneIan'],
|
||||
'age_limit': 0,
|
||||
},
|
||||
@@ -825,6 +779,20 @@ class TwitterIE(TwitterBaseIE):
|
||||
},
|
||||
'skip': 'Requires authentication',
|
||||
}, {
|
||||
# Single Vimeo video result without auth
|
||||
'url': 'https://twitter.com/Srirachachau/status/1395079556562706435',
|
||||
'info_dict': {
|
||||
'id': '551578322',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dusty & The Mayor',
|
||||
'uploader': 'Michael Chau',
|
||||
'uploader_id': 'user29061007',
|
||||
'uploader_url': 'https://vimeo.com/user29061007',
|
||||
'duration': 478,
|
||||
'thumbnail': 'https://i.vimeocdn.com/video/1139658575-0dfdce6e9a2401fe09feb24bf0d14e6f24a53c12f447ff688ace61009ad4c1ba-d_1280',
|
||||
},
|
||||
}, {
|
||||
# Playlist result only with auth
|
||||
'url': 'https://twitter.com/Srirachachau/status/1395079556562706435',
|
||||
'playlist_mincount': 2,
|
||||
'info_dict': {
|
||||
@@ -842,6 +810,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'uploader_url': 'https://twitter.com/Srirachachau',
|
||||
'timestamp': 1621447860,
|
||||
},
|
||||
'skip': 'Requires authentication',
|
||||
}, {
|
||||
'url': 'https://twitter.com/DavidToons_/status/1578353380363501568',
|
||||
'playlist_mincount': 2,
|
||||
@@ -860,6 +829,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'upload_date': '20221007',
|
||||
'age_limit': 0,
|
||||
},
|
||||
'skip': 'Requires authentication',
|
||||
}, {
|
||||
'url': 'https://twitter.com/primevideouk/status/1578401165338976258',
|
||||
'playlist_count': 2,
|
||||
@@ -873,8 +843,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'upload_date': '20221007',
|
||||
'age_limit': 0,
|
||||
'uploader_url': 'https://twitter.com/primevideouk',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
'like_count': int,
|
||||
'tags': ['TheRingsOfPower'],
|
||||
},
|
||||
@@ -889,11 +857,14 @@ class TwitterIE(TwitterBaseIE):
|
||||
'uploader_id': 'MoniqueCamarra',
|
||||
'live_status': 'was_live',
|
||||
'release_timestamp': 1658417414,
|
||||
'description': 'md5:acce559345fd49f129c20dbcda3f1201',
|
||||
'timestamp': 1658407771464,
|
||||
'description': 'md5:4dc8e972f1d8b3c6580376fabb02a3ad',
|
||||
'timestamp': 1658407771,
|
||||
'release_date': '20220721',
|
||||
'upload_date': '20220721',
|
||||
},
|
||||
'add_ie': ['TwitterSpaces'],
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'skip': 'Requires authentication',
|
||||
}, {
|
||||
# URL specifies video number but --yes-playlist
|
||||
'url': 'https://twitter.com/CTVJLaidlaw/status/1600649710662213632/video/1',
|
||||
@@ -903,9 +874,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'title': 'md5:be05989b0722e114103ed3851a0ffae2',
|
||||
'timestamp': 1670459604.0,
|
||||
'description': 'md5:591c19ce66fadc2359725d5cd0d1052c',
|
||||
'comment_count': int,
|
||||
'uploader_id': 'CTVJLaidlaw',
|
||||
'repost_count': int,
|
||||
'tags': ['colorectalcancer', 'cancerjourney', 'imnotaquitter'],
|
||||
'upload_date': '20221208',
|
||||
'age_limit': 0,
|
||||
@@ -924,14 +893,11 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1670459604.0,
|
||||
'uploader_id': 'CTVJLaidlaw',
|
||||
'uploader': 'Jocelyn Laidlaw',
|
||||
'repost_count': int,
|
||||
'comment_count': int,
|
||||
'tags': ['colorectalcancer', 'cancerjourney', 'imnotaquitter'],
|
||||
'duration': 102.226,
|
||||
'uploader_url': 'https://twitter.com/CTVJLaidlaw',
|
||||
'display_id': '1600649710662213632',
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'description': 'md5:591c19ce66fadc2359725d5cd0d1052c',
|
||||
'upload_date': '20221208',
|
||||
'age_limit': 0,
|
||||
@@ -957,9 +923,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'age_limit': 18,
|
||||
'tags': [],
|
||||
'like_count': int,
|
||||
'repost_count': int,
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://twitter.com/hlo_again/status/1599108751385972737/video/2',
|
||||
@@ -972,10 +935,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'like_count': int,
|
||||
'uploader_id': 'hlo_again',
|
||||
'thumbnail': 'https://pbs.twimg.com/ext_tw_video_thumb/1599108643743473680/pu/img/UG3xjov4rgg5sbYM.jpg?name=orig',
|
||||
'repost_count': int,
|
||||
'duration': 9.531,
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
'upload_date': '20221203',
|
||||
'age_limit': 0,
|
||||
'timestamp': 1670092210.0,
|
||||
@@ -992,14 +952,11 @@ class TwitterIE(TwitterBaseIE):
|
||||
'ext': 'mp4',
|
||||
'uploader_url': 'https://twitter.com/MunTheShinobi',
|
||||
'description': 'This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525 https://t.co/cNsA0MoOml',
|
||||
'view_count': int,
|
||||
'thumbnail': 'https://pbs.twimg.com/ext_tw_video_thumb/1600009362759733248/pu/img/XVhFQivj75H_YxxV.jpg?name=orig',
|
||||
'age_limit': 0,
|
||||
'uploader': 'Mün The Shinobi',
|
||||
'repost_count': int,
|
||||
'upload_date': '20221206',
|
||||
'title': 'Mün The Shinobi - This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525',
|
||||
'comment_count': int,
|
||||
'like_count': int,
|
||||
'tags': [],
|
||||
'uploader_id': 'MunTheShinobi',
|
||||
@@ -1007,14 +964,14 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1670306984.0,
|
||||
},
|
||||
}, {
|
||||
# url to retweet id, legacy API
|
||||
# url to retweet id
|
||||
'url': 'https://twitter.com/liberdalau/status/1623739803874349067',
|
||||
'info_dict': {
|
||||
'id': '1623274794488659969',
|
||||
'display_id': '1623739803874349067',
|
||||
'ext': 'mp4',
|
||||
'title': 'Johnny Bullets - Me after going viral to over 30million people: Whoopsie-daisy',
|
||||
'description': 'md5:e873616a4a8fe0f93e71872678a672f3',
|
||||
'description': 'md5:224d62f54b0cdef8e33d4c56c41ac503',
|
||||
'uploader': 'Johnny Bullets',
|
||||
'uploader_id': 'Johnnybull3ts',
|
||||
'uploader_url': 'https://twitter.com/Johnnybull3ts',
|
||||
@@ -1025,10 +982,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
'upload_date': '20230208',
|
||||
'thumbnail': r're:https://pbs\.twimg\.com/ext_tw_video_thumb/.+',
|
||||
'like_count': int,
|
||||
'repost_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
'params': {'extractor_args': {'twitter': {'legacy_api': ['']}}},
|
||||
}, {
|
||||
# onion route
|
||||
'url': 'https://twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid.onion/TwitterBlue/status/1484226494708662273',
|
||||
@@ -1079,8 +1033,6 @@ def _graphql_to_legacy(self, data, twid):
|
||||
|
||||
if 'tombstone' in result:
|
||||
cause = remove_end(traverse_obj(result, ('tombstone', 'text', 'text', {str})), '. Learn more')
|
||||
if cause and 'adult content' in cause:
|
||||
self.raise_login_required(cause)
|
||||
raise ExtractorError(f'Twitter API says: {cause or "Unknown error"}', expected=True)
|
||||
|
||||
status = result.get('legacy', {})
|
||||
@@ -1136,19 +1088,22 @@ def _build_graphql_query(self, media_id):
|
||||
|
||||
def _real_extract(self, url):
|
||||
twid, selected_index = self._match_valid_url(url).group('id', 'index')
|
||||
if self._configuration_arg('legacy_api') and not self.is_logged_in:
|
||||
status = traverse_obj(self._call_api(f'statuses/show/{twid}.json', twid, {
|
||||
'cards_platform': 'Web-12',
|
||||
'include_cards': 1,
|
||||
'include_reply_count': 1,
|
||||
'include_user_entities': 0,
|
||||
'tweet_mode': 'extended',
|
||||
}), 'retweeted_status', None)
|
||||
if not self.is_logged_in:
|
||||
try:
|
||||
status = self._download_json(
|
||||
'https://cdn.syndication.twimg.com/tweet-result', twid, 'Downloading syndication JSON',
|
||||
headers={'User-Agent': 'Googlebot'}, query={'id': twid})
|
||||
self.to_screen(f'Some metadata is missing without authentication. {self._login_hint()}')
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404:
|
||||
self.raise_login_required('Requested tweet may only be available when logged in')
|
||||
raise
|
||||
else:
|
||||
result = self._call_graphql_api('zZXycP0V6H7m-2r0mOnFcA/TweetDetail', twid)
|
||||
status = self._graphql_to_legacy(result, twid)
|
||||
status = self._graphql_to_legacy(
|
||||
self._call_graphql_api('zZXycP0V6H7m-2r0mOnFcA/TweetDetail', twid), twid)
|
||||
|
||||
title = description = status['full_text'].replace('\n', ' ')
|
||||
title = description = traverse_obj(
|
||||
status, (('full_text', 'text'), {lambda x: x.replace('\n', ' ')}), get_all=False) or ''
|
||||
# strip 'https -_t.co_BJYgOjSeGA' junk from filenames
|
||||
title = re.sub(r'\s+(https?://[^ ]+)', '', title)
|
||||
user = status.get('user') or {}
|
||||
@@ -1174,12 +1129,16 @@ def _real_extract(self, url):
|
||||
|
||||
def extract_from_video_info(media):
|
||||
media_id = traverse_obj(media, 'id_str', 'id', expected_type=str_or_none)
|
||||
if not media_id:
|
||||
# workaround for non-authenticated responses
|
||||
media_id = traverse_obj(media, (
|
||||
'video_info', 'variants', ..., 'url',
|
||||
{lambda x: re.search(r'_video/(\d+)/', x)[1]}), get_all=False)
|
||||
self.write_debug(f'Extracting from video info: {media_id}')
|
||||
video_info = media.get('video_info') or {}
|
||||
|
||||
formats = []
|
||||
subtitles = {}
|
||||
for variant in video_info.get('variants', []):
|
||||
for variant in traverse_obj(media, ('video_info', 'variants', ...)):
|
||||
fmts, subs = self._extract_variant_formats(variant, twid)
|
||||
subtitles = self._merge_subtitles(subtitles, subs)
|
||||
formats.extend(fmts)
|
||||
@@ -1199,12 +1158,12 @@ def add_thumbnail(name, size):
|
||||
add_thumbnail('orig', media.get('original_info') or {})
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'id': media_id or twid,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'thumbnails': thumbnails,
|
||||
'view_count': traverse_obj(media, ('mediaStats', 'viewCount', {int_or_none})),
|
||||
'duration': float_or_none(video_info.get('duration_millis'), 1000),
|
||||
'duration': float_or_none(traverse_obj(media, ('video_info', 'duration_millis')), 1000),
|
||||
# The codec of http formats are unknown
|
||||
'_format_sort_fields': ('res', 'br', 'size', 'proto'),
|
||||
}
|
||||
@@ -1284,12 +1243,15 @@ def get_binding_value(k):
|
||||
}
|
||||
|
||||
videos = traverse_obj(status, (
|
||||
(None, 'quoted_status'), 'extended_entities', 'media', lambda _, m: m['type'] != 'photo', {dict}))
|
||||
('mediaDetails', ((None, 'quoted_status'), 'extended_entities', 'media')),
|
||||
lambda _, m: m['type'] != 'photo', {dict}))
|
||||
|
||||
if self._yes_playlist(twid, selected_index, video_label='URL-specified video number'):
|
||||
selected_entries = (*map(extract_from_video_info, videos), *extract_from_card_info(status.get('card')))
|
||||
else:
|
||||
desired_obj = traverse_obj(status, ('extended_entities', 'media', int(selected_index) - 1, {dict}))
|
||||
desired_obj = traverse_obj(status, (
|
||||
('mediaDetails', ((None, 'quoted_status'), 'extended_entities', 'media')),
|
||||
int(selected_index) - 1, {dict}), get_all=False)
|
||||
if not desired_obj:
|
||||
raise ExtractorError(f'Video #{selected_index} is unavailable', expected=True)
|
||||
elif desired_obj.get('type') != 'video':
|
||||
@@ -1436,7 +1398,10 @@ class TwitterSpacesIE(TwitterBaseIE):
|
||||
'uploader': r're:Lucio Di Gaetano.*?',
|
||||
'uploader_id': 'luciodigaetano',
|
||||
'live_status': 'was_live',
|
||||
'timestamp': 1659877956397,
|
||||
'timestamp': 1659877956,
|
||||
'upload_date': '20220807',
|
||||
'release_timestamp': 1659904215,
|
||||
'release_date': '20220807',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
@@ -1482,26 +1447,31 @@ def _real_extract(self, url):
|
||||
|
||||
metadata = space_data['metadata']
|
||||
live_status = try_call(lambda: self.SPACE_STATUS[metadata['state'].lower()])
|
||||
is_live = live_status == 'is_live'
|
||||
|
||||
formats = []
|
||||
if live_status == 'is_upcoming':
|
||||
self.raise_no_formats('Twitter Space not started yet', expected=True)
|
||||
elif live_status == 'post_live':
|
||||
self.raise_no_formats('Twitter Space ended but not downloadable yet', expected=True)
|
||||
else:
|
||||
source = self._call_api(
|
||||
f'live_video_stream/status/{metadata["media_key"]}', metadata['media_key'])['source']
|
||||
|
||||
# XXX: Native downloader does not work
|
||||
elif not is_live and not metadata.get('is_space_available_for_replay'):
|
||||
self.raise_no_formats('Twitter Space ended and replay is disabled', expected=True)
|
||||
elif metadata.get('media_key'):
|
||||
source = traverse_obj(
|
||||
self._call_api(f'live_video_stream/status/{metadata["media_key"]}', metadata['media_key']),
|
||||
('source', ('noRedirectPlaybackUrl', 'location'), {url_or_none}), get_all=False)
|
||||
formats = self._extract_m3u8_formats(
|
||||
traverse_obj(source, 'noRedirectPlaybackUrl', 'location'),
|
||||
metadata['media_key'], 'm4a', 'm3u8', live=live_status == 'is_live',
|
||||
headers={'Referer': 'https://twitter.com/'})
|
||||
source, metadata['media_key'], 'm4a', live=is_live, fatal=False,
|
||||
headers={'Referer': 'https://twitter.com/'}) if source else []
|
||||
for fmt in formats:
|
||||
fmt.update({'vcodec': 'none', 'acodec': 'aac'})
|
||||
if not is_live:
|
||||
fmt['container'] = 'm4a_dash'
|
||||
|
||||
participants = ', '.join(traverse_obj(
|
||||
space_data, ('participants', 'speakers', ..., 'display_name'))) or 'nobody yet'
|
||||
|
||||
if not formats and live_status == 'post_live':
|
||||
self.raise_no_formats('Twitter Space ended but not downloadable yet', expected=True)
|
||||
|
||||
return {
|
||||
'id': space_id,
|
||||
'title': metadata.get('title'),
|
||||
@@ -1513,7 +1483,7 @@ def _real_extract(self, url):
|
||||
'live_status': live_status,
|
||||
'release_timestamp': try_call(
|
||||
lambda: int_or_none(metadata['scheduled_start'], scale=1000)),
|
||||
'timestamp': metadata.get('created_at'),
|
||||
'timestamp': int_or_none(metadata.get('created_at'), scale=1000),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
@@ -70,6 +70,7 @@ def _real_extract(self, url):
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
|
||||
webpage) or []]
|
||||
for source in sources:
|
||||
source = urljoin(url, source)
|
||||
height = int(self._search_regex(r'(\d+).mp4', source, 'height', default=360))
|
||||
if self._request_webpage(HEADRequest(source), video_id, f'Checking {height}p url', errnote=False):
|
||||
formats.append({
|
||||
|
||||
@@ -11,11 +11,13 @@
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
UserNotLive,
|
||||
clean_html,
|
||||
get_element_by_class,
|
||||
get_element_html_by_id,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
parse_resolution,
|
||||
str_or_none,
|
||||
str_to_int,
|
||||
try_call,
|
||||
@@ -25,6 +27,7 @@
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
urljoin,
|
||||
traverse_obj,
|
||||
)
|
||||
|
||||
|
||||
@@ -701,3 +704,139 @@ def _real_extract(self, url):
|
||||
return self.playlist_result(
|
||||
entries, post_id, join_nonempty(uploader, f'Wall post {post_id}', delim=' - '),
|
||||
clean_html(get_element_by_class('wall_post_text', webpage)))
|
||||
|
||||
|
||||
class VKPlayBaseIE(InfoExtractor):
|
||||
_RESOLUTIONS = {
|
||||
'tiny': '256x144',
|
||||
'lowest': '426x240',
|
||||
'low': '640x360',
|
||||
'medium': '852x480',
|
||||
'high': '1280x720',
|
||||
'full_hd': '1920x1080',
|
||||
'quad_hd': '2560x1440',
|
||||
}
|
||||
|
||||
def _extract_from_initial_state(self, url, video_id, path):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_info = traverse_obj(self._search_json(
|
||||
r'<script[^>]+\bid="initial-state"[^>]*>', webpage, 'initial state', video_id),
|
||||
path, expected_type=dict)
|
||||
if not video_info:
|
||||
raise ExtractorError('Unable to extract video info from html inline initial state')
|
||||
return video_info
|
||||
|
||||
def _extract_formats(self, stream_info, video_id):
|
||||
formats = []
|
||||
for stream in traverse_obj(stream_info, (
|
||||
'data', 0, 'playerUrls', lambda _, v: url_or_none(v['url']) and v['type'])):
|
||||
url = stream['url']
|
||||
format_id = str_or_none(stream['type'])
|
||||
if format_id in ('hls', 'live_hls', 'live_playback_hls') or '.m3u8' in url:
|
||||
formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id=format_id, fatal=False))
|
||||
elif format_id == 'dash':
|
||||
formats.extend(self._extract_mpd_formats(url, video_id, mpd_id=format_id, fatal=False))
|
||||
elif format_id in ('live_dash', 'live_playback_dash'):
|
||||
self.write_debug(f'Not extracting unsupported format "{format_id}"')
|
||||
else:
|
||||
formats.append({
|
||||
'url': url,
|
||||
'ext': 'mp4',
|
||||
'format_id': format_id,
|
||||
**parse_resolution(self._RESOLUTIONS.get(format_id)),
|
||||
})
|
||||
return formats
|
||||
|
||||
def _extract_common_meta(self, stream_info):
|
||||
return traverse_obj(stream_info, {
|
||||
'id': ('id', {str_or_none}),
|
||||
'title': ('title', {str}),
|
||||
'release_timestamp': ('startTime', {int_or_none}),
|
||||
'thumbnail': ('previewUrl', {url_or_none}),
|
||||
'view_count': ('count', 'views', {int_or_none}),
|
||||
'like_count': ('count', 'likes', {int_or_none}),
|
||||
'categories': ('category', 'title', {str}, {lambda x: [x] if x else None}),
|
||||
'uploader': (('user', ('blog', 'owner')), 'nick', {str}),
|
||||
'uploader_id': (('user', ('blog', 'owner')), 'id', {str_or_none}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'is_live': ('isOnline', {bool}),
|
||||
'concurrent_view_count': ('count', 'viewers', {int_or_none}),
|
||||
}, get_all=False)
|
||||
|
||||
|
||||
class VKPlayIE(VKPlayBaseIE):
|
||||
_VALID_URL = r'https?://vkplay\.live/(?P<username>[^/]+)/record/(?P<id>[a-f0-9\-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://vkplay.live/zitsmann/record/f5e6e3b5-dc52-4d14-965d-0680dd2882da',
|
||||
'info_dict': {
|
||||
'id': 'f5e6e3b5-dc52-4d14-965d-0680dd2882da',
|
||||
'ext': 'mp4',
|
||||
'title': 'Atomic Heart (пробуем!) спасибо подписчику EKZO!',
|
||||
'uploader': 'ZitsmanN',
|
||||
'uploader_id': '13159830',
|
||||
'release_timestamp': 1683461378,
|
||||
'release_date': '20230507',
|
||||
'thumbnail': r're:https://images.vkplay.live/public_video_stream/record/f5e6e3b5-dc52-4d14-965d-0680dd2882da/preview\?change_time=\d+',
|
||||
'duration': 10608,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'categories': ['Atomic Heart'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
username, video_id = self._match_valid_url(url).groups()
|
||||
|
||||
record_info = traverse_obj(self._download_json(
|
||||
f'https://api.vkplay.live/v1/blog/{username}/public_video_stream/record/{video_id}', video_id, fatal=False),
|
||||
('data', 'record', {dict}))
|
||||
if not record_info:
|
||||
record_info = self._extract_from_initial_state(url, video_id, ('record', 'currentRecord', 'data'))
|
||||
|
||||
return {
|
||||
**self._extract_common_meta(record_info),
|
||||
'id': video_id,
|
||||
'formats': self._extract_formats(record_info, video_id),
|
||||
}
|
||||
|
||||
|
||||
class VKPlayLiveIE(VKPlayBaseIE):
|
||||
_VALID_URL = r'https?://vkplay\.live/(?P<id>[^/]+)/?(?:[#?]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://vkplay.live/bayda',
|
||||
'info_dict': {
|
||||
'id': 'f02c321e-427b-408d-b12f-ae34e53e0ea2',
|
||||
'ext': 'mp4',
|
||||
'title': r're:эскапизм крута .*',
|
||||
'uploader': 'Bayda',
|
||||
'uploader_id': 12279401,
|
||||
'release_timestamp': 1687209962,
|
||||
'release_date': '20230619',
|
||||
'thumbnail': r're:https://images.vkplay.live/public_video_stream/12279401/preview\?change_time=\d+',
|
||||
'view_count': int,
|
||||
'concurrent_view_count': int,
|
||||
'like_count': int,
|
||||
'categories': ['EVE Online'],
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'skip': 'livestream',
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
username = self._match_id(url)
|
||||
|
||||
stream_info = self._download_json(
|
||||
f'https://api.vkplay.live/v1/blog/{username}/public_video_stream', username, fatal=False)
|
||||
if not stream_info:
|
||||
stream_info = self._extract_from_initial_state(url, username, ('stream', 'stream', 'data', 'stream'))
|
||||
|
||||
formats = self._extract_formats(stream_info, username)
|
||||
if not formats and not traverse_obj(stream_info, ('isOnline', {bool})):
|
||||
raise UserNotLive(video_id=username)
|
||||
|
||||
return {
|
||||
**self._extract_common_meta(stream_info),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@@ -22,7 +22,7 @@ def _extract_packed(self, webpage):
|
||||
packed = self._search_regex(
|
||||
r'(eval\(function.+)', webpage, 'packed code')
|
||||
unpacked = decode_packed_codes(packed)
|
||||
digits = self._search_regex(r'\[((?:\d+,?)+)\]', unpacked, 'digits')
|
||||
digits = self._search_regex(r'\[([\d,]+)\]', unpacked, 'digits')
|
||||
digits = [int(digit) for digit in digits.split(',')]
|
||||
key_digit = self._search_regex(
|
||||
r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
|
||||
|
||||
@@ -14,12 +14,14 @@
|
||||
try_call,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
variadic,
|
||||
)
|
||||
|
||||
|
||||
class WrestleUniverseBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'wrestleuniverse'
|
||||
_VALID_URL_TMPL = r'https?://(?:www\.)?wrestle-universe\.com/(?:(?P<lang>\w{2})/)?%s/(?P<id>\w+)'
|
||||
_API_HOST = 'api.wrestle-universe.com'
|
||||
_API_PATH = None
|
||||
_REAL_TOKEN = None
|
||||
_TOKEN_EXPIRY = None
|
||||
@@ -67,24 +69,28 @@ def _perform_login(self, username, password):
|
||||
'returnSecureToken': True,
|
||||
'email': username,
|
||||
'password': password,
|
||||
}, separators=(',', ':')).encode())
|
||||
}, separators=(',', ':')).encode(), expected_status=400)
|
||||
token = traverse_obj(login, ('idToken', {str}))
|
||||
if not token:
|
||||
raise ExtractorError(
|
||||
f'Unable to log in: {traverse_obj(login, ("error", "message"))}', expected=True)
|
||||
self._REFRESH_TOKEN = traverse_obj(login, ('refreshToken', {str}))
|
||||
if not self._REFRESH_TOKEN:
|
||||
self.report_warning('No refresh token was granted')
|
||||
self._TOKEN = traverse_obj(login, ('idToken', {str}))
|
||||
self._TOKEN = token
|
||||
|
||||
def _real_initialize(self):
|
||||
if WrestleUniverseBaseIE._DEVICE_ID:
|
||||
if self._DEVICE_ID:
|
||||
return
|
||||
|
||||
WrestleUniverseBaseIE._DEVICE_ID = self._configuration_arg('device_id', [None], ie_key='WrestleUniverse')[0]
|
||||
if not WrestleUniverseBaseIE._DEVICE_ID:
|
||||
WrestleUniverseBaseIE._DEVICE_ID = self.cache.load(self._NETRC_MACHINE, 'device_id')
|
||||
if WrestleUniverseBaseIE._DEVICE_ID:
|
||||
self._DEVICE_ID = self._configuration_arg('device_id', [None], ie_key=self._NETRC_MACHINE)[0]
|
||||
if not self._DEVICE_ID:
|
||||
self._DEVICE_ID = self.cache.load(self._NETRC_MACHINE, 'device_id')
|
||||
if self._DEVICE_ID:
|
||||
return
|
||||
WrestleUniverseBaseIE._DEVICE_ID = str(uuid.uuid4())
|
||||
self._DEVICE_ID = str(uuid.uuid4())
|
||||
|
||||
self.cache.store(self._NETRC_MACHINE, 'device_id', WrestleUniverseBaseIE._DEVICE_ID)
|
||||
self.cache.store(self._NETRC_MACHINE, 'device_id', self._DEVICE_ID)
|
||||
|
||||
def _refresh_token(self):
|
||||
refresh = self._download_json(
|
||||
@@ -108,10 +114,10 @@ def _call_api(self, video_id, param='', msg='API', auth=True, data=None, query={
|
||||
if data:
|
||||
headers['Content-Type'] = 'application/json;charset=utf-8'
|
||||
data = json.dumps(data, separators=(',', ':')).encode()
|
||||
if auth:
|
||||
if auth and self._TOKEN:
|
||||
headers['Authorization'] = f'Bearer {self._TOKEN}'
|
||||
return self._download_json(
|
||||
f'https://api.wrestle-universe.com/v1/{self._API_PATH}/{video_id}{param}', video_id,
|
||||
f'https://{self._API_HOST}/v1/{self._API_PATH}/{video_id}{param}', video_id,
|
||||
note=f'Downloading {msg} JSON', errnote=f'Failed to download {msg} JSON',
|
||||
data=data, headers=headers, query=query, fatal=fatal)
|
||||
|
||||
@@ -137,12 +143,13 @@ def decrypt(data):
|
||||
}, query=query, fatal=fatal)
|
||||
return api_json, decrypt
|
||||
|
||||
def _download_metadata(self, url, video_id, lang, props_key):
|
||||
def _download_metadata(self, url, video_id, lang, props_keys):
|
||||
metadata = self._call_api(video_id, msg='metadata', query={'al': lang or 'ja'}, auth=False, fatal=False)
|
||||
if not metadata:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
nextjs_data = self._search_nextjs_data(webpage, video_id)
|
||||
metadata = traverse_obj(nextjs_data, ('props', 'pageProps', props_key, {dict})) or {}
|
||||
metadata = traverse_obj(nextjs_data, (
|
||||
'props', 'pageProps', *variadic(props_keys, (str, bytes, dict, set)), {dict})) or {}
|
||||
return metadata
|
||||
|
||||
def _get_formats(self, data, path, video_id=None):
|
||||
|
||||
@@ -2499,29 +2499,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'uploader_id': '@abaointokyo',
|
||||
},
|
||||
'params': {'skip_download': True}
|
||||
}, {
|
||||
# Story. Requires specific player params to work.
|
||||
'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
|
||||
'info_dict': {
|
||||
'id': 'vv8qTUWmulI',
|
||||
'ext': 'mp4',
|
||||
'availability': 'unlisted',
|
||||
'view_count': int,
|
||||
'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
|
||||
'upload_date': '20220526',
|
||||
'categories': ['Education'],
|
||||
'title': 'Story',
|
||||
'channel': 'IT\'S HISTORY',
|
||||
'description': '',
|
||||
'duration': 12,
|
||||
'playable_in_embed': True,
|
||||
'age_limit': 0,
|
||||
'live_status': 'not_live',
|
||||
'tags': [],
|
||||
'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
|
||||
'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
|
||||
},
|
||||
'skip': 'stories get removed after some period of time',
|
||||
}, {
|
||||
'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
|
||||
'info_dict': {
|
||||
@@ -3140,7 +3117,7 @@ def _extract_n_function_name(self, jscode):
|
||||
return funcname
|
||||
|
||||
return json.loads(js_to_json(self._search_regex(
|
||||
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])[,;]', jscode,
|
||||
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
|
||||
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
|
||||
|
||||
def _extract_n_function_code(self, video_id, player_url):
|
||||
@@ -3356,7 +3333,7 @@ def _extract_comment(self, comment_renderer, parent=None):
|
||||
info['author_is_uploader'] = author_is_uploader
|
||||
|
||||
comment_abr = traverse_obj(
|
||||
comment_renderer, ('actionsButtons', 'commentActionButtonsRenderer'), expected_type=dict)
|
||||
comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
|
||||
if comment_abr is not None:
|
||||
info['is_favorited'] = 'creatorHeart' in comment_abr
|
||||
|
||||
@@ -3426,7 +3403,9 @@ def extract_thread(contents):
|
||||
# Pinned comments may appear a second time in newest first sort
|
||||
# See: https://github.com/yt-dlp/yt-dlp/issues/6712
|
||||
continue
|
||||
self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
|
||||
self.report_warning(
|
||||
'Detected YouTube comments looping. Stopping comment extraction '
|
||||
f'{"for this thread" if parent else ""} as we probably cannot get any more.')
|
||||
yield
|
||||
else:
|
||||
tracker['seen_comment_ids'].add(comment['id'])
|
||||
@@ -3517,12 +3496,18 @@ def extract_thread(contents):
|
||||
# Ignore incomplete data error for replies if retries didn't work.
|
||||
# This is to allow any other parent comments and comment threads to be downloaded.
|
||||
# See: https://github.com/yt-dlp/yt-dlp/issues/4669
|
||||
if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
|
||||
self.report_warning(
|
||||
'Received incomplete data for a comment reply thread and retrying did not help. '
|
||||
'Ignoring to let other comments be downloaded.')
|
||||
else:
|
||||
raise
|
||||
if 'incomplete data' in str(e).lower() and parent:
|
||||
if self.get_param('ignoreerrors') in (True, 'only_download'):
|
||||
self.report_warning(
|
||||
'Received incomplete data for a comment reply thread and retrying did not help. '
|
||||
'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
|
||||
return
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'Incomplete data received for comment reply thread. '
|
||||
'Pass --ignore-errors to ignore and allow rest of comments to download.',
|
||||
expected=True)
|
||||
raise
|
||||
is_forced_continuation = False
|
||||
continuation = None
|
||||
for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
|
||||
@@ -3612,7 +3597,7 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg,
|
||||
yt_query = {
|
||||
'videoId': video_id,
|
||||
}
|
||||
if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
|
||||
if _split_innertube_client(client)[0] == 'android':
|
||||
yt_query['params'] = self._PLAYER_PARAMS
|
||||
|
||||
yt_query.update(self._generate_player_context(sts))
|
||||
@@ -3737,7 +3722,7 @@ def append_client(*client_names):
|
||||
|
||||
def _needs_live_processing(self, live_status, duration):
|
||||
if (live_status == 'is_live' and self.get_param('live_from_start')
|
||||
or live_status == 'post_live' and (duration or 0) > 4 * 3600):
|
||||
or live_status == 'post_live' and (duration or 0) > 2 * 3600):
|
||||
return live_status
|
||||
|
||||
def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
|
||||
@@ -3752,7 +3737,12 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l
|
||||
'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
|
||||
])
|
||||
streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
|
||||
all_formats = self._configuration_arg('include_duplicate_formats')
|
||||
format_types = self._configuration_arg('formats')
|
||||
all_formats = 'duplicate' in format_types
|
||||
if self._configuration_arg('include_duplicate_formats'):
|
||||
all_formats = True
|
||||
self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
|
||||
'Use formats=duplicate extractor argument instead')
|
||||
|
||||
def build_fragments(f):
|
||||
return LazyList({
|
||||
@@ -3892,18 +3882,23 @@ def build_fragments(f):
|
||||
if single_stream and dct.get('ext'):
|
||||
dct['container'] = dct['ext'] + '_dash'
|
||||
|
||||
if all_formats and dct['filesize']:
|
||||
if (all_formats or 'dashy' in format_types) and dct['filesize']:
|
||||
yield {
|
||||
**dct,
|
||||
'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
|
||||
'protocol': 'http_dash_segments',
|
||||
'fragments': build_fragments(dct),
|
||||
}
|
||||
dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
|
||||
yield dct
|
||||
if all_formats or 'dashy' not in format_types:
|
||||
dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
|
||||
yield dct
|
||||
|
||||
needs_live_processing = self._needs_live_processing(live_status, duration)
|
||||
skip_bad_formats = not self._configuration_arg('include_incomplete_formats')
|
||||
skip_bad_formats = 'incomplete' not in format_types
|
||||
if self._configuration_arg('include_incomplete_formats'):
|
||||
skip_bad_formats = False
|
||||
self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
|
||||
'Use formats=incomplete extractor argument instead')
|
||||
|
||||
skip_manifests = set(self._configuration_arg('skip'))
|
||||
if (not self.get_param('youtube_include_hls_manifest', True)
|
||||
@@ -3915,7 +3910,7 @@ def build_fragments(f):
|
||||
skip_manifests.add('dash')
|
||||
if self._configuration_arg('include_live_dash'):
|
||||
self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
|
||||
'Use include_incomplete_formats extractor argument instead')
|
||||
'Use formats=incomplete extractor argument instead')
|
||||
elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
|
||||
skip_manifests.add('dash')
|
||||
|
||||
@@ -3932,9 +3927,12 @@ def process_manifest_format(f, proto, client_name, itag):
|
||||
elif itag:
|
||||
f['format_id'] = itag
|
||||
|
||||
if f.get('source_preference') is None:
|
||||
f['source_preference'] = -1
|
||||
|
||||
if itag in ('616', '235'):
|
||||
f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
|
||||
f['source_preference'] = (f.get('source_preference') or -1) + 100
|
||||
f['source_preference'] += 100
|
||||
|
||||
f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
|
||||
if f['quality'] == -1 and f.get('height'):
|
||||
@@ -3943,6 +3941,10 @@ def process_manifest_format(f, proto, client_name, itag):
|
||||
f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
|
||||
if f.get('fps') and f['fps'] <= 1:
|
||||
del f['fps']
|
||||
|
||||
if proto == 'hls' and f.get('has_drm'):
|
||||
f['has_drm'] = 'maybe'
|
||||
f['source_preference'] -= 5
|
||||
return True
|
||||
|
||||
subtitles = {}
|
||||
@@ -4015,8 +4017,6 @@ def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
|
||||
webpage = None
|
||||
if 'webpage' not in self._configuration_arg('player_skip'):
|
||||
query = {'bpctr': '9999999999', 'has_verified': '1'}
|
||||
if smuggled_data.get('is_story'): # XXX: Deprecated
|
||||
query['pp'] = self._PLAYER_PARAMS
|
||||
webpage = self._download_webpage(
|
||||
webpage_url, video_id, fatal=False, query=query)
|
||||
|
||||
@@ -4044,6 +4044,10 @@ def _list_formats(self, video_id, microformats, video_details, player_responses,
|
||||
else None)
|
||||
streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
|
||||
*formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
|
||||
if all(f.get('has_drm') for f in formats):
|
||||
# If there are no formats that definitely don't have DRM, all have DRM
|
||||
for f in formats:
|
||||
f['has_drm'] = True
|
||||
|
||||
return live_broadcast_details, live_status, streaming_data, formats, subtitles
|
||||
|
||||
@@ -4228,7 +4232,7 @@ def is_bad_format(fmt):
|
||||
|
||||
for fmt in filter(is_bad_format, formats):
|
||||
fmt['preference'] = (fmt.get('preference') or -1) - 10
|
||||
fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 4 hours)', delim=' ')
|
||||
fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
|
||||
|
||||
if needs_live_processing:
|
||||
self._prepare_live_from_start_formats(
|
||||
@@ -4888,7 +4892,8 @@ def _extract_entries(self, parent_renderer, continuation_list):
|
||||
'videoRenderer': lambda x: [self._video_entry(x)],
|
||||
'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
|
||||
'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
|
||||
'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
|
||||
'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
|
||||
'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
|
||||
}
|
||||
for key, renderer in isr_content.items():
|
||||
if key not in known_renderers:
|
||||
@@ -6380,6 +6385,28 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
|
||||
'channel_is_verified': True,
|
||||
},
|
||||
'playlist_mincount': 10,
|
||||
}, {
|
||||
# Playlist with only shorts, shown as reel renderers
|
||||
# FIXME: future: YouTube currently doesn't give continuation for this,
|
||||
# may do in future.
|
||||
'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
|
||||
'info_dict': {
|
||||
'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
|
||||
'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
|
||||
'view_count': int,
|
||||
'uploader_id': '@BangyShorts',
|
||||
'description': '',
|
||||
'uploader_url': 'https://www.youtube.com/@BangyShorts',
|
||||
'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
|
||||
'channel': 'Bangy Shorts',
|
||||
'uploader': 'Bangy Shorts',
|
||||
'tags': [],
|
||||
'availability': 'public',
|
||||
'modified_date': '20230626',
|
||||
'title': 'Uploads from Bangy Shorts',
|
||||
},
|
||||
'playlist_mincount': 100,
|
||||
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
@@ -7104,22 +7131,6 @@ class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
|
||||
}]
|
||||
|
||||
|
||||
class YoutubeStoriesIE(InfoExtractor):
|
||||
IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
|
||||
IE_NAME = 'youtube:stories'
|
||||
_VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
|
||||
_TESTS = [{
|
||||
'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = f'RLTD{self._match_id(url)}'
|
||||
return self.url_result(
|
||||
smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
|
||||
ie=YoutubeTabIE, video_id=playlist_id)
|
||||
|
||||
|
||||
class YoutubeShortsAudioPivotIE(InfoExtractor):
|
||||
IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
|
||||
IE_NAME = 'youtube:shorts:pivot:audio'
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
# flake8: noqa: F401, F403
|
||||
import warnings
|
||||
|
||||
from ..compat.compat_utils import passthrough_module
|
||||
|
||||
@@ -1556,7 +1556,12 @@ def redirect_request(self, req, fp, code, msg, headers, newurl):
|
||||
|
||||
new_method = req.get_method()
|
||||
new_data = req.data
|
||||
remove_headers = []
|
||||
|
||||
# Technically the Cookie header should be in unredirected_hdrs,
|
||||
# however in practice some may set it in normal headers anyway.
|
||||
# We will remove it here to prevent any leaks.
|
||||
remove_headers = ['Cookie']
|
||||
|
||||
# A 303 must either use GET or HEAD for subsequent request
|
||||
# https://datatracker.ietf.org/doc/html/rfc7231#section-6.4.4
|
||||
if code == 303 and req.get_method() != 'HEAD':
|
||||
@@ -1573,7 +1578,7 @@ def redirect_request(self, req, fp, code, msg, headers, newurl):
|
||||
new_data = None
|
||||
remove_headers.extend(['Content-Length', 'Content-Type'])
|
||||
|
||||
new_headers = {k: v for k, v in req.headers.items() if k.lower() not in remove_headers}
|
||||
new_headers = {k: v for k, v in req.headers.items() if k.title() not in remove_headers}
|
||||
|
||||
return urllib.request.Request(
|
||||
newurl, headers=new_headers, origin_req_host=req.origin_req_host,
|
||||
@@ -3758,8 +3763,6 @@ def __init__(self, chapters, ranges, from_info=False):
|
||||
self.chapters, self.ranges, self.from_info = chapters, ranges, from_info
|
||||
|
||||
def __call__(self, info_dict, ydl):
|
||||
if not any((self.ranges, self.chapters, self.from_info)):
|
||||
yield {}
|
||||
|
||||
warning = ('There are no chapters matching the regex' if info_dict.get('chapters')
|
||||
else 'Cannot match chapters since chapter information is unavailable')
|
||||
@@ -3779,9 +3782,11 @@ def __call__(self, info_dict, ydl):
|
||||
|
||||
if self.from_info and (info_dict.get('start_time') or info_dict.get('end_time')):
|
||||
yield {
|
||||
'start_time': info_dict.get('start_time'),
|
||||
'end_time': info_dict.get('end_time'),
|
||||
'start_time': info_dict.get('start_time') or 0,
|
||||
'end_time': info_dict.get('end_time') or float('inf'),
|
||||
}
|
||||
elif not self.ranges and not self.chapters:
|
||||
yield {}
|
||||
|
||||
@staticmethod
|
||||
def _handle_negative_timestamp(time, info):
|
||||
@@ -5113,7 +5118,7 @@ def format_field(obj, field=None, template='%s', ignore=NO_DEFAULT, default='',
|
||||
|
||||
|
||||
def clean_podcast_url(url):
|
||||
return re.sub(r'''(?x)
|
||||
url = re.sub(r'''(?x)
|
||||
(?:
|
||||
(?:
|
||||
chtbl\.com/track|
|
||||
@@ -5127,6 +5132,7 @@ def clean_podcast_url(url):
|
||||
st\.fm # https://podsights.com/docs/
|
||||
)/e
|
||||
)/''', '', url)
|
||||
return re.sub(r'^\w+://(\w+://)', r'\1', url)
|
||||
|
||||
|
||||
_HEX_TABLE = '0123456789abcdef'
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# Autogenerated by devscripts/update-version.py
|
||||
|
||||
__version__ = '2023.06.22'
|
||||
__version__ = '2023.07.06'
|
||||
|
||||
RELEASE_GIT_HEAD = '812cdfa06c33a40e73a8e04b3e6f42c084666a43'
|
||||
RELEASE_GIT_HEAD = 'b532a3481046e1eabb6232ee8196fb696c356ff6'
|
||||
|
||||
VARIANT = None
|
||||
|
||||
|
||||
Reference in New Issue
Block a user