1
0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-12-17 06:35:42 +07:00

Compare commits

..

198 Commits

Author SHA1 Message Date
github-actions[bot]
b7de89c910 Release 2025.08.11
Created by: bashonly

:ci skip all
2025-08-11 03:54:46 +00:00
sepro
5e4ceb35cf [cleanup] Misc (#13852)
Closes #13815
Authored by: seproDev, injust, bashonly

Co-authored-by: Justin Su <injustsu@gmail.com>
Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-08-11 03:18:28 +00:00
bashonly
e98695549e [rh:curl_cffi] Support curl_cffi 0.11.x, 0.12.x, 0.13.x (#13989)
Authored by: bashonly
2025-08-11 03:16:07 +00:00
bashonly
bf366517ef [ie/youtube] Update player params (#13979)
Closes #13930
Authored by: bashonly
2025-08-10 07:33:45 +00:00
bashonly
c76ce28e06 Deprecate linux_armv7l_exe support (#13978)
Ref: https://github.com/yt-dlp/yt-dlp/issues/13976

Authored by: bashonly
2025-08-10 06:53:10 +00:00
Simon Sawicki
e8d49b1c7f [ie/motherless] Fix extractor (#13960)
Authored by: Grub4K
2025-08-07 21:04:30 -07:00
Sojiroh
a6df5e8a58 [ie/YandexDisk] Support 360 URLs (#13935)
Closes #13887
Authored by: Sojiroh
2025-08-07 23:16:55 +02:00
bashonly
e8d2807296 [ie/digitalconcerthall] Fix formats extraction (#13948)
Closes #13925
Authored by: bashonly
2025-08-07 00:03:44 +00:00
bashonly
fe53ebe5b6 [fd/dash] Re-extract if using --load-info-json with --live-from-start (#13922)
Closes #13906
Authored by: bashonly
2025-08-06 20:08:34 +00:00
sepro
662af5bb83 Warn when yt-dlp is severely outdated (#13937)
Authored by: seproDev
2025-08-06 21:14:45 +02:00
bashonly
8175f3738f [rh:requests] Bump minimum required version of urllib3 to 2.0.2 (#13939)
- urllib3 1.26.x gives unexpected results with partial reads: https://github.com/urllib3/urllib3/issues/2128
- urllib3 2.0.0 and 2.0.1 were yanked from PyPI: https://github.com/urllib3/urllib3/issues/3009

Closes #13927
Authored by: bashonly
2025-08-06 19:00:53 +00:00
sepro
1e0c77ddcc [pp/XAttrMetadata] Don't write "Where from" on Windows (#13944)
Fix 3e918d825d

Closes #13942
Authored by: seproDev
2025-08-06 16:52:34 +02:00
sepro
e651a53a2f Revert f799a4b472 2025-08-05 22:02:13 +02:00
sepro
f799a4b472 [ie/youtube] Update tv client config (#13934)
Closes #13930
Authored by: seproDev
2025-08-05 18:47:37 +02:00
coletdjnz
38c2bf4026 [ie/youtube] Add player params to mweb client (#13914)
Authored by: coletdjnz
2025-08-03 13:07:06 +12:00
Iuri Campos
6ff135c319 [ie/shiey] Add extractor (#13354)
Closes #12129
Authored by: iribeirocampos
2025-08-03 00:05:40 +02:00
JChris246
cd31c319e3 [ie/fc2] Fix old video support (#12633)
Closes #11778
Authored by: JChris246, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-08-02 23:37:35 +02:00
u-spec-png
6539ee1947 [ie/N1Info:article] Fix extractor (#13865)
Authored by: u-spec-png
2025-08-02 20:10:40 +00:00
CasperMcFadden95
43dedbe639 [ie/RoyaLive] Support en URLs (#13908)
Authored by: CasperMcFadden95
2025-08-02 19:59:30 +00:00
doe1080
05e553e9d1 [ie/niconico] Fix error handling & improve metadata extraction (#13240)
Closes #13338
Authored by: doe1080
2025-08-02 19:55:08 +00:00
doe1080
1c6068af99 [cleanup] Move embed tests to dedicated extractors (#13782)
Authored by: doe1080
2025-08-01 20:50:20 +00:00
garret1317
71f30921a2 [ie/tbsjp] Fix extractor (#13485)
Closes #13484
Authored by: garret1317
2025-07-31 20:33:05 +00:00
Abdulmohsen
121647705a [ie/TVer] Support --ignore-no-formats-error when geo-blocked (#13598)
Authored by: arabcoders
2025-07-30 23:23:06 +00:00
bashonly
70d7687487 [ie/TVer] Extract Streaks API info (#13885)
Closes #13874
Authored by: bashonly
2025-07-30 23:15:59 +00:00
bashonly
42ca3d601e [ie/archive.org] Fix metadata extraction (#13880)
Closes #13881
Authored by: bashonly
2025-07-30 06:11:09 +00:00
bashonly
62e2a9c0d5 [ci] Bump supported PyPy version to 3.11 (#13877)
Ref: https://pypy.org/posts/2025/07/pypy-v7320-release.html

Authored by: bashonly
2025-07-29 21:31:35 +00:00
bashonly
28b68f6875 [cookies] Load cookies with float expires timestamps (#13873)
Authored by: bashonly
2025-07-29 19:47:28 +00:00
fries1234
682334e4b3 [ie/tvw:news] Add extractor (#12907)
Authored by: fries1234
2025-07-27 22:26:33 +02:00
Florentin Le Moal
b831406a1d [ie/rtve.es:program] Add extractor
Authored by: meGAmeS1, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-27 21:52:05 +02:00
bashonly
23c658b9cb Raise minimum recommended Python version to 3.10 (#13859)
Ref: https://github.com/yt-dlp/yt-dlp/issues/13858

Authored by: bashonly
2025-07-26 22:59:02 +00:00
bashonly
cc5a5caac5 Deprecate darwin_legacy_exe support (#13857)
Ref: https://github.com/yt-dlp/yt-dlp/issues/13856

Authored by: bashonly
2025-07-26 22:12:53 +00:00
bashonly
66aa21dc5a [build] Use macos-14 runner for macos builds (#13814)
Ref: https://github.blog/changelog/2025-07-11-upcoming-changes-to-macos-hosted-runners-macos-latest-migration-and-xcode-support-policy-updates/#macos-13-is-closing-down

Authored by: bashonly
2025-07-26 19:39:54 +00:00
Tom Hebb
57186f958f [fd/hls] Fix --hls-split-continuity support (#13321)
Authored by: tchebb
2025-07-26 20:43:38 +02:00
CasperMcFadden95
daa1859be1 [ie/FaulioLive] Support Bahry TV (#13850)
Authored by: CasperMcFadden95
2025-07-26 20:11:57 +02:00
c-basalt
e8c2bf798b [ie/neteasemusic] Support XFF (#11044)
Closes #11043
Authored by: c-basalt
2025-07-26 20:02:56 +02:00
doe1080
1fe83b0111 [ie/eagleplatform] Remove extractors (#13469)
Authored by: doe1080
2025-07-26 17:34:22 +02:00
InvalidUsernameException
30302df22b [ie/sportdeuschland] Support embedded player URLs (#13833)
Closes #13766
Authored by: InvalidUsernameException
2025-07-25 22:22:32 +00:00
CasperMcFadden95
3e609b2ced [ie/FaulioLive] Add extractor (#13421)
Authored by: CasperMcFadden95, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-25 23:33:49 +02:00
bashonly
d399505fdf [fd/external] Work around ffmpeg's file: URL handling (#13844)
Closes #13781
Authored by: bashonly
2025-07-25 19:44:39 +00:00
sepro
61d4cd0bc0 [ie/PlyrEmbed] Add extractor (#13836)
Closes #13827
Authored by: seproDev
2025-07-25 20:55:41 +02:00
doe1080
4385480795 [utils] parse_resolution: Support width-only pattern (#13802)
Authored by: doe1080
2025-07-25 20:41:21 +02:00
Barry van Oudtshoorn
485de69dbf [ie/Parlview] Rework extractor (#13788)
Closes #13787
Authored by: barryvan
2025-07-25 06:00:31 +02:00
ischmidt20
0adeb1e54b [ie/tbs] Fix truTV support (#9683)
Closes #3400
Authored by: ischmidt20, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-07-24 22:35:48 +00:00
bashonly
afaf60d9fd [ie/vimeo] Fix login support and require authentication (#13823)
Closes #13822
Authored by: bashonly
2025-07-23 23:27:20 +00:00
Atsushi2965
7e3f48d64d [pp/EmbedThumbnail] Fix ffmpeg args for embedding in mp3 (#13720)
Authored by: atsushi2965
2025-07-22 21:55:00 +00:00
bashonly
59765ecbc0 [ie/sproutvideo] Fix extractor (#13813)
Authored by: bashonly
2025-07-22 21:46:46 +00:00
bashonly
c59ad2b066 [utils] random_user_agent: Bump versions (#13543)
Closes #5362
Authored by: bashonly
2025-07-22 21:34:03 +00:00
Simon Sawicki
eed94c7306 [utils] Add WINDOWS_VT_MODE to globals (#12460)
Authored by: Grub4K
2025-07-22 20:10:51 +02:00
Roland Crosby
3e918d825d [pp/XAttrMetadata] Add macOS "Where from" attribute (#12664)
Authored by: rolandcrosby
2025-07-22 19:50:42 +02:00
github-actions[bot]
035b1ece8f Release 2025.07.21
Created by: bashonly

:ci skip all
2025-07-21 23:47:12 +00:00
sepro
9951fdd0d0 [cleanup] Misc (#13595)
Closes #10853, Closes #12436, Closes #13314, Closes #13609
Authored by: seproDev, InvalidUsernameException, doe1080, hseg, bashonly, adamralph

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
Co-authored-by: InvalidUsernameException <InvalidUsernameException@users.noreply.github.com>
Co-authored-by: gesh <gesh@gesh.uni.cx>
Co-authored-by: Adam Ralph <adam@adamralph.com>
Co-authored-by: doe1080 <98906116+doe1080@users.noreply.github.com>
2025-07-21 23:43:30 +00:00
Simon Sawicki
959ac99e98 Fix --exec placeholder expansion on Windows
See https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-45hg-7f49-5h56 for more details

Authored by: Grub4K
2025-07-21 18:19:46 -05:00
bashonly
d88b304d44 [ie/patreon:campaign] Fix extractor (#13712)
Closes #13622
Authored by: bashonly
2025-07-21 23:15:31 +00:00
bashonly
b15aa8d772 [ie/BiliBiliBangumi] Fix extractor (#13800)
Closes #13795
Authored by: bashonly
2025-07-21 23:11:58 +00:00
c-basalt
d3edc5d52a [ie/bilibili] Pass newer user-agent with API requests (#13736)
Closes #12887
Authored by: c-basalt
2025-07-21 23:04:43 +00:00
doe1080
060c6a4501 [ie/skeb] Rework extractor (#13593)
Closes #7440
Authored by: doe1080
2025-07-21 22:32:10 +00:00
doe1080
6be26626f7 [utils] unified_timestamp: Return int values (#13796)
Authored by: doe1080
2025-07-21 21:59:13 +00:00
bashonly
ef103b2d11 [ie/hotstar] Fix error handling (#13793)
Fix 7e0af2b1f0

Closes #13790
Authored by: bashonly
2025-07-21 19:09:52 +00:00
bashonly
3e49bc8a1b Make extractor-designated impersonation override --impersonate (#13792)
Fix 32809eb2da

Authored by: bashonly
2025-07-21 18:42:21 +00:00
bashonly
2ac3eb9837 Fix ImpersonateTarget sanitization (#13791)
Fix 32809eb2da

Authored by: bashonly
2025-07-21 18:41:00 +00:00
bashonly
8820101aa3 [ie/youtube] Use impersonation for downloading subtitles (#13786)
Closes #13770
Authored by: bashonly
2025-07-20 23:22:04 +00:00
bashonly
a4561c7a66 [rh:requests] Refactor default headers (#13785)
Authored by: bashonly
2025-07-20 23:20:58 +00:00
bashonly
32809eb2da Allow extractors to designate formats/subtitles for impersonation (#13778)
Authored by: bashonly
2025-07-20 23:05:43 +00:00
WouterGordts
f9dff95cb1 [ie/bandcamp] Extract tags (#13480)
Authored by: WouterGordts
2025-07-20 20:12:40 +00:00
Tim
790c286ce3 [ie/10play] Support new site domain (#13611)
Closes #13577
Authored by: Georift
2025-07-20 20:00:44 +00:00
bashonly
87e3dc8c7f [ie/mlbtv] Make formats downloadable with ffmpeg (#13761)
Authored by: bashonly
2025-07-20 19:57:20 +00:00
R0hanW
1a8474c3ca [ie/PlayerFm] Add extractor (#13016)
Closes #4518
Authored by: R0hanW
2025-07-19 01:38:52 +02:00
bashonly
09982bc33e [ie/dangalplay] Support other login regions (#13768)
Authored by: bashonly
2025-07-18 23:24:52 +00:00
Víctor Schmidt
c8329fc572 [ie/rai] Fix formats extraction (#13572)
Closes #13548
Authored by: moonshinerd, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-18 22:43:04 +00:00
bashonly
1f27a9f8ba [core] Warn when skipping formats (#13090)
Authored by: bashonly
2025-07-18 21:59:50 +00:00
bashonly
4919051e44 [core] Don't let format testing alter the return code (#13767)
Closes #13750
Authored by: bashonly
2025-07-18 21:55:02 +00:00
bashonly
5f951ce929 [ie/aenetworks] Support new URL formats (#13747)
Closes #13745
Authored by: bashonly
2025-07-18 20:06:02 +00:00
bashonly
28bf46b7da [utils] urlhandle_detect_ext: Use x-amz-meta-file-type headers (#13749)
Authored by: bashonly
2025-07-18 19:46:06 +00:00
bashonly
b8abd255e4 [utils] mimetype2ext: Always parse flac from audio/flac (#13748)
Authored by: bashonly
2025-07-18 19:43:40 +00:00
bashonly
c1ac543c81 [ie/soundcloud] Always extract original format extension (#13746)
Closes #13743
Authored by: bashonly
2025-07-16 23:19:58 +00:00
flanter21
dcc4cba39e [ie/blackboardcollaborate] Support subtitles and authwalled videos (#12473)
Authored by: flanter21
2025-07-16 23:17:48 +00:00
Nikolay Fedorov
3a84be9d16 [ie/TheHighWire] Add extractor (#13505)
Closes #13364
Authored by: swayll
2025-07-14 19:01:53 +00:00
rdamas
d42a6ff0c4 [ie/archive.org] Fix extractor (#13706)
Closes #13704
Authored by: rdamas
2025-07-14 18:55:52 +00:00
bashonly
ade876efb3 [ie/francetv] Improve error handling (#13726)
Closes #13324
Authored by: bashonly
2025-07-14 17:25:45 +00:00
bashonly
7e0af2b1f0 [ie/hotstar] Improve error handling (#13727)
Authored by: bashonly
2025-07-14 17:24:52 +00:00
doe1080
d57a0b5aa7 [ie/noovo] Remove extractor (#13429)
Authored by: doe1080
2025-07-14 01:12:00 +02:00
doe1080
6fb3947c0d [ie/bellmedia] Remove extractor (#13429)
Authored by: doe1080
2025-07-14 01:12:00 +02:00
doe1080
9f54ea3898 [ie/ctv] Remove extractor (#13429)
Authored by: doe1080
2025-07-14 01:12:00 +02:00
chauhantirth
07d1d85f63 [ie/hotstar] Fix support for free accounts (#13700)
Fixes b5bd057fe8

Closes #13600
Authored by: chauhantirth
2025-07-13 22:35:26 +00:00
doe1080
5d693446e8 [ie/limelight] Remove extractors (#13267)
Authored by: doe1080
2025-07-14 00:10:59 +02:00
doe1080
23e9389f93 [ie/bandaichannel] Remove extractor (#13152)
Closes #8829
Authored by: doe1080
2025-07-13 23:53:47 +02:00
doe1080
6d39c420f7 [ie/JoqrAg] Remove extractor (#13152)
Authored by: doe1080
2025-07-13 23:53:47 +02:00
barsnick
85c3fa1925 [ie/RaiSudtirol] Support alternative domain (#13718)
Authored by: barsnick
2025-07-13 23:35:10 +02:00
Povilas Balzaravičius
b4b4486eff [ie/LRTRadio] Fix extractor (#13717)
Authored by: Pawka
2025-07-13 21:24:37 +00:00
Frank Cai
630f3389c3 [ie/UnitedNationsWebTv] Add extractor (#13538)
Closes #2675
Authored by: averageFOSSenjoyer
2025-07-13 23:16:01 +02:00
bashonly
a6db1d297a [ie/vimeo] Handle age-restricted videos (#13719)
Closes #13716
Authored by: bashonly
2025-07-13 21:09:39 +00:00
ShockedPlot7560
0f33950c77 [ie/mixlr] Add extractors (#13561)
Authored by: ShockedPlot7560, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-13 01:35:51 +02:00
bashonly
b5fea53f20 [ie] Rework _search_nextjs_v13_data helper (#13711)
Fix 5245231e4a

Authored by: bashonly
2025-07-12 23:12:05 +00:00
bashonly
5245231e4a [ie] Add _search_nextjs_v13_data helper (#13398)
* Fixes FranceTVSiteIE livestream extraction
* Fixes GoPlayIE metadata extraction

Authored by: bashonly
2025-07-12 22:12:46 +00:00
Lyuben Ivanov
3ae61e0f31 [ie/BTVPlus] Add extractor (#13541)
Authored by: bubo
2025-07-12 21:56:11 +02:00
bashonly
a5d697f62d [ie/vimeo] Fix extractor (#13692)
Closes #13180, Closes #13689
Authored by: bashonly
2025-07-12 19:23:22 +00:00
coletdjnz
6e5bee418b [ie/youtube] Ensure context params are consistent for web clients (#13701)
Authored by: coletdjnz
2025-07-12 13:44:27 +12:00
coletdjnz
5b57b72c1a [ie/youtube] Do not require PO Token for premium accounts (#13640)
Authored by: coletdjnz
2025-07-11 18:54:01 +12:00
doe1080
2aaf1aa71d [ie/newspicks] Fix extractor (#13612)
Closes #10472
Authored by: doe1080
2025-07-09 22:21:47 +00:00
Nikolay Fedorov
7b4c96e089 [ie/mir24.tv] Add extractor (#13651)
Closes #13365
Authored by: swayll
2025-07-09 22:16:33 +00:00
bashonly
0b359b184d [ie/9gag] Support browser impersonation (#13678)
Closes #10837
Authored by: bashonly
2025-07-09 21:58:19 +00:00
bashonly
805519bfaa [jsinterp] Fix undefined variable name caching (#13677)
Fix b342d27f3f

Authored by: bashonly
2025-07-09 20:45:47 +00:00
coletdjnz
aa9f1f4d57 [ie/youtube] Log bad playability statuses of player responses (#13647)
Authored by: coletdjnz
2025-07-09 18:29:54 +12:00
InvalidUsernameException
fd36b8f31b [test:download] Support playlist_maxcount (#13433)
Authored by: InvalidUsernameException
2025-07-08 04:19:03 +00:00
barsnick
99093e96fd [devscripts] Fix filename/directory Bash completions (#13620)
Closes #13619
Authored by: barsnick
2025-07-08 04:18:15 +00:00
garret1317
7c49a93788 [ie/NhkRadiru] Fix metadata extraction (#12708)
Authored by: garret1317
2025-07-08 03:55:19 +00:00
bashonly
884f35d54a [ie/BiliBiliBangumi] Fix geo-block detection (#13667)
Closes #13634
Authored by: bashonly
2025-07-08 03:54:27 +00:00
bashonly
c23d837b65 [ie/youtube:tab] Fix subscriptions feed extraction (#13665)
Adds support for LOCKUP_CONTENT_TYPE_VIDEO view models

Closes #13658
Authored by: bashonly
2025-07-07 20:25:34 +00:00
bashonly
a7113722ec [fd/hls] Do not fall back to ffmpeg when native is required (#13655)
Authored by: bashonly
2025-07-06 22:14:22 +00:00
bashonly
0e68332bcb [ie/youtube] Fix subtitles extraction (#13659)
Fixes regression introduced in 2ba5391cd6

Closes #13654
Authored by: bashonly
2025-07-06 22:07:21 +00:00
bashonly
422cc8cb2f [ie/twitch] Improve error handling (#13618)
Authored by: bashonly
2025-07-06 22:03:34 +00:00
bashonly
fca94ac5d6 [ie/youtube] Extract global nsig helper functions (#13639)
Authored by: bashonly, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-05 18:23:15 -05:00
bashonly
b342d27f3f [jsinterp] Cache undefined variable names (#13639)
Authored by: bashonly
2025-07-05 18:23:15 -05:00
bashonly
b6328ca050 [jsinterp] Fix variable scoping (#13639)
Authored by: bashonly, seproDev

Co-authored-by: sepro <sepro@sepr0.com>
2025-07-05 18:23:15 -05:00
bashonly
0b41746964 [ie/sproutvideo] Fix extractor (#13610)
Closes #13606
Authored by: bashonly
2025-07-02 13:21:06 +00:00
Simon Sawicki
c316416b97 [rh:requests] Do not allocate 2GB on read (#13603)
Fixes c2ff2dbaec

Authored by: Grub4K
2025-07-02 01:42:00 +02:00
Simon Sawicki
e99c0b838a [ie] Detect invalid m3u8 playlist data (#13601)
Authored by: Grub4K
2025-07-02 00:32:32 +02:00
Simon Sawicki
c2ff2dbaec [rh:requests] Work around partial read dropping data (#13599)
Authored by: Grub4K
2025-07-02 00:12:43 +02:00
sepro
ca5cce5b07 [cleanup] Bump ruff to 0.12.x (#13596)
Authored by: seproDev
2025-07-01 21:17:11 +02:00
sepro
f3008bc5f8 No longer enable --mtime by default (#12781)
Closes #12780
Authored by: seproDev
2025-07-01 13:23:53 +02:00
github-actions[bot]
30fa54280b Release 2025.06.30
Created by: bashonly

:ci skip all
2025-06-30 23:47:20 +00:00
bashonly
b018784498 [cleanup] Misc (#13590)
Authored by: bashonly
2025-06-30 23:44:42 +00:00
bashonly
11b9416e10 [ie/sproutvideo] Support browser impersonation (#13589)
Closes #13576
Authored by: bashonly
2025-06-30 23:37:56 +00:00
Clark
35fc33fbc5 [ie/sauceplus] Add extractor (#13567)
Authored by: ceandreasen, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-06-30 23:25:28 +00:00
helpimnotdrowning
b16722ede8 [ie/kick] Support subscriber-only content (#13550)
Closes #13442
Authored by: helpimnotdrowning
2025-06-30 23:24:04 +00:00
bashonly
500761e41a [ie] Fix m3u8 playlist data corruption (#13588)
Revert 7b81634fb1

Closes #13581
Authored by: bashonly
2025-06-30 23:06:22 +00:00
bashonly
2ba5391cd6 [ie/youtube] Fix premium formats extraction (#13586)
Fix ff6f94041a

Closes #13545
Authored by: bashonly
2025-06-30 23:02:59 +00:00
bashonly
e9f157669e [ie/hotstar] Fix formats extraction (#13585)
Fix b5bd057fe8

Authored by: bashonly
2025-06-30 19:19:43 +00:00
sepro
958153a226 [jsinterp] Fix extract_object (#13580)
Fixes sig extraction for YouTube player `e12fbea4`

Authored by: seproDev
2025-06-30 15:50:33 +02:00
bashonly
1b88384634 [ci] Add signature tests (#13582)
Authored by: bashonly
2025-06-30 13:05:52 +00:00
Simon Sawicki
7b81634fb1 [ie] Detect invalid m3u8 playlist data (#13563)
Authored by: Grub4K
2025-06-29 18:49:27 +02:00
bashonly
7e2504f941 [ie/jiocinema] Remove extractors (#13565)
Closes #10123, Closes #10144, Closes #10225, Closes #10240, Closes #10508
Authored by: bashonly
2025-06-28 23:32:21 +00:00
bashonly
4bd9a7ade7 [ie/hotstar:series] Fix extractor (#13564)
* Removes HotStarSeasonIE and HotStarPlaylistIE

Authored by: bashonly
2025-06-28 23:30:51 +00:00
chauhantirth
b5bd057fe8 [ie/hotstar] Fix extractor (#13530)
Closes #11195
Authored by: chauhantirth, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-06-28 02:29:43 +00:00
bashonly
5e292baad6 [ie/hotstar] Raise for login required (#10405)
Closes #10366
Authored by: bashonly
2025-06-27 22:31:06 +00:00
bashonly
0a6b104489 [ie/hotstar] Fix metadata extraction (#13560)
Closes #7946
Authored by: bashonly
2025-06-27 22:29:37 +00:00
doe1080
06c1a8cdff [ie/niconico:live] Fix extractor and downloader (#13158)
Authored by: doe1080
2025-06-26 17:45:03 +00:00
c-basalt
99b85ac102 [ie/BilibiliSpaceVideo] Extract hidden-mode collections as playlists (#13533)
Closes #13435
Authored by: c-basalt
2025-06-26 17:42:41 +00:00
github-actions[bot]
eff0759705 Release 2025.06.25
Created by: bashonly

:ci skip all
2025-06-25 23:53:38 +00:00
Anton Larionov
1838a1ce5d [ie/mave] Add extractor (#13380)
Authored by: anlar
2025-06-25 23:51:20 +00:00
doe1080
2600849bad [ie/huya:live] Fix extractor (#13520)
Authored by: doe1080
2025-06-25 23:37:49 +00:00
D Trombett
3bd3029160 [ie/tv8.it] Support slugless URLs (#13478)
Authored by: DTrombett
2025-06-25 23:26:23 +00:00
D Trombett
a4ce4327c9 [ie/SportDeutschland] Fix extractor (#13519)
Closes #13518
Authored by: DTrombett
2025-06-25 23:24:39 +00:00
Cæsim
c57412d1f9 [ie/lsm] Fix extractors (#13126)
Closes #12298
Authored by: Caesim404
2025-06-25 19:24:20 +00:00
bashonly
5b559d0072 [ie/sproutvideo] Fix extractor (#13544)
Closes #13540
Authored by: bashonly
2025-06-25 19:02:37 +00:00
bashonly
8f94b76cbf [ie/youtube] Check any ios m3u8 formats prior to download (#13524)
Closes #13511
Authored by: bashonly
2025-06-25 18:32:57 +00:00
bashonly
ff6f94041a [ie/youtube] Improve player context payloads (#13539)
Closes #12563
Authored by: bashonly
2025-06-25 17:10:00 +00:00
Simon Sawicki
73bf102116 [test] traversal: Fix morsel tests for Python 3.14 (#13471)
Authored by: Grub4K
2025-06-17 09:45:19 +02:00
doe1080
1722c55400 [ie/hypergryph] Improve metadata extraction (#13415)
Closes #13384
Authored by: doe1080, eason1478

Co-authored-by: eason1478 <134664337+eason1478@users.noreply.github.com>
2025-06-12 23:25:08 +00:00
doe1080
e6bd4a3da2 [ie/brightcove:new] Improve metadata extraction (#13461)
Authored by: doe1080
2025-06-12 23:16:48 +00:00
bashonly
51887484e4 [ie] Add _search_nuxt_json helper (#13386)
* Adds InfoExtractor._search_nuxt_json for webpage extraction
* Adds InfoExtractor._resolve_nuxt_array for direct use with payload JSON
* Adds yt_dlp.utils.jslib module for Python solutions to common JavaScript libraries
* Adds devalue.parse and devalue.parse_iter to jslib utils

Ref:
* 9e503be0f2
* f3fd2aa93d/src/parse.js

Authored by: bashonly, Grub4K

Co-authored-by: Simon Sawicki <contact@grub4k.dev>
2025-06-12 22:15:01 +00:00
github-actions[bot]
ba090caeaa Release 2025.06.09
Created by: bashonly

:ci skip all
2025-06-09 23:41:52 +00:00
bashonly
339614a173 [cleanup] Misc (#13278)
Authored by: bashonly
2025-06-09 23:39:00 +00:00
nullpos
aa863ddab9 [ie/cu.ntv.co.jp] Fix extractor (#13302)
Closes #10976
Authored by: nullpos, doe1080

Co-authored-by: doe1080 <98906116+doe1080@users.noreply.github.com>
2025-06-08 00:45:32 +00:00
InvalidUsernameException
db162b76f6 [ie/zdf] Fix language extraction and format sorting (#13313)
Closes #13118
Authored by: InvalidUsernameException
2025-06-08 00:10:01 +00:00
doe1080
e3c605a61f [ie/sr:mediathek] Improve metadata extraction (#13294)
Authored by: doe1080
2025-06-08 00:06:57 +00:00
doe1080
97ddfefeb4 [ie/nobelprize] Fix extractor (#13205)
Authored by: doe1080
2025-06-08 00:04:32 +00:00
doe1080
a8bf0011bd [ie/startrek] Fix extractor (#13188)
Authored by: doe1080
2025-06-07 23:16:31 +00:00
c-basalt
13e5516271 [ie/BiliBiliBangumi] Fix extractor (#13416)
Closes #13121
Authored by: c-basalt
2025-06-07 23:14:57 +00:00
bashonly
03dba2012d [ie/telecinco] Fix extractor (#13379)
Closes #13378
Authored by: bashonly
2025-06-06 22:02:26 +00:00
bashonly
5d96527be8 [ie/stacommu] Avoid partial stream formats (#13412)
Authored by: bashonly
2025-06-06 21:53:30 +00:00
gamer191
1fd0e88b67 [ie/youtube] Add tv_simply player client (#13389)
Authored by: gamer191
2025-06-06 21:50:36 +00:00
gamer191
231349786e [ie/youtube] Extract srt subtitles (#13411)
Closes #1734
Authored by: gamer191
2025-06-06 19:32:03 +00:00
Sipherdrakon
f37d599a69 [ie/aenetworks] Fix playlist extractors (#13408)
Fix 41952255d1

Authored by: Sipherdrakon
2025-06-06 09:50:21 +00:00
Simon Sawicki
9e38b273b7 [ie/youtube] Rework nsig function name extraction (#13403)
Closes #13401

Authored by: Grub4K
2025-06-05 23:50:58 +02:00
doe1080
4e7c1ea346 [ie/umg:de] Rework extractor (#13373)
Authored by: doe1080
2025-06-03 19:20:46 +00:00
barsnick
e1b6062f8c [ie/svt:play] Fix extractor (#13329)
Closes #13312
Authored by: barsnick, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-06-03 02:29:03 +00:00
bashonly
c723c4e5e7 [ie/vimeo] Extract subtitles from player subdomain (#13350)
Closes #12198
Authored by: bashonly
2025-06-01 23:20:29 +00:00
bashonly
148a1eb4c5 [ie/odnoklassniki] Detect and raise when login is required (#13361)
Closes #13360
Authored by: bashonly
2025-06-01 23:18:24 +00:00
bashonly
85c8a405e3 [ie] Improve JSON LD thumbnails extraction (#13368)
Authored by: bashonly, doe1080

Co-authored-by: doe1080 <98906116+doe1080@users.noreply.github.com>
2025-06-01 23:09:47 +00:00
Sipherdrakon
943083edcd [ie/adobepass] Fix Philo MSO authentication (#13335)
Closes #2603
Authored by: Sipherdrakon
2025-06-01 17:26:33 +00:00
bashonly
3fe72e9eea [ie/weverse] Support login with oauth refresh tokens (#13284)
Closes #7806
Authored by: bashonly
2025-05-30 23:20:59 +00:00
bashonly
d30a49742c [ie/youtube] Improve signature extraction debug output (#13327)
Authored by: bashonly
2025-05-30 23:16:47 +00:00
bashonly
6d265388c6 [ie/10play] Fix extractor (#13349)
Closes #12337
Authored by: bashonly
2025-05-30 22:51:25 +00:00
bashonly
a9b3700698 [test:postprocessors] Remove binary thumbnail test data (#13341)
Authored by: bashonly
2025-05-30 22:48:48 +00:00
bashonly
201812100f [build] Fix macOS requirements caching (#13328)
Authored by: bashonly
2025-05-28 18:13:48 +00:00
bashonly
cc749a8a3b [build] Exclude pkg_resources from being collected (#13320)
Closes #13311
Authored by: bashonly
2025-05-27 23:11:58 +00:00
bashonly
f7bbf5a617 [ie/youtube] nsig code improvements and cleanup (#13280)
Authored by: bashonly
2025-05-26 22:54:43 +00:00
Brian
b5be29fa58 [ie/youtube] Fix --mark-watched support (#13222)
Closes #11532
Authored by: iednod55, brian6932

Co-authored-by: iednod55 <210167282+iednod55@users.noreply.github.com>
2025-05-26 22:31:22 +00:00
bashonly
6121559e02 [ie/vice] Mark extractors as broken (#13131)
Authored by: bashonly
2025-05-26 15:57:19 -05:00
Max
2e5bf002da [ie/go] Fix provider-locked content extraction (#13131)
Closes #1770, Closes #8073
Authored by: maxbin123, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-05-26 15:57:19 -05:00
Max
6693d66033 [ie/aenetworks] Fix provider-locked content extraction (#13131)
Authored by: maxbin123
2025-05-26 15:57:19 -05:00
Max
b094747e93 [ie/WatchESPN] Fix provider-locked content extraction (#13131)
Closes #4662
Authored by: maxbin123
2025-05-26 15:57:19 -05:00
bashonly
98f8eec956 [ie/brightcove:new] Adapt to new AdobePass requirement (#13131)
Authored by: bashonly
2025-05-26 15:57:19 -05:00
bashonly
0daddc780d [ie/turner] Adapt extractors to new AdobePass flow (#13131)
Authored by: bashonly
2025-05-26 15:57:19 -05:00
bashonly
2d7949d564 [ie/nbc] Rework and adapt extractors to new AdobePass flow (#13131)
Closes #1032, Closes #10874, Closes #11148, Closes #12432
Authored by: bashonly
2025-05-26 15:57:19 -05:00
bashonly
ed108b3ea4 [ie/theplatform] Improve metadata extraction (#13131)
Authored by: bashonly
2025-05-26 15:57:19 -05:00
Max
eee90acc47 [ie/adobepass] Add Fubo MSO (#13131)
Closes #8287
Authored by: maxbin123
2025-05-26 15:57:19 -05:00
Max
711c5d5d09 [ie/adobepass] Rework to require software statement (#13131)
* Also removes broken cookie support

Closes #11811
Authored by: maxbin123, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2025-05-26 15:57:19 -05:00
bashonly
89c1b349ad [ie/adobepass] Validate login URL before sending credentials (#13131)
Authored by: bashonly
2025-05-26 15:57:19 -05:00
bashonly
0ee1102268 [ie/adobepass] Always add newer user-agent when required (#13131)
Fix dcfeea4dd5

Closes #516
Authored by: bashonly
2025-05-26 15:57:19 -05:00
doe1080
7794374de8 [ie/twitter:broadcast] Support events URLs (#13248)
Closes #12989
Authored by: doe1080
2025-05-23 19:25:56 +00:00
bashonly
538eb30567 [ie/podchaser] Fix extractor (#13271)
Closes #13269
Authored by: bashonly
2025-05-23 17:42:24 +00:00
doe1080
f8051e3a61 [ie/toutiao] Add extractor (#13246)
Closes #12125
Authored by: doe1080
2025-05-23 17:29:55 +00:00
bashonly
52f9729c9a [ie/twitcasting] Fix password-protected livestream support (#13097)
Closes #13096
Authored by: bashonly
2025-05-23 12:58:53 +00:00
bashonly
1a8a03ea8d [ie/patreon] Fix referer header used for embeds (#13276)
Fix e0d6c08229

Closes #13263
Authored by: bashonly
2025-05-23 12:53:36 +00:00
bashonly
e0d6c08229 [ie/patreon] Fix m3u8 formats extraction (#13266)
Closes #13263
Authored by: bashonly
2025-05-22 22:42:42 +00:00
bashonly
53ea743a9c [ie/youtube] Fix automatic captions for some client combinations (#13268)
Fix 32ed5f107c

Authored by: bashonly
2025-05-22 22:41:31 +00:00
222 changed files with 11923 additions and 10059 deletions

View File

@@ -208,7 +208,7 @@ jobs:
python3.9 -m pip install -U pip wheel 'setuptools>=71.0.2'
# XXX: Keep this in sync with pyproject.toml (it can't be accessed at this stage) and exclude secretstorage
python3.9 -m pip install -U Pyinstaller mutagen pycryptodomex brotli certifi cffi \
'requests>=2.32.2,<3' 'urllib3>=1.26.17,<3' 'websockets>=13.0'
'requests>=2.32.2,<3' 'urllib3>=2.0.2,<3' 'websockets>=13.0'
run: |
cd repo
@@ -242,7 +242,7 @@ jobs:
permissions:
contents: read
actions: write # For cleaning up cache
runs-on: macos-13
runs-on: macos-14
steps:
- uses: actions/checkout@v4
@@ -256,11 +256,13 @@ jobs:
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
key: cache-reqs-${{ github.job }}-${{ github.ref }}
- name: Install Requirements
run: |
brew install coreutils
# We need to use system Python in order to roll our own universal2 curl_cffi wheel
brew uninstall --ignore-dependencies python3
python3 -m venv ~/yt-dlp-build-venv
source ~/yt-dlp-build-venv/bin/activate
python3 devscripts/install_deps.py -o --include build
@@ -331,19 +333,16 @@ jobs:
if: steps.restore-cache.outputs.cache-hit == 'true'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
cache_key: cache-reqs-${{ github.job }}
repository: ${{ github.repository }}
branch: ${{ github.ref }}
cache_key: cache-reqs-${{ github.job }}-${{ github.ref }}
run: |
gh extension install actions/gh-actions-cache
gh actions-cache delete "${cache_key}" -R "${repository}" -B "${branch}" --confirm
gh cache delete "${cache_key}"
- name: Cache requirements
uses: actions/cache/save@v4
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
key: cache-reqs-${{ github.job }}-${{ github.ref }}
macos_legacy:
needs: process

View File

@@ -37,7 +37,7 @@ jobs:
matrix:
os: [ubuntu-latest]
# CPython 3.9 is in quick-test
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.10]
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
include:
# atleast one of each CPython/PyPy tests must be in windows
- os: windows-latest
@@ -49,7 +49,7 @@ jobs:
- os: windows-latest
python-version: '3.13'
- os: windows-latest
python-version: pypy-3.10
python-version: pypy-3.11
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}

View File

@@ -28,13 +28,13 @@ jobs:
fail-fast: true
matrix:
os: [ubuntu-latest]
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.10]
python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
include:
# atleast one of each CPython/PyPy tests must be in windows
- os: windows-latest
python-version: '3.9'
- os: windows-latest
python-version: pypy-3.10
python-version: pypy-3.11
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}

41
.github/workflows/signature-tests.yml vendored Normal file
View File

@@ -0,0 +1,41 @@
name: Signature Tests
on:
push:
paths:
- .github/workflows/signature-tests.yml
- test/test_youtube_signature.py
- yt_dlp/jsinterp.py
pull_request:
paths:
- .github/workflows/signature-tests.yml
- test/test_youtube_signature.py
- yt_dlp/jsinterp.py
permissions:
contents: read
concurrency:
group: signature-tests-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
tests:
name: Signature Tests
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, windows-latest]
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', pypy-3.11]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install test requirements
run: python3 ./devscripts/install_deps.py --only-optional --include test
- name: Run tests
timeout-minutes: 15
run: |
python3 -m yt_dlp -v || true # Print debug head
python3 ./devscripts/run_tests.py test/test_youtube_signature.py

2
.gitignore vendored
View File

@@ -105,6 +105,8 @@ README.txt
*.zsh
*.spec
test/testdata/sigs/player-*.js
test/testdata/thumbnails/empty.webp
test/testdata/thumbnails/foo\ %d\ bar/foo_%d.*
# Binary
/youtube-dl

View File

@@ -126,7 +126,7 @@ ### Are you willing to share account details if needed?
While these steps won't necessarily ensure that no misuse of the account takes place, these are still some good practices to follow.
- Look for people with `Member` (maintainers of the project) or `Contributor` (people who have previously contributed code) tag on their messages.
- Change the password before sharing the account to something random (use [this](https://passwordsgenerator.net/) if you don't have a random password generator).
- Change the password before sharing the account to something random.
- Change the password after receiving the account back.
### Is the website primarily used for piracy?
@@ -272,7 +272,7 @@ ## Adding support for a new site
You can use `hatch fmt` to automatically fix problems. Rules that the linter/formatter enforces should not be disabled with `# noqa` unless a maintainer requests it. The only exception allowed is for old/printf-style string formatting in GraphQL query templates (use `# noqa: UP031`).
1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython >=3.9 and PyPy >=3.10. Backward compatibility is not required for even older versions of Python.
1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython >=3.9 and PyPy >=3.11. Backward compatibility is not required for even older versions of Python.
1. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files, [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
```shell

View File

@@ -4,6 +4,7 @@ coletdjnz/colethedj (collaborator)
Ashish0804 (collaborator)
bashonly (collaborator)
Grub4K (collaborator)
seproDev (collaborator)
h-h-h-h
pauldubois98
nixxo
@@ -403,7 +404,6 @@ rebane2001
road-master
rohieb
sdht0
seproDev
Hill-98
LXYan2333
mushbite
@@ -775,3 +775,28 @@ GeoffreyFrogeye
Pawka
v3DJG6GL
yozel
brian6932
iednod55
maxbin123
nullpos
anlar
eason1478
ceandreasen
chauhantirth
helpimnotdrowning
adamralph
averageFOSSenjoyer
bubo
flanter21
Georift
moonshinerd
R0hanW
ShockedPlot7560
swayll
atsushi2965
barryvan
injust
iribeirocampos
rolandcrosby
Sojiroh
tchebb

View File

@@ -4,6 +4,267 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2025.08.11
#### Important changes
- **The minimum *recommended* Python version has been raised to 3.10**
Since Python 3.9 will reach end-of-life in October 2025, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13858)
- **darwin_legacy_exe builds are being discontinued**
This release's `yt-dlp_macos_legacy` binary will likely be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13857)
- **linux_armv7l_exe builds are being discontinued**
This release's `yt-dlp_linux_armv7l` binary could be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13976)
#### Core changes
- [Deprecate `darwin_legacy_exe` support](https://github.com/yt-dlp/yt-dlp/commit/cc5a5caac5fbc0d605b52bde0778d6fd5f97b5ab) ([#13857](https://github.com/yt-dlp/yt-dlp/issues/13857)) by [bashonly](https://github.com/bashonly)
- [Deprecate `linux_armv7l_exe` support](https://github.com/yt-dlp/yt-dlp/commit/c76ce28e06c816eb5b261dfb6aff6e69dd9b7382) ([#13978](https://github.com/yt-dlp/yt-dlp/issues/13978)) by [bashonly](https://github.com/bashonly)
- [Raise minimum recommended Python version to 3.10](https://github.com/yt-dlp/yt-dlp/commit/23c658b9cbe34a151f8f921ab1320bb5d4e40a4d) ([#13859](https://github.com/yt-dlp/yt-dlp/issues/13859)) by [bashonly](https://github.com/bashonly)
- [Warn when yt-dlp is severely outdated](https://github.com/yt-dlp/yt-dlp/commit/662af5bb8307ec3ff8ab0857f1159922d64792f0) ([#13937](https://github.com/yt-dlp/yt-dlp/issues/13937)) by [seproDev](https://github.com/seproDev)
- **cookies**: [Load cookies with float `expires` timestamps](https://github.com/yt-dlp/yt-dlp/commit/28b68f687561468e0c664dcb430707458970019f) ([#13873](https://github.com/yt-dlp/yt-dlp/issues/13873)) by [bashonly](https://github.com/bashonly)
- **utils**
- [Add `WINDOWS_VT_MODE` to globals](https://github.com/yt-dlp/yt-dlp/commit/eed94c7306d4ecdba53ad8783b1463a9af5c97f1) ([#12460](https://github.com/yt-dlp/yt-dlp/issues/12460)) by [Grub4K](https://github.com/Grub4K)
- `parse_resolution`: [Support width-only pattern](https://github.com/yt-dlp/yt-dlp/commit/4385480795acda35667be008d0bf26b46e9d65b4) ([#13802](https://github.com/yt-dlp/yt-dlp/issues/13802)) by [doe1080](https://github.com/doe1080)
- `random_user_agent`: [Bump versions](https://github.com/yt-dlp/yt-dlp/commit/c59ad2b066bbccd3cc4eed580842f961bce7dd4a) ([#13543](https://github.com/yt-dlp/yt-dlp/issues/13543)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **archive.org**: [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/42ca3d601ee10cef89d698f72e2b5d44fab4f013) ([#13880](https://github.com/yt-dlp/yt-dlp/issues/13880)) by [bashonly](https://github.com/bashonly)
- **digitalconcerthall**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/e8d2807296ccc603e031f5982623a8311f2a5119) ([#13948](https://github.com/yt-dlp/yt-dlp/issues/13948)) by [bashonly](https://github.com/bashonly)
- **eagleplatform**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/1fe83b0111277a6f214c5ec1819cfbf943508baf) ([#13469](https://github.com/yt-dlp/yt-dlp/issues/13469)) by [doe1080](https://github.com/doe1080)
- **fauliolive**
- [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3e609b2cedd285739bf82c7af7853735092070a4) ([#13421](https://github.com/yt-dlp/yt-dlp/issues/13421)) by [CasperMcFadden95](https://github.com/CasperMcFadden95), [seproDev](https://github.com/seproDev)
- [Support Bahry TV](https://github.com/yt-dlp/yt-dlp/commit/daa1859be1b0e7d123da8b4e0988f2eb7bd47d15) ([#13850](https://github.com/yt-dlp/yt-dlp/issues/13850)) by [CasperMcFadden95](https://github.com/CasperMcFadden95)
- **fc2**: [Fix old video support](https://github.com/yt-dlp/yt-dlp/commit/cd31c319e3142622ec43c49485d196ed2835df05) ([#12633](https://github.com/yt-dlp/yt-dlp/issues/12633)) by [JChris246](https://github.com/JChris246), [seproDev](https://github.com/seproDev)
- **motherless**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e8d49b1c7f11c7e282319395ca9c2a201304be41) ([#13960](https://github.com/yt-dlp/yt-dlp/issues/13960)) by [Grub4K](https://github.com/Grub4K)
- **n1info**: article: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6539ee1947d7885d3606da6365fd858308435a63) ([#13865](https://github.com/yt-dlp/yt-dlp/issues/13865)) by [u-spec-png](https://github.com/u-spec-png)
- **neteasemusic**: [Support XFF](https://github.com/yt-dlp/yt-dlp/commit/e8c2bf798b6707d27fecde66161172da69c7cd72) ([#11044](https://github.com/yt-dlp/yt-dlp/issues/11044)) by [c-basalt](https://github.com/c-basalt)
- **niconico**: [Fix error handling & improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/05e553e9d1f57655d65c9811d05df38261601b85) ([#13240](https://github.com/yt-dlp/yt-dlp/issues/13240)) by [doe1080](https://github.com/doe1080)
- **parlview**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/485de69dbfeb7de7bcf9f7fe16d6c6ba9e81e1a0) ([#13788](https://github.com/yt-dlp/yt-dlp/issues/13788)) by [barryvan](https://github.com/barryvan)
- **plyrembed**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/61d4cd0bc01be6ebe11fd53c2d3805d1a2058990) ([#13836](https://github.com/yt-dlp/yt-dlp/issues/13836)) by [seproDev](https://github.com/seproDev)
- **royalive**: [Support `en` URLs](https://github.com/yt-dlp/yt-dlp/commit/43dedbe6394bdd489193b15ee9690a62d1b82d94) ([#13908](https://github.com/yt-dlp/yt-dlp/issues/13908)) by [CasperMcFadden95](https://github.com/CasperMcFadden95)
- **rtve.es**: program: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b831406a1d3be34c159835079d12bae624c43610) ([#12955](https://github.com/yt-dlp/yt-dlp/issues/12955)) by [meGAmeS1](https://github.com/meGAmeS1), [seproDev](https://github.com/seproDev)
- **shiey**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/6ff135c31914ea8b5545f8d187c60e852cfde9bc) ([#13354](https://github.com/yt-dlp/yt-dlp/issues/13354)) by [iribeirocampos](https://github.com/iribeirocampos)
- **sportdeuschland**: [Support embedded player URLs](https://github.com/yt-dlp/yt-dlp/commit/30302df22b7b431ce920e0f7298cd10be9989967) ([#13833](https://github.com/yt-dlp/yt-dlp/issues/13833)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/59765ecbc08d18005de7143fbb1d1caf90239471) ([#13813](https://github.com/yt-dlp/yt-dlp/issues/13813)) by [bashonly](https://github.com/bashonly)
- **tbs**: [Fix truTV support](https://github.com/yt-dlp/yt-dlp/commit/0adeb1e54b2d7e95cd19999e71013877850f8f41) ([#9683](https://github.com/yt-dlp/yt-dlp/issues/9683)) by [bashonly](https://github.com/bashonly), [ischmidt20](https://github.com/ischmidt20)
- **tbsjp**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/71f30921a2023dbb25c53fd1bb1399cac803116d) ([#13485](https://github.com/yt-dlp/yt-dlp/issues/13485)) by [garret1317](https://github.com/garret1317)
- **tver**
- [Extract Streaks API info](https://github.com/yt-dlp/yt-dlp/commit/70d7687487252a08dbf8b2831743e7833472ba05) ([#13885](https://github.com/yt-dlp/yt-dlp/issues/13885)) by [bashonly](https://github.com/bashonly)
- [Support --ignore-no-formats-error when geo-blocked](https://github.com/yt-dlp/yt-dlp/commit/121647705a2fc6b968278723fe61801007e228a4) ([#13598](https://github.com/yt-dlp/yt-dlp/issues/13598)) by [arabcoders](https://github.com/arabcoders)
- **tvw**: news: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/682334e4b35112f7a5798decdcb5cb12230ef948) ([#12907](https://github.com/yt-dlp/yt-dlp/issues/12907)) by [fries1234](https://github.com/fries1234)
- **vimeo**: [Fix login support and require authentication](https://github.com/yt-dlp/yt-dlp/commit/afaf60d9fd5a0c7a85aeb1374fd97fbc13cd652c) ([#13823](https://github.com/yt-dlp/yt-dlp/issues/13823)) by [bashonly](https://github.com/bashonly)
- **yandexdisk**: [Support 360 URLs](https://github.com/yt-dlp/yt-dlp/commit/a6df5e8a58d6743dd230011389c986495ec509da) ([#13935](https://github.com/yt-dlp/yt-dlp/issues/13935)) by [Sojiroh](https://github.com/Sojiroh)
- **youtube**
- [Add player params to mweb client](https://github.com/yt-dlp/yt-dlp/commit/38c2bf40260f7788efb5a7f5e8eba8e5cb43f741) ([#13914](https://github.com/yt-dlp/yt-dlp/issues/13914)) by [coletdjnz](https://github.com/coletdjnz)
- [Update player params](https://github.com/yt-dlp/yt-dlp/commit/bf366517ef0b745490ee9e0f929254fa26b69647) ([#13979](https://github.com/yt-dlp/yt-dlp/issues/13979)) by [bashonly](https://github.com/bashonly)
#### Downloader changes
- **dash**: [Re-extract if using --load-info-json with --live-from-start](https://github.com/yt-dlp/yt-dlp/commit/fe53ebe5b66a03c664708a4d6fd87b8c13a1bc7b) ([#13922](https://github.com/yt-dlp/yt-dlp/issues/13922)) by [bashonly](https://github.com/bashonly)
- **external**: [Work around ffmpeg's `file:` URL handling](https://github.com/yt-dlp/yt-dlp/commit/d399505fdf8292332bdc91d33859a0b0d08104fd) ([#13844](https://github.com/yt-dlp/yt-dlp/issues/13844)) by [bashonly](https://github.com/bashonly)
- **hls**: [Fix `--hls-split-continuity` support](https://github.com/yt-dlp/yt-dlp/commit/57186f958f164daa50203adcbf7ec74d541151cf) ([#13321](https://github.com/yt-dlp/yt-dlp/issues/13321)) by [tchebb](https://github.com/tchebb)
#### Postprocessor changes
- **embedthumbnail**: [Fix ffmpeg args for embedding in mp3](https://github.com/yt-dlp/yt-dlp/commit/7e3f48d64d237281a97b3df1a61980c78a0302fe) ([#13720](https://github.com/yt-dlp/yt-dlp/issues/13720)) by [atsushi2965](https://github.com/atsushi2965)
- **xattrmetadata**: [Add macOS "Where from" attribute](https://github.com/yt-dlp/yt-dlp/commit/3e918d825d7ff367812658957b281b8cda8f9ebb) ([#12664](https://github.com/yt-dlp/yt-dlp/issues/12664)) by [rolandcrosby](https://github.com/rolandcrosby) (With fixes in [1e0c77d](https://github.com/yt-dlp/yt-dlp/commit/1e0c77ddcce335a1875ecc17d93ed6ff3fabd975) by [seproDev](https://github.com/seproDev))
#### Networking changes
- **Request Handler**
- curl_cffi: [Support `curl_cffi` 0.11.x, 0.12.x, 0.13.x](https://github.com/yt-dlp/yt-dlp/commit/e98695549e2eb8ce4a59abe16b5afa8adc075bbe) ([#13989](https://github.com/yt-dlp/yt-dlp/issues/13989)) by [bashonly](https://github.com/bashonly)
- requests: [Bump minimum required version of urllib3 to 2.0.2](https://github.com/yt-dlp/yt-dlp/commit/8175f3738fe4db3bc629d36bb72b927d4286d3f9) ([#13939](https://github.com/yt-dlp/yt-dlp/issues/13939)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**: [Use `macos-14` runner for `macos` builds](https://github.com/yt-dlp/yt-dlp/commit/66aa21dc5a3b79059c38f3ad1d05dc9b29187701) ([#13814](https://github.com/yt-dlp/yt-dlp/issues/13814)) by [bashonly](https://github.com/bashonly)
- **ci**: [Bump supported PyPy version to 3.11](https://github.com/yt-dlp/yt-dlp/commit/62e2a9c0d55306906f18da2927e05e1cbc31473c) ([#13877](https://github.com/yt-dlp/yt-dlp/issues/13877)) by [bashonly](https://github.com/bashonly)
- **cleanup**
- [Move embed tests to dedicated extractors](https://github.com/yt-dlp/yt-dlp/commit/1c6068af997cfc0e28061fc00f4d6091e1de57da) ([#13782](https://github.com/yt-dlp/yt-dlp/issues/13782)) by [doe1080](https://github.com/doe1080)
- Miscellaneous: [5e4ceb3](https://github.com/yt-dlp/yt-dlp/commit/5e4ceb35cf997af0dbf100e1de37f4e2bcbaa0b7) by [bashonly](https://github.com/bashonly), [injust](https://github.com/injust), [seproDev](https://github.com/seproDev)
### 2025.07.21
#### Important changes
- **Default behaviour changed from `--mtime` to `--no-mtime`**
yt-dlp no longer applies the server modified time to downloaded files by default. [Read more](https://github.com/yt-dlp/yt-dlp/issues/12780)
- Security: [[CVE-2025-54072](https://nvd.nist.gov/vuln/detail/CVE-2025-54072)] [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-45hg-7f49-5h56)
- When `--exec` is used on Windows, the filepath expanded from `{}` (or the default placeholder) is now properly escaped
#### Core changes
- [Allow extractors to designate formats/subtitles for impersonation](https://github.com/yt-dlp/yt-dlp/commit/32809eb2da92c649e540a5b714f6235036026161) ([#13778](https://github.com/yt-dlp/yt-dlp/issues/13778)) by [bashonly](https://github.com/bashonly) (With fixes in [3e49bc8](https://github.com/yt-dlp/yt-dlp/commit/3e49bc8a1bdb4109b857f2c361c358e86fa63405), [2ac3eb9](https://github.com/yt-dlp/yt-dlp/commit/2ac3eb98373d1c31341c5e918c83872c7ff409c6))
- [Don't let format testing alter the return code](https://github.com/yt-dlp/yt-dlp/commit/4919051e447c7f8ae9df8ba5c4208b6b5c04915a) ([#13767](https://github.com/yt-dlp/yt-dlp/issues/13767)) by [bashonly](https://github.com/bashonly)
- [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/commit/959ac99e98c3215437e573c22d64be42d361e863) by [Grub4K](https://github.com/Grub4K)
- [No longer enable `--mtime` by default](https://github.com/yt-dlp/yt-dlp/commit/f3008bc5f89d2691f2f8dfc51b406ef4e25281c3) ([#12781](https://github.com/yt-dlp/yt-dlp/issues/12781)) by [seproDev](https://github.com/seproDev)
- [Warn when skipping formats](https://github.com/yt-dlp/yt-dlp/commit/1f27a9f8baccb9105f2476154557540efe09a937) ([#13090](https://github.com/yt-dlp/yt-dlp/issues/13090)) by [bashonly](https://github.com/bashonly)
- **jsinterp**
- [Cache undefined variable names](https://github.com/yt-dlp/yt-dlp/commit/b342d27f3f82d913976509ddf5bff539ad8567ec) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly) (With fixes in [805519b](https://github.com/yt-dlp/yt-dlp/commit/805519bfaa7cb5443912dfe45ac774834ba65a16))
- [Fix variable scoping](https://github.com/yt-dlp/yt-dlp/commit/b6328ca05030d815222b25d208cc59a964623bf9) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- **utils**
- `mimetype2ext`: [Always parse `flac` from `audio/flac`](https://github.com/yt-dlp/yt-dlp/commit/b8abd255e454acbe0023cdb946f9eb461ced7eeb) ([#13748](https://github.com/yt-dlp/yt-dlp/issues/13748)) by [bashonly](https://github.com/bashonly)
- `unified_timestamp`: [Return `int` values](https://github.com/yt-dlp/yt-dlp/commit/6be26626f7cfa71d28e0fac2861eb04758810c5d) ([#13796](https://github.com/yt-dlp/yt-dlp/issues/13796)) by [doe1080](https://github.com/doe1080)
- `urlhandle_detect_ext`: [Use `x-amz-meta-file-type` headers](https://github.com/yt-dlp/yt-dlp/commit/28bf46b7dafe2e241137763bf570a2f91ba8a53a) ([#13749](https://github.com/yt-dlp/yt-dlp/issues/13749)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- [Add `_search_nextjs_v13_data` helper](https://github.com/yt-dlp/yt-dlp/commit/5245231e4a39ecd5595d4337d46d85e150e2430a) ([#13398](https://github.com/yt-dlp/yt-dlp/issues/13398)) by [bashonly](https://github.com/bashonly) (With fixes in [b5fea53](https://github.com/yt-dlp/yt-dlp/commit/b5fea53f2099bed41ba1b17ab0ac87c8dba5a5ec))
- [Detect invalid m3u8 playlist data](https://github.com/yt-dlp/yt-dlp/commit/e99c0b838a9c5feb40c0dcd291bd7b8620b8d36d) ([#13601](https://github.com/yt-dlp/yt-dlp/issues/13601)) by [Grub4K](https://github.com/Grub4K)
- **10play**: [Support new site domain](https://github.com/yt-dlp/yt-dlp/commit/790c286ce3e0b534ca2d8f6648ced220d888f139) ([#13611](https://github.com/yt-dlp/yt-dlp/issues/13611)) by [Georift](https://github.com/Georift)
- **9gag**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/0b359b184dee0c7052be482857bf562de67e4928) ([#13678](https://github.com/yt-dlp/yt-dlp/issues/13678)) by [bashonly](https://github.com/bashonly)
- **aenetworks**: [Support new URL formats](https://github.com/yt-dlp/yt-dlp/commit/5f951ce929b56a822514f1a02cc06af030855ec7) ([#13747](https://github.com/yt-dlp/yt-dlp/issues/13747)) by [bashonly](https://github.com/bashonly)
- **archive.org**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d42a6ff0c4ca8893d722ff4e0c109aecbf4cc7cf) ([#13706](https://github.com/yt-dlp/yt-dlp/issues/13706)) by [rdamas](https://github.com/rdamas)
- **bandaichannel**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/23e9389f936ec5236a87815b8576e5ce567b2f77) ([#13152](https://github.com/yt-dlp/yt-dlp/issues/13152)) by [doe1080](https://github.com/doe1080)
- **bandcamp**: [Extract tags](https://github.com/yt-dlp/yt-dlp/commit/f9dff95cb1c138913011417b3bba020c0a691bba) ([#13480](https://github.com/yt-dlp/yt-dlp/issues/13480)) by [WouterGordts](https://github.com/WouterGordts)
- **bellmedia**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/6fb3947c0dc6d0e3eab5077c5bada8402f47a277) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
- **bilibili**: [Pass newer user-agent with API requests](https://github.com/yt-dlp/yt-dlp/commit/d3edc5d52a7159eda2331dbc7e14bf40a6585c81) ([#13736](https://github.com/yt-dlp/yt-dlp/issues/13736)) by [c-basalt](https://github.com/c-basalt)
- **bilibilibangumi**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b15aa8d77257b86fa44c9a42a615dfe47ac5b3b7) ([#13800](https://github.com/yt-dlp/yt-dlp/issues/13800)) by [bashonly](https://github.com/bashonly)
- [Fix geo-block detection](https://github.com/yt-dlp/yt-dlp/commit/884f35d54a64f1e6e7be49459842f573fc3a2701) ([#13667](https://github.com/yt-dlp/yt-dlp/issues/13667)) by [bashonly](https://github.com/bashonly)
- **blackboardcollaborate**: [Support subtitles and authwalled videos](https://github.com/yt-dlp/yt-dlp/commit/dcc4cba39e2a79d3efce16afa28dbe245468489f) ([#12473](https://github.com/yt-dlp/yt-dlp/issues/12473)) by [flanter21](https://github.com/flanter21)
- **btvplus**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3ae61e0f313dd03a09060abc7a212775c3717818) ([#13541](https://github.com/yt-dlp/yt-dlp/issues/13541)) by [bubo](https://github.com/bubo)
- **ctv**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/9f54ea38984788811773ca2ceaca73864acf0e8a) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
- **dangalplay**: [Support other login regions](https://github.com/yt-dlp/yt-dlp/commit/09982bc33e2f1f9a1ff66e6738df44f15b36f6a6) ([#13768](https://github.com/yt-dlp/yt-dlp/issues/13768)) by [bashonly](https://github.com/bashonly)
- **francetv**: [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/ade876efb31d55d3394185ffc56942fdc8d325cc) ([#13726](https://github.com/yt-dlp/yt-dlp/issues/13726)) by [bashonly](https://github.com/bashonly)
- **hotstar**
- [Fix support for free accounts](https://github.com/yt-dlp/yt-dlp/commit/07d1d85f6387e4bdb107096f0131c7054f078bb9) ([#13700](https://github.com/yt-dlp/yt-dlp/issues/13700)) by [chauhantirth](https://github.com/chauhantirth)
- [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/7e0af2b1f0c3edb688603b022f3a9ca0bfdf75e9) ([#13727](https://github.com/yt-dlp/yt-dlp/issues/13727)) by [bashonly](https://github.com/bashonly) (With fixes in [ef103b2](https://github.com/yt-dlp/yt-dlp/commit/ef103b2d115bd0e880f9cfd2f7dd705f48e4b40d))
- **joqrag**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/6d39c420f7774562a106d90253e2ed5b75036321) ([#13152](https://github.com/yt-dlp/yt-dlp/issues/13152)) by [doe1080](https://github.com/doe1080)
- **limelight**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/5d693446e882931618c40c99bb593f0b87b30eb9) ([#13267](https://github.com/yt-dlp/yt-dlp/issues/13267)) by [doe1080](https://github.com/doe1080)
- **lrtradio**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b4b4486effdcb96bb6b8148171a49ff579b69a4a) ([#13717](https://github.com/yt-dlp/yt-dlp/issues/13717)) by [Pawka](https://github.com/Pawka)
- **mir24.tv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/7b4c96e0898db048259ef5fdf12ed14e3605dce3) ([#13651](https://github.com/yt-dlp/yt-dlp/issues/13651)) by [swayll](https://github.com/swayll)
- **mixlr**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/0f33950c778331bf4803c76e8b0ba1862df93431) ([#13561](https://github.com/yt-dlp/yt-dlp/issues/13561)) by [seproDev](https://github.com/seproDev), [ShockedPlot7560](https://github.com/ShockedPlot7560)
- **mlbtv**: [Make formats downloadable with ffmpeg](https://github.com/yt-dlp/yt-dlp/commit/87e3dc8c7f78929d2ef4f4a44e6a567e04cd8226) ([#13761](https://github.com/yt-dlp/yt-dlp/issues/13761)) by [bashonly](https://github.com/bashonly)
- **newspicks**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2aaf1aa71d174700859c9ec1a81109b78e34961c) ([#13612](https://github.com/yt-dlp/yt-dlp/issues/13612)) by [doe1080](https://github.com/doe1080)
- **nhkradiru**: [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/7c49a937887756efcfa162abdcf17e48c244cb0c) ([#12708](https://github.com/yt-dlp/yt-dlp/issues/12708)) by [garret1317](https://github.com/garret1317)
- **noovo**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/d57a0b5aa78d59324b037d37492fe86aa4fbf58a) ([#13429](https://github.com/yt-dlp/yt-dlp/issues/13429)) by [doe1080](https://github.com/doe1080)
- **patreon**: campaign: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d88b304d44c599d81acfa4231502270c8b9fe2f8) ([#13712](https://github.com/yt-dlp/yt-dlp/issues/13712)) by [bashonly](https://github.com/bashonly)
- **playerfm**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1a8474c3ca6dbe51bb153b2b8eef7b9a61fa7dc3) ([#13016](https://github.com/yt-dlp/yt-dlp/issues/13016)) by [R0hanW](https://github.com/R0hanW)
- **rai**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/c8329fc572903eeed7edad1642773b2268b71a62) ([#13572](https://github.com/yt-dlp/yt-dlp/issues/13572)) by [moonshinerd](https://github.com/moonshinerd), [seproDev](https://github.com/seproDev)
- **raisudtirol**: [Support alternative domain](https://github.com/yt-dlp/yt-dlp/commit/85c3fa1925a9057ef4ae8af682686d5b3eb8e568) ([#13718](https://github.com/yt-dlp/yt-dlp/issues/13718)) by [barsnick](https://github.com/barsnick)
- **skeb**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/060c6a4501a0b8a92f1b9c12788f556d902c83c6) ([#13593](https://github.com/yt-dlp/yt-dlp/issues/13593)) by [doe1080](https://github.com/doe1080)
- **soundcloud**: [Always extract original format extension](https://github.com/yt-dlp/yt-dlp/commit/c1ac543c8166ff031d62e340b3244ca8556e3fb9) ([#13746](https://github.com/yt-dlp/yt-dlp/issues/13746)) by [bashonly](https://github.com/bashonly)
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0b41746964e1d0470ac286ce09408940a3a51147) ([#13610](https://github.com/yt-dlp/yt-dlp/issues/13610)) by [bashonly](https://github.com/bashonly)
- **thehighwire**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3a84be9d1660ef798ea28f929a20391bef6afda4) ([#13505](https://github.com/yt-dlp/yt-dlp/issues/13505)) by [swayll](https://github.com/swayll)
- **twitch**: [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/422cc8cb2ff2bd3b4c2bc64e23507b7e6f522c35) ([#13618](https://github.com/yt-dlp/yt-dlp/issues/13618)) by [bashonly](https://github.com/bashonly)
- **unitednationswebtv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/630f3389c33f0f7f6ec97e8917d20aeb4e4078da) ([#13538](https://github.com/yt-dlp/yt-dlp/issues/13538)) by [averageFOSSenjoyer](https://github.com/averageFOSSenjoyer)
- **vimeo**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a5d697f62d8be78ffd472acb2f52c8bc32833003) ([#13692](https://github.com/yt-dlp/yt-dlp/issues/13692)) by [bashonly](https://github.com/bashonly)
- [Handle age-restricted videos](https://github.com/yt-dlp/yt-dlp/commit/a6db1d297ab40cc346de24aacbeab93112b2f4e1) ([#13719](https://github.com/yt-dlp/yt-dlp/issues/13719)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Do not require PO Token for premium accounts](https://github.com/yt-dlp/yt-dlp/commit/5b57b72c1a7c6bd249ffcebdf5630761ec664c10) ([#13640](https://github.com/yt-dlp/yt-dlp/issues/13640)) by [coletdjnz](https://github.com/coletdjnz)
- [Ensure context params are consistent for web clients](https://github.com/yt-dlp/yt-dlp/commit/6e5bee418bc108565108153fd745c8e7a59f16dd) ([#13701](https://github.com/yt-dlp/yt-dlp/issues/13701)) by [coletdjnz](https://github.com/coletdjnz)
- [Extract global nsig helper functions](https://github.com/yt-dlp/yt-dlp/commit/fca94ac5d63ed6578b5cd9c8129d97a8a713c39a) ([#13639](https://github.com/yt-dlp/yt-dlp/issues/13639)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- [Fix subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/0e68332bcb9fba87c42805b7a051eeb2bed36206) ([#13659](https://github.com/yt-dlp/yt-dlp/issues/13659)) by [bashonly](https://github.com/bashonly)
- [Log bad playability statuses of player responses](https://github.com/yt-dlp/yt-dlp/commit/aa9f1f4d577e99897ac16cd19d4e217d688ea75d) ([#13647](https://github.com/yt-dlp/yt-dlp/issues/13647)) by [coletdjnz](https://github.com/coletdjnz)
- [Use impersonation for downloading subtitles](https://github.com/yt-dlp/yt-dlp/commit/8820101aa3152e5f4811541c645f8b5de231ba8c) ([#13786](https://github.com/yt-dlp/yt-dlp/issues/13786)) by [bashonly](https://github.com/bashonly)
- tab: [Fix subscriptions feed extraction](https://github.com/yt-dlp/yt-dlp/commit/c23d837b6524d1e7a4595948871ba1708cba4dfa) ([#13665](https://github.com/yt-dlp/yt-dlp/issues/13665)) by [bashonly](https://github.com/bashonly)
#### Downloader changes
- **hls**: [Do not fall back to ffmpeg when native is required](https://github.com/yt-dlp/yt-dlp/commit/a7113722ec33f30fc898caee9242af2b82188a53) ([#13655](https://github.com/yt-dlp/yt-dlp/issues/13655)) by [bashonly](https://github.com/bashonly)
#### Networking changes
- **Request Handler**
- requests
- [Refactor default headers](https://github.com/yt-dlp/yt-dlp/commit/a4561c7a66c39d88efe7ae51e7fa1986faf093fb) ([#13785](https://github.com/yt-dlp/yt-dlp/issues/13785)) by [bashonly](https://github.com/bashonly)
- [Work around partial read dropping data](https://github.com/yt-dlp/yt-dlp/commit/c2ff2dbaec7929015373fe002e9bd4849931a4ce) ([#13599](https://github.com/yt-dlp/yt-dlp/issues/13599)) by [Grub4K](https://github.com/Grub4K) (With fixes in [c316416](https://github.com/yt-dlp/yt-dlp/commit/c316416b972d1b05e58fbcc21e80428b900ce102))
#### Misc. changes
- **cleanup**
- [Bump ruff to 0.12.x](https://github.com/yt-dlp/yt-dlp/commit/ca5cce5b07d51efe7310b449cdefeca8d873e9df) ([#13596](https://github.com/yt-dlp/yt-dlp/issues/13596)) by [seproDev](https://github.com/seproDev)
- Miscellaneous: [9951fdd](https://github.com/yt-dlp/yt-dlp/commit/9951fdd0d08b655cb1af8cd7f32a3fb7e2b1324e) by [adamralph](https://github.com/adamralph), [bashonly](https://github.com/bashonly), [doe1080](https://github.com/doe1080), [hseg](https://github.com/hseg), [InvalidUsernameException](https://github.com/InvalidUsernameException), [seproDev](https://github.com/seproDev)
- **devscripts**: [Fix filename/directory Bash completions](https://github.com/yt-dlp/yt-dlp/commit/99093e96fd6a26dea9d6e4bd1e4b16283b6ad1ee) ([#13620](https://github.com/yt-dlp/yt-dlp/issues/13620)) by [barsnick](https://github.com/barsnick)
- **test**: download: [Support `playlist_maxcount`](https://github.com/yt-dlp/yt-dlp/commit/fd36b8f31bafbd8096bdb92a446a0c9c6081209c) ([#13433](https://github.com/yt-dlp/yt-dlp/issues/13433)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
### 2025.06.30
#### Core changes
- **jsinterp**: [Fix `extract_object`](https://github.com/yt-dlp/yt-dlp/commit/958153a226214c86879e36211ac191bf78289578) ([#13580](https://github.com/yt-dlp/yt-dlp/issues/13580)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **bilibilispacevideo**: [Extract hidden-mode collections as playlists](https://github.com/yt-dlp/yt-dlp/commit/99b85ac102047446e6adf5b62bfc3c8d80b53778) ([#13533](https://github.com/yt-dlp/yt-dlp/issues/13533)) by [c-basalt](https://github.com/c-basalt)
- **hotstar**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b5bd057fe86550f3aa67f2fc8790d1c6a251c57b) ([#13530](https://github.com/yt-dlp/yt-dlp/issues/13530)) by [bashonly](https://github.com/bashonly), [chauhantirth](https://github.com/chauhantirth) (With fixes in [e9f1576](https://github.com/yt-dlp/yt-dlp/commit/e9f157669e24953a88d15ce22053649db7a8e81e) by [bashonly](https://github.com/bashonly))
- [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0a6b1044899f452cd10b6c7a6b00fa985a9a8b97) ([#13560](https://github.com/yt-dlp/yt-dlp/issues/13560)) by [bashonly](https://github.com/bashonly)
- [Raise for login required](https://github.com/yt-dlp/yt-dlp/commit/5e292baad62c749b6c340621ab2d0f904165ddfb) ([#10405](https://github.com/yt-dlp/yt-dlp/issues/10405)) by [bashonly](https://github.com/bashonly)
- series: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4bd9a7ade7e0508b9795b3e72a69eeb40788b62b) ([#13564](https://github.com/yt-dlp/yt-dlp/issues/13564)) by [bashonly](https://github.com/bashonly)
- **jiocinema**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/7e2504f941a11ea2b0dba00de3f0295cdc253e79) ([#13565](https://github.com/yt-dlp/yt-dlp/issues/13565)) by [bashonly](https://github.com/bashonly)
- **kick**: [Support subscriber-only content](https://github.com/yt-dlp/yt-dlp/commit/b16722ede83377f77ea8352dcd0a6ca8e83b8f0f) ([#13550](https://github.com/yt-dlp/yt-dlp/issues/13550)) by [helpimnotdrowning](https://github.com/helpimnotdrowning)
- **niconico**: live: [Fix extractor and downloader](https://github.com/yt-dlp/yt-dlp/commit/06c1a8cdffe14050206683253726875144192ef5) ([#13158](https://github.com/yt-dlp/yt-dlp/issues/13158)) by [doe1080](https://github.com/doe1080)
- **sauceplus**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/35fc33fbc51c7f5392fb2300f65abf6cf107ef90) ([#13567](https://github.com/yt-dlp/yt-dlp/issues/13567)) by [bashonly](https://github.com/bashonly), [ceandreasen](https://github.com/ceandreasen)
- **sproutvideo**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/11b9416e10cff7513167d76d6c47774fcdd3e26a) ([#13589](https://github.com/yt-dlp/yt-dlp/issues/13589)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix premium formats extraction](https://github.com/yt-dlp/yt-dlp/commit/2ba5391cd68ed4f2415c827d2cecbcbc75ace10b) ([#13586](https://github.com/yt-dlp/yt-dlp/issues/13586)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **ci**: [Add signature tests](https://github.com/yt-dlp/yt-dlp/commit/1b883846347addeab12663fd74317fd544341a1c) ([#13582](https://github.com/yt-dlp/yt-dlp/issues/13582)) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [b018784](https://github.com/yt-dlp/yt-dlp/commit/b0187844988e557c7e1e6bb1aabd4c1176768d86) by [bashonly](https://github.com/bashonly)
### 2025.06.25
#### Extractor changes
- [Add `_search_nuxt_json` helper](https://github.com/yt-dlp/yt-dlp/commit/51887484e46ab6015c041cb1ab626a55f25a03bd) ([#13386](https://github.com/yt-dlp/yt-dlp/issues/13386)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- **brightcove**: new: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/e6bd4a3da295b760ab20b39c18ce8934d312c2bf) ([#13461](https://github.com/yt-dlp/yt-dlp/issues/13461)) by [doe1080](https://github.com/doe1080)
- **huya**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2600849badb0d08c55b58dcc77a13af6ba423da6) ([#13520](https://github.com/yt-dlp/yt-dlp/issues/13520)) by [doe1080](https://github.com/doe1080)
- **hypergryph**: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/1722c55400ff30bb5aee5dd7a262f0b7e9ce2f0e) ([#13415](https://github.com/yt-dlp/yt-dlp/issues/13415)) by [doe1080](https://github.com/doe1080), [eason1478](https://github.com/eason1478)
- **lsm**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/c57412d1f9cf0124adc972a47858ac42b740c61d) ([#13126](https://github.com/yt-dlp/yt-dlp/issues/13126)) by [Caesim404](https://github.com/Caesim404)
- **mave**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1838a1ce5d4ade80770ba9162eaffc9a1607dc70) ([#13380](https://github.com/yt-dlp/yt-dlp/issues/13380)) by [anlar](https://github.com/anlar)
- **sportdeutschland**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a4ce4327c9836691d3b6b00e44a90b6741601ed8) ([#13519](https://github.com/yt-dlp/yt-dlp/issues/13519)) by [DTrombett](https://github.com/DTrombett)
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/5b559d0072b7164daf06bacdc41c6f11283452c8) ([#13544](https://github.com/yt-dlp/yt-dlp/issues/13544)) by [bashonly](https://github.com/bashonly)
- **tv8.it**: [Support slugless URLs](https://github.com/yt-dlp/yt-dlp/commit/3bd30291601c47fa4a257983473884103ecab0c7) ([#13478](https://github.com/yt-dlp/yt-dlp/issues/13478)) by [DTrombett](https://github.com/DTrombett)
- **youtube**
- [Check any `ios` m3u8 formats prior to download](https://github.com/yt-dlp/yt-dlp/commit/8f94b76cbf7bbd9dfd8762c63cdea04f90f1297f) ([#13524](https://github.com/yt-dlp/yt-dlp/issues/13524)) by [bashonly](https://github.com/bashonly)
- [Improve player context payloads](https://github.com/yt-dlp/yt-dlp/commit/ff6f94041aeee19c5559e1c1cd693960a1c1dd14) ([#13539](https://github.com/yt-dlp/yt-dlp/issues/13539)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **test**: `traversal`: [Fix morsel tests for Python 3.14](https://github.com/yt-dlp/yt-dlp/commit/73bf10211668e4a59ccafd790e06ee82d9fea9ea) ([#13471](https://github.com/yt-dlp/yt-dlp/issues/13471)) by [Grub4K](https://github.com/Grub4K)
### 2025.06.09
#### Extractor changes
- [Improve JSON LD thumbnails extraction](https://github.com/yt-dlp/yt-dlp/commit/85c8a405e3651dc041b758f4744d4fb3c4c55e01) ([#13368](https://github.com/yt-dlp/yt-dlp/issues/13368)) by [bashonly](https://github.com/bashonly), [doe1080](https://github.com/doe1080)
- **10play**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6d265388c6e943419ac99e9151cf75a3265f980f) ([#13349](https://github.com/yt-dlp/yt-dlp/issues/13349)) by [bashonly](https://github.com/bashonly)
- **adobepass**
- [Add Fubo MSO](https://github.com/yt-dlp/yt-dlp/commit/eee90acc47d7f8de24afaa8b0271ccaefdf6e88c) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- [Always add newer user-agent when required](https://github.com/yt-dlp/yt-dlp/commit/0ee1102268cf31b07f8a8318a47424c66b2f7378) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- [Fix Philo MSO authentication](https://github.com/yt-dlp/yt-dlp/commit/943083edcd3df45aaa597a6967bc6c95b720f54c) ([#13335](https://github.com/yt-dlp/yt-dlp/issues/13335)) by [Sipherdrakon](https://github.com/Sipherdrakon)
- [Rework to require software statement](https://github.com/yt-dlp/yt-dlp/commit/711c5d5d098fee2992a1a624b1c4b30364b91426) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly), [maxbin123](https://github.com/maxbin123)
- [Validate login URL before sending credentials](https://github.com/yt-dlp/yt-dlp/commit/89c1b349ad81318d9d3bea76c01c891696e58d38) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **aenetworks**
- [Fix playlist extractors](https://github.com/yt-dlp/yt-dlp/commit/f37d599a697e82fe68b423865897d55bae34f373) ([#13408](https://github.com/yt-dlp/yt-dlp/issues/13408)) by [Sipherdrakon](https://github.com/Sipherdrakon)
- [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/6693d6603358ae6beca834dbd822a7917498b813) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- **bilibilibangumi**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/13e55162719528d42d2133e16b65ff59a667a6e4) ([#13416](https://github.com/yt-dlp/yt-dlp/issues/13416)) by [c-basalt](https://github.com/c-basalt)
- **brightcove**: new: [Adapt to new AdobePass requirement](https://github.com/yt-dlp/yt-dlp/commit/98f8eec956e3b16cb66a3d49cc71af3807db795e) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **cu.ntv.co.jp**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/aa863ddab9b1d104678e9cf39bb76f5b14fca660) ([#13302](https://github.com/yt-dlp/yt-dlp/issues/13302)) by [doe1080](https://github.com/doe1080), [nullpos](https://github.com/nullpos)
- **go**: [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/2e5bf002dad16f5ce35aa2023d392c9e518fcd8f) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly), [maxbin123](https://github.com/maxbin123)
- **nbc**: [Rework and adapt extractors to new AdobePass flow](https://github.com/yt-dlp/yt-dlp/commit/2d7949d5642bc37d1e71bf00c9a55260e5505d58) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **nobelprize**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/97ddfefeb4faba6e61cd80996c16952b8eab16f3) ([#13205](https://github.com/yt-dlp/yt-dlp/issues/13205)) by [doe1080](https://github.com/doe1080)
- **odnoklassniki**: [Detect and raise when login is required](https://github.com/yt-dlp/yt-dlp/commit/148a1eb4c59e127965396c7a6e6acf1979de459e) ([#13361](https://github.com/yt-dlp/yt-dlp/issues/13361)) by [bashonly](https://github.com/bashonly)
- **patreon**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/e0d6c0822930f6e63f574d46d946a58b73ecd10c) ([#13266](https://github.com/yt-dlp/yt-dlp/issues/13266)) by [bashonly](https://github.com/bashonly) (With fixes in [1a8a03e](https://github.com/yt-dlp/yt-dlp/commit/1a8a03ea8d827107319a18076ee3505090667c5a))
- **podchaser**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/538eb305673c26bff6a2b12f1c96375fe02ce41a) ([#13271](https://github.com/yt-dlp/yt-dlp/issues/13271)) by [bashonly](https://github.com/bashonly)
- **sr**: mediathek: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/e3c605a61f4cc2de9059f37434fa108c3c20f58e) ([#13294](https://github.com/yt-dlp/yt-dlp/issues/13294)) by [doe1080](https://github.com/doe1080)
- **stacommu**: [Avoid partial stream formats](https://github.com/yt-dlp/yt-dlp/commit/5d96527be80dc1ed1702d9cd548ff86de570ad70) ([#13412](https://github.com/yt-dlp/yt-dlp/issues/13412)) by [bashonly](https://github.com/bashonly)
- **startrek**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a8bf0011bde92b3f1324a98bfbd38932fd3ebe18) ([#13188](https://github.com/yt-dlp/yt-dlp/issues/13188)) by [doe1080](https://github.com/doe1080)
- **svt**: play: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e1b6062f8c4a3fa33c65269d48d09ec78de765a2) ([#13329](https://github.com/yt-dlp/yt-dlp/issues/13329)) by [barsnick](https://github.com/barsnick), [bashonly](https://github.com/bashonly)
- **telecinco**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/03dba2012d9bd3f402fa8c2f122afba89bbd22a4) ([#13379](https://github.com/yt-dlp/yt-dlp/issues/13379)) by [bashonly](https://github.com/bashonly)
- **theplatform**: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/ed108b3ea481c6a4b5215a9302ba92d74baa2425) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **toutiao**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/f8051e3a61686c5db1de5f5746366ecfbc3ad20c) ([#13246](https://github.com/yt-dlp/yt-dlp/issues/13246)) by [doe1080](https://github.com/doe1080)
- **turner**: [Adapt extractors to new AdobePass flow](https://github.com/yt-dlp/yt-dlp/commit/0daddc780d3ac5bebc3a3ec5b884d9243cbc0745) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **twitcasting**: [Fix password-protected livestream support](https://github.com/yt-dlp/yt-dlp/commit/52f9729c9a92ad4656d746ff0b1acecb87b3e96d) ([#13097](https://github.com/yt-dlp/yt-dlp/issues/13097)) by [bashonly](https://github.com/bashonly)
- **twitter**: broadcast: [Support events URLs](https://github.com/yt-dlp/yt-dlp/commit/7794374de8afb20499b023107e2abfd4e6b93ee4) ([#13248](https://github.com/yt-dlp/yt-dlp/issues/13248)) by [doe1080](https://github.com/doe1080)
- **umg**: de: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/4e7c1ea346b510280218b47e8653dbbca3a69870) ([#13373](https://github.com/yt-dlp/yt-dlp/issues/13373)) by [doe1080](https://github.com/doe1080)
- **vice**: [Mark extractors as broken](https://github.com/yt-dlp/yt-dlp/commit/6121559e027a04574690799c1776bc42bb51af31) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Extract subtitles from player subdomain](https://github.com/yt-dlp/yt-dlp/commit/c723c4e5e78263df178dbe69844a3d05f3ef9e35) ([#13350](https://github.com/yt-dlp/yt-dlp/issues/13350)) by [bashonly](https://github.com/bashonly)
- **watchespn**: [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/b094747e93cfb0a2c53007120e37d0d84d41f030) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- **weverse**: [Support login with oauth refresh tokens](https://github.com/yt-dlp/yt-dlp/commit/3fe72e9eea38d9a58211cde42cfaa577ce020e2c) ([#13284](https://github.com/yt-dlp/yt-dlp/issues/13284)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Add `tv_simply` player client](https://github.com/yt-dlp/yt-dlp/commit/1fd0e88b67db53ad163393d6965f68e908fa70e3) ([#13389](https://github.com/yt-dlp/yt-dlp/issues/13389)) by [gamer191](https://github.com/gamer191)
- [Extract srt subtitles](https://github.com/yt-dlp/yt-dlp/commit/231349786e8c42089c2e079ec94c0ea866c37999) ([#13411](https://github.com/yt-dlp/yt-dlp/issues/13411)) by [gamer191](https://github.com/gamer191)
- [Fix `--mark-watched` support](https://github.com/yt-dlp/yt-dlp/commit/b5be29fa58ec98226e11621fd9c58585bcff6879) ([#13222](https://github.com/yt-dlp/yt-dlp/issues/13222)) by [brian6932](https://github.com/brian6932), [iednod55](https://github.com/iednod55)
- [Fix automatic captions for some client combinations](https://github.com/yt-dlp/yt-dlp/commit/53ea743a9c158f8ca2d75a09ca44ba68606042d8) ([#13268](https://github.com/yt-dlp/yt-dlp/issues/13268)) by [bashonly](https://github.com/bashonly)
- [Improve signature extraction debug output](https://github.com/yt-dlp/yt-dlp/commit/d30a49742cfa22e61c47df4ac0e7334d648fb85d) ([#13327](https://github.com/yt-dlp/yt-dlp/issues/13327)) by [bashonly](https://github.com/bashonly)
- [Rework nsig function name extraction](https://github.com/yt-dlp/yt-dlp/commit/9e38b273b7ac942e7e9fc05a651ed810ab7d30ba) ([#13403](https://github.com/yt-dlp/yt-dlp/issues/13403)) by [Grub4K](https://github.com/Grub4K)
- [nsig code improvements and cleanup](https://github.com/yt-dlp/yt-dlp/commit/f7bbf5a617f9ab54ef51eaef99be36e175b5e9c3) ([#13280](https://github.com/yt-dlp/yt-dlp/issues/13280)) by [bashonly](https://github.com/bashonly)
- **zdf**: [Fix language extraction and format sorting](https://github.com/yt-dlp/yt-dlp/commit/db162b76f6bdece50babe2e0cacfe56888c2e125) ([#13313](https://github.com/yt-dlp/yt-dlp/issues/13313)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
#### Misc. changes
- **build**
- [Exclude `pkg_resources` from being collected](https://github.com/yt-dlp/yt-dlp/commit/cc749a8a3b8b6e5c05318868c72a403f376a1b38) ([#13320](https://github.com/yt-dlp/yt-dlp/issues/13320)) by [bashonly](https://github.com/bashonly)
- [Fix macOS requirements caching](https://github.com/yt-dlp/yt-dlp/commit/201812100f315c6727a4418698d5b4e8a79863d4) ([#13328](https://github.com/yt-dlp/yt-dlp/issues/13328)) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [339614a](https://github.com/yt-dlp/yt-dlp/commit/339614a173c74b42d63e858c446a9cae262a13af) by [bashonly](https://github.com/bashonly)
- **test**: postprocessors: [Remove binary thumbnail test data](https://github.com/yt-dlp/yt-dlp/commit/a9b370069838e84d44ac7ad095d657003665885a) ([#13341](https://github.com/yt-dlp/yt-dlp/issues/13341)) by [bashonly](https://github.com/bashonly)
### 2025.05.22
#### Core changes

View File

@@ -18,10 +18,11 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
tar pypi-files lazy-extractors install uninstall
clean-test:
rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
rm -rf tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp \
test/testdata/sigs/player-*.js test/testdata/thumbnails/empty.webp "test/testdata/thumbnails/foo %d bar/foo_%d."*
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS

View File

@@ -171,8 +171,11 @@ # To install nightly with pip:
python3 -m pip install -U --pre "yt-dlp[default]"
```
When running a yt-dlp version that is older than 90 days, you will see a warning message suggesting to update to the latest version.
You can suppress this warning by adding `--no-update` to your command or configuration file.
## DEPENDENCIES
Python versions 3.9+ (CPython) and 3.10+ (PyPy) are supported. Other versions and implementations may or may not work correctly.
Python versions 3.9+ (CPython) and 3.11+ (PyPy) are supported. Other versions and implementations may or may not work correctly.
<!-- Python 3.5+ uses VC++14 and it is already embedded in the binary created
<!x-- https://www.microsoft.com/en-us/download/details.aspx?id=26999 --x>
@@ -208,7 +211,7 @@ ### Metadata
* [**mutagen**](https://github.com/quodlibet/mutagen)\* - For `--embed-thumbnail` in certain formats. Licensed under [GPLv2+](https://github.com/quodlibet/mutagen/blob/master/COPYING)
* [**AtomicParsley**](https://github.com/wez/atomicparsley) - For `--embed-thumbnail` in `mp4`/`m4a` files when `mutagen`/`ffmpeg` cannot. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING)
* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattr`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattrs`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
### Misc
@@ -277,7 +280,7 @@ # USAGE AND OPTIONS
<!-- MANPAGE: BEGIN EXCLUDED SECTION -->
yt-dlp [OPTIONS] [--] URL [URL...]
`Ctrl+F` is your friend :D
Tip: Use `CTRL`+`F` (or `Command`+`F`) to search by keywords
<!-- MANPAGE: END EXCLUDED SECTION -->
<!-- Auto generated -->
@@ -639,9 +642,9 @@ ## Filesystem Options:
--no-part Do not use .part files - write directly into
output file
--mtime Use the Last-modified header to set the file
modification time (default)
modification time
--no-mtime Do not use the Last-modified header to set
the file modification time
the file modification time (default)
--write-description Write video description to a .description file
--no-write-description Do not write video description (default)
--write-info-json Write video metadata to a .info.json file
@@ -1156,15 +1159,15 @@ # CONFIGURATION
* `/etc/yt-dlp/config`
* `/etc/yt-dlp/config.txt`
E.g. with the following configuration file, yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
E.g. with the following configuration file, yt-dlp will always extract the audio, copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
```
# Lines starting with # are comments
# Always extract audio
-x
# Do not copy the mtime
--no-mtime
# Copy the mtime
--mtime
# Use this proxy
--proxy 127.0.0.1:3128
@@ -1795,10 +1798,11 @@ # EXTRACTOR ARGUMENTS
The following extractors use this feature:
#### youtube
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube/_base.py](https://github.com/yt-dlp/yt-dlp/blob/415b4c9f955b1a0391204bd24a7132590e7b3bdb/yt_dlp/extractor/youtube/_base.py#L402-L409) for the list of supported content language codes
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
* `webpage_skip`: Skip extraction of embedded webpage data. One or both of `player_response`, `initial_data`. These options are for testing purposes and don't skip any network requests
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@@ -1900,6 +1904,10 @@ #### sonylivseries
#### tver
* `backend`: Backend API to use for extraction - one of `streaks` (default) or `brightcove` (deprecated)
#### vimeo
* `client`: Client to extract video data from. The currently available clients are `android`, `ios`, and `web`. Only one client can be used. The `web` client is used by default. The `web` client only works with account cookies or login credentials. The `android` and `ios` clients only work with previously cached OAuth tokens
* `original_format_policy`: Policy for when to try extracting original formats. One of `always`, `never`, or `auto`. The default `auto` policy tries to avoid exceeding the web client's API rate-limit by only making an extra request when Vimeo publicizes the video's downloadability
**Note**: These options may be changed/removed in the future without concern for backward compatibility
<!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
@@ -2262,6 +2270,7 @@ ### Differences in default behavior
* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
* The sub-modules `swfinterp`, `casefold` are removed.
* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
* yt-dlp no longer applies the server modified time to downloaded files by default. Use `--mtime` or `--compat-options mtime-by-default` to revert this.
For ease of use, a few more compat options are available:
@@ -2271,7 +2280,7 @@ ### Differences in default behavior
* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization`
* `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
* `--compat-options 2023`: Same as `--compat-options 2024,prefer-vp9-sort`
* `--compat-options 2024`: Currently does nothing. Use this to enable all future compat options
* `--compat-options 2024`: Same as `--compat-options mtime-by-default`. Use this to enable all future compat options
The following compat options restore vulnerable behavior from before security patches:
@@ -2361,7 +2370,6 @@ #### Old aliases
--dump-headers --print-traffic
--dump-intermediate-pages --dump-pages
--force-write-download-archive --force-write-archive
--load-info --load-info-json
--no-clean-infojson --no-clean-info-json
--no-split-tracks --no-split-chapters
--no-write-srt --no-write-subs

View File

@@ -2,6 +2,7 @@
set -e
source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
python -m devscripts.install_deps -o --include build
python -m devscripts.install_deps --include secretstorage --include curl-cffi
python -m devscripts.make_lazy_extractors
python devscripts/update-version.py -c "${channel}" -r "${origin}" "${version}"

View File

@@ -36,6 +36,9 @@ def main():
f'--name={name}',
'--icon=devscripts/logo.ico',
'--upx-exclude=vcruntime140.dll',
# Ref: https://github.com/yt-dlp/yt-dlp/issues/13311
# https://github.com/pyinstaller/pyinstaller/issues/9149
'--exclude-module=pkg_resources',
'--noconfirm',
'--additional-hooks-dir=yt_dlp/__pyinstaller',
*opts,
@@ -59,16 +62,22 @@ def parse_options():
def exe(onedir):
"""@returns (name, path)"""
platform_name, machine, extension = {
'win32': (None, MACHINE, '.exe'),
'darwin': ('macos', None, None),
}.get(OS_NAME, (OS_NAME, MACHINE, None))
name = '_'.join(filter(None, (
'yt-dlp',
{'win32': '', 'darwin': 'macos'}.get(OS_NAME, OS_NAME),
MACHINE,
platform_name,
machine,
)))
return name, ''.join(filter(None, (
'dist/',
onedir and f'{name}/',
name,
OS_NAME == 'win32' and '.exe',
extension,
)))

View File

@@ -6,13 +6,17 @@ __yt_dlp()
prev="${COMP_WORDS[COMP_CWORD-1]}"
opts="{{flags}}"
keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info-json"
diropts="--cache-dir"
if [[ ${prev} =~ ${fileopts} ]]; then
local IFS=$'\n'
type compopt &>/dev/null && compopt -o filenames
COMPREPLY=( $(compgen -f -- ${cur}) )
return 0
elif [[ ${prev} =~ ${diropts} ]]; then
local IFS=$'\n'
type compopt &>/dev/null && compopt -o dirnames
COMPREPLY=( $(compgen -d -- ${cur}) )
return 0
fi

View File

@@ -254,5 +254,44 @@
{
"action": "remove",
"when": "d596824c2f8428362c072518856065070616e348"
},
{
"action": "remove",
"when": "7b81634fb1d15999757e7a9883daa6ef09ea785b"
},
{
"action": "remove",
"when": "500761e41acb96953a5064e951d41d190c287e46"
},
{
"action": "add",
"when": "f3008bc5f89d2691f2f8dfc51b406ef4e25281c3",
"short": "[priority] **Default behaviour changed from `--mtime` to `--no-mtime`**\nyt-dlp no longer applies the server modified time to downloaded files by default. [Read more](https://github.com/yt-dlp/yt-dlp/issues/12780)"
},
{
"action": "add",
"when": "959ac99e98c3215437e573c22d64be42d361e863",
"short": "[priority] Security: [[CVE-2025-54072](https://nvd.nist.gov/vuln/detail/CVE-2025-54072)] [Fix `--exec` placeholder expansion on Windows](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-45hg-7f49-5h56)\n - When `--exec` is used on Windows, the filepath expanded from `{}` (or the default placeholder) is now properly escaped"
},
{
"action": "change",
"when": "b831406a1d3be34c159835079d12bae624c43610",
"short": "[ie/rtve.es:program] Add extractor (#12955)",
"authors": ["meGAmeS1", "seproDev"]
},
{
"action": "add",
"when": "23c658b9cbe34a151f8f921ab1320bb5d4e40a4d",
"short": "[priority] **The minimum *recommended* Python version has been raised to 3.10**\nSince Python 3.9 will reach end-of-life in October 2025, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13858)"
},
{
"action": "add",
"when": "cc5a5caac5fbc0d605b52bde0778d6fd5f97b5ab",
"short": "[priority] **darwin_legacy_exe builds are being discontinued**\nThis release's `yt-dlp_macos_legacy` binary will likely be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13857)"
},
{
"action": "add",
"when": "c76ce28e06c816eb5b261dfb6aff6e69dd9b7382",
"short": "[priority] **linux_armv7l_exe builds are being discontinued**\nThis release's `yt-dlp_linux_armv7l` binary could be the last one. [Read more](https://github.com/yt-dlp/yt-dlp/issues/13976)"
}
]

View File

@@ -20,6 +20,7 @@ def parse_patched_options(opts):
'fragment_retries': 0,
'extract_flat': False,
'concat_playlist': 'never',
'update_self': False,
})
yt_dlp.options.create_parser = lambda: patched_parser
try:

View File

@@ -15,11 +15,11 @@ description = "A feature-rich command-line audio/video downloader"
readme = "README.md"
requires-python = ">=3.9"
keywords = [
"cli",
"downloader",
"youtube-dl",
"video-downloader",
"youtube-downloader",
"sponsorblock",
"youtube-dlc",
"yt-dlp",
]
license = {file = "LICENSE"}
@@ -51,11 +51,11 @@ default = [
"mutagen",
"pycryptodomex",
"requests>=2.32.2,<3",
"urllib3>=1.26.17,<3",
"urllib3>=2.0.2,<3",
"websockets>=13.0",
]
curl-cffi = [
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.11; implementation_name=='cpython'",
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.14; implementation_name=='cpython'",
]
secretstorage = [
"cffi",
@@ -65,7 +65,7 @@ build = [
"build",
"hatchling",
"pip",
"setuptools>=71.0.2", # 71.0.0 broke pyinstaller
"setuptools>=71.0.2,<81", # See https://github.com/pyinstaller/pyinstaller/issues/9149
"wheel",
]
dev = [
@@ -75,7 +75,7 @@ dev = [
]
static-analysis = [
"autopep8~=2.0",
"ruff~=0.11.0",
"ruff~=0.12.0",
]
test = [
"pytest~=8.1",
@@ -210,10 +210,12 @@ ignore = [
"TD001", # invalid-todo-tag
"TD002", # missing-todo-author
"TD003", # missing-todo-link
"PLC0415", # import-outside-top-level
"PLE0604", # invalid-all-object (false positives)
"PLE0643", # potential-index-error (false positives)
"PLW0603", # global-statement
"PLW1510", # subprocess-run-without-check
"PLW1641", # eq-without-hash
"PLW2901", # redefined-loop-name
"RUF001", # ambiguous-unicode-character-string
"RUF012", # mutable-class-default

View File

@@ -16,7 +16,7 @@ remove-unused-variables = true
[tox:tox]
skipsdist = true
envlist = py{39,310,311,312,313},pypy310
envlist = py{39,310,311,312,313},pypy311
skip_missing_interpreters = true
[testenv] # tox

View File

@@ -5,12 +5,14 @@ # Supported sites
Not all sites listed here are guaranteed to work; websites are constantly changing and sometimes this breaks yt-dlp's support for them.
The only reliable way to check if a site is supported is to try it.
- **10play**: [*10play*](## "netrc machine")
- **10play:season**
- **17live**
- **17live:clip**
- **17live:vod**
- **1News**: 1news.co.nz article videos
- **1tv**: Первый канал
- **20min**
- **20min**: (**Currently broken**)
- **23video**
- **247sports**: (**Currently broken**)
- **24tv.ua**
@@ -42,10 +44,10 @@ # Supported sites
- **ADN**: [*animationdigitalnetwork*](## "netrc machine") Animation Digital Network
- **ADNSeason**: [*animationdigitalnetwork*](## "netrc machine") Animation Digital Network
- **AdobeConnect**
- **adobetv**
- **adobetv:channel**
- **adobetv:embed**
- **adobetv:show**
- **adobetv**: (**Currently broken**)
- **adobetv:channel**: (**Currently broken**)
- **adobetv:embed**: (**Currently broken**)
- **adobetv:show**: (**Currently broken**)
- **adobetv:video**
- **AdultSwim**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
@@ -131,7 +133,6 @@ # Supported sites
- **BaiduVideo**: 百度视频
- **BanBye**
- **BanByeChannel**
- **bandaichannel**
- **Bandcamp**
- **Bandcamp:album**
- **Bandcamp:user**
@@ -155,7 +156,6 @@ # Supported sites
- **Beeg**
- **BehindKink**: (**Currently broken**)
- **Bellator**
- **BellMedia**
- **BerufeTV**
- **Bet**: (**Currently broken**)
- **bfi:player**: (**Currently broken**)
@@ -195,6 +195,7 @@ # Supported sites
- **BitChute**
- **BitChuteChannel**
- **BlackboardCollaborate**
- **BlackboardCollaborateLaunch**
- **BleacherReport**: (**Currently broken**)
- **BleacherReportCMS**: (**Currently broken**)
- **blerp**
@@ -223,6 +224,7 @@ # Supported sites
- **Brilliantpala:Elearn**: [*brilliantpala*](## "netrc machine") VoD on elearn.brilliantpala.org
- **bt:article**: Bergens Tidende Articles
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- **BTVPlus**
- **Bundesliga**
- **Bundestag**
- **BunnyCdn**
@@ -283,7 +285,6 @@ # Supported sites
- **Clipchamp**
- **Clippit**
- **ClipRs**: (**Currently broken**)
- **ClipYouEmbed**
- **CloserToTruth**: (**Currently broken**)
- **CloudflareStream**
- **CloudyCDN**
@@ -295,7 +296,7 @@ # Supported sites
- **CNNIndonesia**
- **ComedyCentral**
- **ComedyCentralTV**
- **ConanClassic**
- **ConanClassic**: (**Currently broken**)
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **CONtv**
- **CookingChannel**
@@ -315,9 +316,8 @@ # Supported sites
- **CSpan**: C-SPAN
- **CSpanCongress**
- **CtsNews**: 華視新聞
- **CTV**
- **CTVNews**
- **cu.ntv.co.jp**: Nippon Television Network
- **cu.ntv.co.jp**: 日テレ無料TADA!
- **CultureUnplugged**
- **curiositystream**: [*curiositystream*](## "netrc machine")
- **curiositystream:collections**: [*curiositystream*](## "netrc machine")
@@ -395,7 +395,6 @@ # Supported sites
- **dw:article**: (**Currently broken**)
- **dzen.ru**: Дзен (dzen) formerly Яндекс.Дзен (Yandex Zen)
- **dzen.ru:channel**
- **EaglePlatform**
- **EbaumsWorld**
- **Ebay**
- **egghead:course**: egghead.io course
@@ -446,6 +445,7 @@ # Supported sites
- **fancode:live**: [*fancode*](## "netrc machine") (**Currently broken**)
- **fancode:vod**: [*fancode*](## "netrc machine") (**Currently broken**)
- **Fathom**
- **FaulioLive**
- **faz.net**
- **fc2**: [*fc2*](## "netrc machine")
- **fc2:embed**
@@ -573,9 +573,7 @@ # Supported sites
- **HollywoodReporterPlaylist**
- **Holodex**
- **HotNewHipHop**: (**Currently broken**)
- **hotstar**
- **hotstar:playlist**
- **hotstar:season**
- **hotstar**: JioHotstar
- **hotstar:series**
- **hrfernsehen**
- **HRTi**: [*hrti*](## "netrc machine")
@@ -588,7 +586,7 @@ # Supported sites
- **Hungama**
- **HungamaAlbumPlaylist**
- **HungamaSong**
- **huya:live**: huya.com
- **huya:live**: 虎牙直播
- **huya:video**: 虎牙视频
- **Hypem**
- **Hytale**
@@ -645,8 +643,6 @@ # Supported sites
- **Jamendo**
- **JamendoAlbum**
- **JeuxVideo**: (**Currently broken**)
- **jiocinema**: [*jiocinema*](## "netrc machine")
- **jiocinema:series**: [*jiocinema*](## "netrc machine")
- **jiosaavn:album**
- **jiosaavn:artist**
- **jiosaavn:playlist**
@@ -654,7 +650,6 @@ # Supported sites
- **jiosaavn:show:playlist**
- **jiosaavn:song**
- **Joj**
- **JoqrAg**: 超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)
- **Jove**
- **JStream**
- **JTBC**: jtbc.co.kr
@@ -725,9 +720,6 @@ # Supported sites
- **life:embed**
- **likee**
- **likee:user**
- **limelight**
- **limelight:channel**
- **limelight:channel_list**
- **LinkedIn**: [*linkedin*](## "netrc machine")
- **linkedin:events**: [*linkedin*](## "netrc machine")
- **linkedin:learning**: [*linkedin*](## "netrc machine")
@@ -735,7 +727,7 @@ # Supported sites
- **Liputan6**
- **ListenNotes**
- **LiTV**
- **LiveJournal**
- **LiveJournal**: (**Currently broken**)
- **livestream**
- **livestream:original**
- **Livestreamfails**
@@ -774,6 +766,7 @@ # Supported sites
- **massengeschmack.tv**
- **Masters**
- **MatchTV**
- **Mave**
- **MBN**: mbn.co.kr (매일방송)
- **MDR**: MDR.DE
- **MedalTV**
@@ -808,6 +801,7 @@ # Supported sites
- **minds:channel**
- **minds:group**
- **Minoto**
- **mir24.tv**
- **mirrativ**
- **mirrativ:user**
- **MirrorCoUK**
@@ -818,6 +812,8 @@ # Supported sites
- **mixcloud**
- **mixcloud:playlist**
- **mixcloud:user**
- **Mixlr**
- **MixlrRecoring**
- **MLB**
- **MLBArticle**
- **MLBTV**: [*mlb*](## "netrc machine")
@@ -830,7 +826,7 @@ # Supported sites
- **Mojevideo**: mojevideo.sk
- **Mojvideo**
- **Monstercat**
- **MonsterSirenHypergryphMusic**
- **monstersiren**: 塞壬唱片
- **Motherless**
- **MotherlessGallery**
- **MotherlessGroup**
@@ -882,19 +878,19 @@ # Supported sites
- **Naver**
- **Naver:live**
- **navernow**
- **nba**
- **nba:channel**
- **nba:embed**
- **nba:watch**
- **nba:watch:collection**
- **nba:watch:embed**
- **nba**: (**Currently broken**)
- **nba:channel**: (**Currently broken**)
- **nba:embed**: (**Currently broken**)
- **nba:watch**: (**Currently broken**)
- **nba:watch:collection**: (**Currently broken**)
- **nba:watch:embed**: (**Currently broken**)
- **NBC**
- **NBCNews**
- **nbcolympics**
- **nbcolympics:stream**
- **NBCSports**
- **NBCSportsStream**
- **NBCSportsVPlayer**
- **nbcolympics:stream**: (**Currently broken**)
- **NBCSports**: (**Currently broken**)
- **NBCSportsStream**: (**Currently broken**)
- **NBCSportsVPlayer**: (**Currently broken**)
- **NBCStations**
- **ndr**: NDR.de - Norddeutscher Rundfunk
- **ndr:embed**
@@ -970,11 +966,10 @@ # Supported sites
- **Nitter**
- **njoy**: N-JOY
- **njoy:embed**
- **NobelPrize**: (**Currently broken**)
- **NobelPrize**
- **NoicePodcast**
- **NonkTube**
- **NoodleMagazine**
- **Noovo**
- **NOSNLArticle**
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
- **NovaEmbed**
@@ -1060,7 +1055,7 @@ # Supported sites
- **ParamountPressExpress**
- **Parler**: Posts on parler.com
- **parliamentlive.tv**: UK parliament videos
- **Parlview**: (**Currently broken**)
- **Parlview**
- **parti:livestream**
- **parti:video**
- **patreon**
@@ -1098,6 +1093,7 @@ # Supported sites
- **Platzi**: [*platzi*](## "netrc machine")
- **PlatziCourse**: [*platzi*](## "netrc machine")
- **player.sky.it**
- **PlayerFm**
- **playeur**
- **PlayPlusTV**: [*playplustv*](## "netrc machine")
- **PlaySuisse**: [*playsuisse*](## "netrc machine")
@@ -1108,6 +1104,7 @@ # Supported sites
- **pluralsight:course**
- **PlutoTV**: (**Currently broken**)
- **PlVideo**: Платформа
- **PlyrEmbed**
- **PodbayFM**
- **PodbayFMChannel**
- **Podchaser**
@@ -1261,6 +1258,7 @@ # Supported sites
- **rtve.es:alacarta**: RTVE a la carta and Play
- **rtve.es:audio**: RTVE audio
- **rtve.es:live**: RTVE.es live streams
- **rtve.es:program**: RTVE.es programs
- **rtve.es:television**
- **rtvslo.si**
- **rtvslo.si:show**
@@ -1278,7 +1276,7 @@ # Supported sites
- **rutube:playlist**: Rutube playlists
- **rutube:tags**: Rutube tags
- **RUTV**: RUTV.RU
- **Ruutu**
- **Ruutu**: (**Currently broken**)
- **Ruv**
- **ruv.is:spila**
- **S4C**
@@ -1296,6 +1294,7 @@ # Supported sites
- **SampleFocus**
- **Sangiin**: 参議院インターネット審議中継 (archive)
- **Sapo**: SAPO Vídeos
- **SaucePlus**: Sauce+
- **SBS**: sbs.com.au
- **sbs.co.kr**
- **sbs.co.kr:allvod_program**
@@ -1328,6 +1327,7 @@ # Supported sites
- **SharePoint**
- **ShareVideosEmbed**
- **ShemarooMe**
- **Shiey**
- **ShowRoomLive**
- **ShugiinItvLive**: 衆議院インターネット審議中継
- **ShugiinItvLiveRoom**: 衆議院インターネット審議中継 (中継)
@@ -1385,7 +1385,7 @@ # Supported sites
- **SpankBangPlaylist**
- **Spiegel**
- **Sport5**
- **SportBox**
- **SportBox**: (**Currently broken**)
- **SportDeutschland**
- **spotify**: Spotify episodes (**Currently broken**)
- **spotify:show**: Spotify shows (**Currently broken**)
@@ -1393,14 +1393,14 @@ # Supported sites
- **SpreakerShow**
- **SpringboardPlatform**
- **SproutVideo**
- **sr:mediathek**: Saarländischer Rundfunk (**Currently broken**)
- **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**: (**Currently broken**)
- **startrek**: STAR TREK
- **startv**
- **Steam**
- **SteamCommunityBroadcast**
@@ -1423,12 +1423,11 @@ # Supported sites
- **SunPorno**
- **sverigesradio:episode**
- **sverigesradio:publication**
- **SVT**
- **SVTPage**
- **SVTPlay**: SVT Play and Öppet arkiv
- **SVTSeries**
- **svt:page**
- **svt:play**: SVT Play and Öppet arkiv
- **svt:play:series**
- **SwearnetEpisode**
- **Syfy**: (**Currently broken**)
- **Syfy**
- **SYVDK**
- **SztvHu**
- **t-online.de**: (**Currently broken**)
@@ -1472,14 +1471,13 @@ # Supported sites
- **Telewebion**: (**Currently broken**)
- **Tempo**
- **TennisTV**: [*tennistv*](## "netrc machine")
- **TenPlay**: [*10play*](## "netrc machine")
- **TenPlaySeason**
- **TF1**
- **TFO**
- **TFO**: (**Currently broken**)
- **theatercomplextown:ppv**: [*theatercomplextown*](## "netrc machine")
- **theatercomplextown:vod**: [*theatercomplextown*](## "netrc machine")
- **TheGuardianPodcast**
- **TheGuardianPodcastPlaylist**
- **TheHighWire**
- **TheHoleTv**
- **TheIntercept**
- **ThePlatform**
@@ -1511,6 +1509,7 @@ # Supported sites
- **tokfm:podcast**
- **ToonGoggles**
- **tou.tv**: [*toutv*](## "netrc machine")
- **toutiao**: 今日头条
- **Toypics**: Toypics video (**Currently broken**)
- **ToypicsUser**: Toypics user profile (**Currently broken**)
- **TrailerAddict**: (**Currently broken**)
@@ -1527,7 +1526,6 @@ # Supported sites
- **TrueID**
- **TruNews**
- **Truth**
- **TruTV**
- **Tube8**: (**Currently broken**)
- **TubeTuGraz**: [*tubetugraz*](## "netrc machine") tube.tugraz.at
- **TubeTuGrazSeries**: [*tubetugraz*](## "netrc machine")
@@ -1546,8 +1544,8 @@ # Supported sites
- **tv2playseries.hu**
- **TV4**: tv4.se and tv4play.se
- **TV5MONDE**
- **tv5unis**
- **tv5unis:video**
- **tv5unis**: (**Currently broken**)
- **tv5unis:video**: (**Currently broken**)
- **tv8.it**
- **tv8.it:live**: TV8 Live
- **tv8.it:playlist**: TV8 Playlist
@@ -1572,6 +1570,7 @@ # Supported sites
- **TVPlayer**
- **TVPlayHome**
- **tvw**
- **tvw:news**
- **tvw:tvchannels**
- **Tweakers**
- **TwitCasting**
@@ -1600,8 +1599,9 @@ # Supported sites
- **UKTVPlay**
- **UlizaPlayer**
- **UlizaPortal**: ulizaportal.jp
- **umg:de**: Universal Music Deutschland (**Currently broken**)
- **umg:de**: Universal Music Deutschland
- **Unistra**
- **UnitedNationsWebTv**
- **Unity**: (**Currently broken**)
- **uol.com.br**
- **uplynk**
@@ -1623,10 +1623,10 @@ # Supported sites
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **vhx:embed**: [*vimeo*](## "netrc machine")
- **vice**
- **vice:article**
- **vice:show**
- **Viddler**
- **vice**: (**Currently broken**)
- **vice:article**: (**Currently broken**)
- **vice:show**: (**Currently broken**)
- **Viddler**: (**Currently broken**)
- **Videa**
- **video.arnes.si**: Arnes Video
- **video.google:search**: Google Video search; "gvsearch:" prefix

View File

@@ -36,6 +36,18 @@ def do_GET(self):
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(TEAPOT_RESPONSE_BODY.encode())
elif self.path == '/fake.m3u8':
self.send_response(200)
self.send_header('Content-Length', '1024')
self.end_headers()
self.wfile.write(1024 * b'\x00')
elif self.path == '/bipbop.m3u8':
with open('test/testdata/m3u8/bipbop_16x9.m3u8', 'rb') as f:
data = f.read()
self.send_response(200)
self.send_header('Content-Length', str(len(data)))
self.end_headers()
self.wfile.write(data)
else:
assert False
@@ -314,6 +326,20 @@ def test_search_json_ld_realworld(self):
},
{},
),
(
# test thumbnail_url key without URL scheme
r'''
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "VideoObject",
"thumbnail_url": "//www.nobelprize.org/images/12693-landscape-medium-gallery.jpg"
}</script>''',
{
'thumbnails': [{'url': 'https://www.nobelprize.org/images/12693-landscape-medium-gallery.jpg'}],
},
{},
),
]
for html, expected_dict, search_json_ld_kwargs in _TESTS:
expect_dict(
@@ -1933,6 +1959,208 @@ def test_search_nextjs_data(self):
with self.assertWarns(DeprecationWarning):
self.assertEqual(self.ie._search_nextjs_data('', None, default='{}'), {})
def test_search_nextjs_v13_data(self):
HTML = R'''
<script>(self.__next_f=self.__next_f||[]).push([0])</script>
<script>self.__next_f.push([2,"0:[\"$\",\"$L0\",null,{\"do_not_add_this\":\"fail\"}]\n"])</script>
<script>self.__next_f.push([1,"1:I[46975,[],\"HTTPAccessFallbackBoundary\"]\n2:I[32630,[\"8183\",\"static/chunks/8183-768193f6a9e33cdd.js\"]]\n"])</script>
<script nonce="abc123">self.__next_f.push([1,"e:[false,[\"$\",\"div\",null,{\"children\":[\"$\",\"$L18\",null,{\"foo\":\"bar\"}]}],false]\n "])</script>
<script>self.__next_f.push([1,"2a:[[\"$\",\"div\",null,{\"className\":\"flex flex-col\",\"children\":[]}],[\"$\",\"$L16\",null,{\"meta\":{\"dateCreated\":1730489700,\"uuid\":\"40cac41d-8d29-4ef5-aa11-75047b9f0907\"}}]]\n"])</script>
<script>self.__next_f.push([1,"df:[\"$undefined\",[\"$\",\"div\",null,{\"children\":[\"$\",\"$L17\",null,{}],\"do_not_include_this_field\":\"fail\"}],[\"$\",\"div\",null,{\"children\":[[\"$\",\"$L19\",null,{\"duplicated_field_name\":{\"x\":1}}],[\"$\",\"$L20\",null,{\"duplicated_field_name\":{\"y\":2}}]]}],\"$undefined\"]\n"])</script>
<script>self.__next_f.push([3,"MzM6WyIkIiwiJEwzMiIsbnVsbCx7ImRlY29kZWQiOiJzdWNjZXNzIn1d"])</script>
'''
EXPECTED = {
'18': {
'foo': 'bar',
},
'16': {
'meta': {
'dateCreated': 1730489700,
'uuid': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
},
},
'19': {
'duplicated_field_name': {'x': 1},
},
'20': {
'duplicated_field_name': {'y': 2},
},
}
self.assertEqual(self.ie._search_nextjs_v13_data(HTML, None), EXPECTED)
self.assertEqual(self.ie._search_nextjs_v13_data('', None, fatal=False), {})
self.assertEqual(self.ie._search_nextjs_v13_data(None, None, fatal=False), {})
def test_search_nuxt_json(self):
HTML_TMPL = '<script data-ssr="true" id="__NUXT_DATA__" type="application/json">[{}]</script>'
VALID_DATA = '''
["ShallowReactive",1],
{"data":2,"state":21,"once":25,"_errors":28,"_server_errors":30},
["ShallowReactive",3],
{"$abcdef123456":4},
{"podcast":5,"activeEpisodeData":7},
{"podcast":6,"seasons":14},
{"title":10,"id":11},
["Reactive",8],
{"episode":9,"creators":18,"empty_list":20},
{"title":12,"id":13,"refs":34,"empty_refs":35},
"Series Title",
"podcast-id-01",
"Episode Title",
"episode-id-99",
[15,16,17],
1,
2,
3,
[19],
"Podcast Creator",
[],
{"$ssite-config":22},
{"env":23,"name":24,"map":26,"numbers":14},
"production",
"podcast-website",
["Set"],
["Reactive",27],
["Map"],
["ShallowReactive",29],
{},
["NuxtError",31],
{"status":32,"message":33},
503,
"Service Unavailable",
[36,37],
[38,39],
["Ref",40],
["ShallowRef",41],
["EmptyRef",42],
["EmptyShallowRef",43],
"ref",
"shallow_ref",
"{\\"ref\\":1}",
"{\\"shallow_ref\\":2}"
'''
PAYLOAD = {
'data': {
'$abcdef123456': {
'podcast': {
'podcast': {
'title': 'Series Title',
'id': 'podcast-id-01',
},
'seasons': [1, 2, 3],
},
'activeEpisodeData': {
'episode': {
'title': 'Episode Title',
'id': 'episode-id-99',
'refs': ['ref', 'shallow_ref'],
'empty_refs': [{'ref': 1}, {'shallow_ref': 2}],
},
'creators': ['Podcast Creator'],
'empty_list': [],
},
},
},
'state': {
'$ssite-config': {
'env': 'production',
'name': 'podcast-website',
'map': [],
'numbers': [1, 2, 3],
},
},
'once': [],
'_errors': {},
'_server_errors': {
'status': 503,
'message': 'Service Unavailable',
},
}
PARTIALLY_INVALID = [(
'''
{"data":1},
{"invalid_raw_list":2},
[15,16,17]
''',
{'data': {'invalid_raw_list': [None, None, None]}},
), (
'''
{"data":1},
["EmptyRef",2],
"not valid JSON"
''',
{'data': None},
), (
'''
{"data":1},
["EmptyShallowRef",2],
"not valid JSON"
''',
{'data': None},
)]
INVALID = [
'''
[]
''',
'''
["unsupported",1],
{"data":2},
{}
''',
]
DEFAULT = object()
self.assertEqual(self.ie._search_nuxt_json(HTML_TMPL.format(VALID_DATA), None), PAYLOAD)
self.assertEqual(self.ie._search_nuxt_json('', None, fatal=False), {})
self.assertIs(self.ie._search_nuxt_json('', None, default=DEFAULT), DEFAULT)
for data, expected in PARTIALLY_INVALID:
self.assertEqual(
self.ie._search_nuxt_json(HTML_TMPL.format(data), None, fatal=False), expected)
for data in INVALID:
self.assertIs(
self.ie._search_nuxt_json(HTML_TMPL.format(data), None, default=DEFAULT), DEFAULT)
class TestInfoExtractorNetwork(unittest.TestCase):
def setUp(self, /):
self.httpd = http.server.HTTPServer(
('127.0.0.1', 0), InfoExtractorTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
self.called = False
def require_warning(*args, **kwargs):
self.called = True
self.ydl = FakeYDL()
self.ydl.report_warning = require_warning
self.ie = DummyIE(self.ydl)
def tearDown(self, /):
self.ydl.close()
self.httpd.shutdown()
self.httpd.server_close()
self.server_thread.join(1)
def test_extract_m3u8_formats(self):
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
f'http://127.0.0.1:{self.port}/bipbop.m3u8', None, fatal=False)
self.assertFalse(self.called)
self.assertTrue(formats)
self.assertTrue(subtitles)
def test_extract_m3u8_formats_warning(self):
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
f'http://127.0.0.1:{self.port}/fake.m3u8', None, fatal=False)
self.assertTrue(self.called, 'Warning was not issued for binary m3u8 file')
self.assertFalse(formats)
self.assertFalse(subtitles)
if __name__ == '__main__':
unittest.main()

View File

@@ -21,9 +21,6 @@ def test_compat_passthrough(self):
with self.assertWarns(DeprecationWarning):
_ = compat.compat_basestring
with self.assertWarns(DeprecationWarning):
_ = compat.WINDOWS_VT_MODE
self.assertEqual(urllib.request.getproxies, getproxies)
with self.assertWarns(DeprecationWarning):

235
test/test_devalue.py Normal file
View File

@@ -0,0 +1,235 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import datetime as dt
import json
import math
import re
import unittest
from yt_dlp.utils.jslib import devalue
TEST_CASES_EQUALS = [{
'name': 'int',
'unparsed': [-42],
'parsed': -42,
}, {
'name': 'str',
'unparsed': ['woo!!!'],
'parsed': 'woo!!!',
}, {
'name': 'Number',
'unparsed': [['Object', 42]],
'parsed': 42,
}, {
'name': 'String',
'unparsed': [['Object', 'yar']],
'parsed': 'yar',
}, {
'name': 'Infinity',
'unparsed': -4,
'parsed': math.inf,
}, {
'name': 'negative Infinity',
'unparsed': -5,
'parsed': -math.inf,
}, {
'name': 'negative zero',
'unparsed': -6,
'parsed': -0.0,
}, {
'name': 'RegExp',
'unparsed': [['RegExp', 'regexp', 'gim']], # XXX: flags are ignored
'parsed': re.compile('regexp'),
}, {
'name': 'Date',
'unparsed': [['Date', '2001-09-09T01:46:40.000Z']],
'parsed': dt.datetime.fromtimestamp(1e9, tz=dt.timezone.utc),
}, {
'name': 'Array',
'unparsed': [[1, 2, 3], 'a', 'b', 'c'],
'parsed': ['a', 'b', 'c'],
}, {
'name': 'Array (empty)',
'unparsed': [[]],
'parsed': [],
}, {
'name': 'Array (sparse)',
'unparsed': [[-2, 1, -2], 'b'],
'parsed': [None, 'b', None],
}, {
'name': 'Object',
'unparsed': [{'foo': 1, 'x-y': 2}, 'bar', 'z'],
'parsed': {'foo': 'bar', 'x-y': 'z'},
}, {
'name': 'Set',
'unparsed': [['Set', 1, 2, 3], 1, 2, 3],
'parsed': [1, 2, 3],
}, {
'name': 'Map',
'unparsed': [['Map', 1, 2], 'a', 'b'],
'parsed': [['a', 'b']],
}, {
'name': 'BigInt',
'unparsed': [['BigInt', '1']],
'parsed': 1,
}, {
'name': 'Uint8Array',
'unparsed': [['Uint8Array', 'AQID']],
'parsed': [1, 2, 3],
}, {
'name': 'ArrayBuffer',
'unparsed': [['ArrayBuffer', 'AQID']],
'parsed': [1, 2, 3],
}, {
'name': 'str (repetition)',
'unparsed': [[1, 1], 'a string'],
'parsed': ['a string', 'a string'],
}, {
'name': 'None (repetition)',
'unparsed': [[1, 1], None],
'parsed': [None, None],
}, {
'name': 'dict (repetition)',
'unparsed': [[1, 1], {}],
'parsed': [{}, {}],
}, {
'name': 'Object without prototype',
'unparsed': [['null']],
'parsed': {},
}, {
'name': 'cross-realm POJO',
'unparsed': [{}],
'parsed': {},
}]
TEST_CASES_IS = [{
'name': 'bool',
'unparsed': [True],
'parsed': True,
}, {
'name': 'Boolean',
'unparsed': [['Object', False]],
'parsed': False,
}, {
'name': 'undefined',
'unparsed': -1,
'parsed': None,
}, {
'name': 'null',
'unparsed': [None],
'parsed': None,
}, {
'name': 'NaN',
'unparsed': -3,
'parsed': math.nan,
}]
TEST_CASES_INVALID = [{
'name': 'empty string',
'unparsed': '',
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'hole',
'unparsed': -2,
'error': ValueError,
'pattern': r'invalid integer input',
}, {
'name': 'string',
'unparsed': 'hello',
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'number',
'unparsed': 42,
'error': ValueError,
'pattern': r'invalid integer input',
}, {
'name': 'boolean',
'unparsed': True,
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'null',
'unparsed': None,
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'object',
'unparsed': {},
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'empty array',
'unparsed': [],
'error': ValueError,
'pattern': r'expected a non-empty list as input',
}, {
'name': 'Python negative indexing',
'unparsed': [[1, 2, 3, 4, 5, 6, 7, -7], 1, 2, 3, 4, 5, 6, 7],
'error': IndexError,
'pattern': r'invalid index: -7',
}]
class TestDevalue(unittest.TestCase):
def test_devalue_parse_equals(self):
for tc in TEST_CASES_EQUALS:
self.assertEqual(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
def test_devalue_parse_is(self):
for tc in TEST_CASES_IS:
self.assertIs(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
def test_devalue_parse_invalid(self):
for tc in TEST_CASES_INVALID:
with self.assertRaisesRegex(tc['error'], tc['pattern'], msg=tc['name']):
devalue.parse(tc['unparsed'])
def test_devalue_parse_cyclical(self):
name = 'Map (cyclical)'
result = devalue.parse([['Map', 1, 0], 'self'])
self.assertEqual(result[0][0], 'self', name)
self.assertIs(result, result[0][1], name)
name = 'Set (cyclical)'
result = devalue.parse([['Set', 0, 1], 42])
self.assertEqual(result[1], 42, name)
self.assertIs(result, result[0], name)
result = devalue.parse([[0]])
self.assertIs(result, result[0], 'Array (cyclical)')
name = 'Object (cyclical)'
result = devalue.parse([{'self': 0}])
self.assertIs(result, result['self'], name)
name = 'Object with null prototype (cyclical)'
result = devalue.parse([['null', 'self', 0]])
self.assertIs(result, result['self'], name)
name = 'Objects (cyclical)'
result = devalue.parse([[1, 2], {'second': 2}, {'first': 1}])
self.assertIs(result[0], result[1]['first'], name)
self.assertIs(result[1], result[0]['second'], name)
def test_devalue_parse_revivers(self):
self.assertEqual(
devalue.parse([['indirect', 1], {'a': 2}, 'b'], revivers={'indirect': lambda x: x}),
{'a': 'b'}, 'revivers (indirect)')
self.assertEqual(
devalue.parse([['parse', 1], '{"a":0}'], revivers={'parse': lambda x: json.loads(x)}),
{'a': 0}, 'revivers (parse)')
if __name__ == '__main__':
unittest.main()

View File

@@ -14,6 +14,7 @@
from test.helper import (
assertGreaterEqual,
assertLessEqual,
expect_info_dict,
expect_warnings,
get_params,
@@ -65,10 +66,6 @@ def _file_md5(fn):
@is_download_test
class TestDownload(unittest.TestCase):
# Parallel testing in nosetests. See
# http://nose.readthedocs.org/en/latest/doc_tests/test_multiprocess/multiprocess.html
_multiprocess_shared_ = True
maxDiff = None
COMPLETED_TESTS = {}
@@ -121,10 +118,13 @@ def print_skipping(reason):
params = get_params(test_case.get('params', {}))
params['outtmpl'] = tname + '_' + params['outtmpl']
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', 'in_playlist')
params.setdefault('playlistend', test_case.get(
'playlist_mincount', test_case.get('playlist_count', -2) + 1))
params.setdefault('playlistend', max(
test_case.get('playlist_mincount', -1),
test_case.get('playlist_count', -2) + 1,
test_case.get('playlist_maxcount', -2) + 1))
params.setdefault('skip_download', True)
if 'playlist_duration_sum' not in test_case:
params.setdefault('extract_flat', 'in_playlist')
ydl = YoutubeDL(params, auto_init=False)
ydl.add_default_info_extractors()
@@ -159,6 +159,7 @@ def try_rm_tcs_files(tcs=None):
try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
try_rm_tcs_files()
try:
test_url = test_case['url']
try_num = 1
while True:
try:
@@ -166,7 +167,7 @@ def try_rm_tcs_files(tcs=None):
# for outside error handling, and returns the exit code
# instead of the result dict.
res_dict = ydl.extract_info(
test_case['url'],
test_url,
force_generic_extractor=params.get('force_generic_extractor', False))
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
@@ -194,23 +195,23 @@ def try_rm_tcs_files(tcs=None):
self.assertTrue('entries' in res_dict)
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
num_entries = len(res_dict.get('entries', []))
if 'playlist_mincount' in test_case:
mincount = test_case['playlist_mincount']
assertGreaterEqual(
self,
len(res_dict['entries']),
test_case['playlist_mincount'],
'Expected at least %d in playlist %s, but got only %d' % (
test_case['playlist_mincount'], test_case['url'],
len(res_dict['entries'])))
self, num_entries, mincount,
f'Expected at least {mincount} entries in playlist {test_url}, but got only {num_entries}')
if 'playlist_count' in test_case:
count = test_case['playlist_count']
got = num_entries if num_entries <= count else 'more'
self.assertEqual(
len(res_dict['entries']),
test_case['playlist_count'],
'Expected %d entries in playlist %s, but got %d.' % (
test_case['playlist_count'],
test_case['url'],
len(res_dict['entries']),
))
num_entries, count,
f'Expected exactly {count} entries in playlist {test_url}, but got {got}')
if 'playlist_maxcount' in test_case:
maxcount = test_case['playlist_maxcount']
assertLessEqual(
self, num_entries, maxcount,
f'Expected at most {maxcount} entries in playlist {test_url}, but got more')
if 'playlist_duration_sum' in test_case:
got_duration = sum(e['duration'] for e in res_dict['entries'])
self.assertEqual(

View File

@@ -478,6 +478,10 @@ def test_extract_function_with_global_stack(self):
func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
self.assertEqual(func([1]), 1111)
def test_extract_object(self):
jsi = JSInterpreter('var a={};a.xy={};var xy;var zxy={};xy={z:function(){return "abc"}};')
self.assertTrue('z' in jsi.extract_object('xy', None))
def test_increment_decrement(self):
self._test('function f() { var x = 1; return ++x; }', 2)
self._test('function f() { var x = 1; return x++; }', 1)
@@ -486,6 +490,57 @@ def test_increment_decrement(self):
self._test('function f() { var a = "test--"; return a; }', 'test--')
self._test('function f() { var b = 1; var a = "b--"; return a; }', 'b--')
def test_nested_function_scoping(self):
self._test(R'''
function f() {
var g = function() {
var P = 2;
return P;
};
var P = 1;
g();
return P;
}
''', 1)
self._test(R'''
function f() {
var x = function() {
for (var w = 1, M = []; w < 2; w++) switch (w) {
case 1:
M.push("a");
case 2:
M.push("b");
}
return M
};
var w = "c";
var M = "d";
var y = x();
y.push(w);
y.push(M);
return y;
}
''', ['a', 'b', 'c', 'd'])
self._test(R'''
function f() {
var P, Q;
var z = 100;
var g = function() {
var P, Q; P = 2; Q = 15;
z = 0;
return P+Q;
};
P = 1; Q = 10;
var x = g(), y = 3;
return P+Q+x+y+z;
}
''', 31)
def test_undefined_varnames(self):
jsi = JSInterpreter('function f(){ var a; return [a, b]; }')
self._test(jsi, [JS_Undefined, JS_Undefined])
self.assertEqual(jsi._undefined_varnames, {'b'})
if __name__ == '__main__':
unittest.main()

View File

@@ -22,7 +22,6 @@
import tempfile
import threading
import time
import urllib.error
import urllib.request
import warnings
import zlib
@@ -223,10 +222,7 @@ def do_GET(self):
if encoding == 'br' and brotli:
payload = brotli.compress(payload)
elif encoding == 'gzip':
buf = io.BytesIO()
with gzip.GzipFile(fileobj=buf, mode='wb') as f:
f.write(payload)
payload = buf.getvalue()
payload = gzip.compress(payload, mtime=0)
elif encoding == 'deflate':
payload = zlib.compress(payload)
elif encoding == 'unsupported':
@@ -729,6 +725,17 @@ def test_keep_header_casing(self, handler):
assert 'X-test-heaDer: test' in res
def test_partial_read_then_full_read(self, handler):
with handler() as rh:
for encoding in ('', 'gzip', 'deflate'):
res = validate_and_send(rh, Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': encoding}))
assert res.headers.get('Content-Encoding') == encoding
assert res.read(6) == b'<html>'
assert res.read(0) == b''
assert res.read() == b'<video src="/vid.mp4" /></html>'
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
class TestClientCertificate:

View File

@@ -8,6 +8,8 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import subprocess
from yt_dlp import YoutubeDL
from yt_dlp.utils import shell_quote
from yt_dlp.postprocessor import (
@@ -47,7 +49,18 @@ def test_escaping(self):
print('Skipping: ffmpeg not found')
return
file = 'test/testdata/thumbnails/foo %d bar/foo_%d.{}'
test_data_dir = 'test/testdata/thumbnails'
generated_file = f'{test_data_dir}/empty.webp'
subprocess.check_call([
pp.executable, '-y', '-f', 'lavfi', '-i', 'color=c=black:s=320x320',
'-c:v', 'libwebp', '-pix_fmt', 'yuv420p', '-vframes', '1', generated_file,
], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
file = test_data_dir + '/foo %d bar/foo_%d.{}'
initial_file = file.format('webp')
os.replace(generated_file, initial_file)
tests = (('webp', 'png'), ('png', 'jpg'))
for inp, out in tests:
@@ -55,11 +68,13 @@ def test_escaping(self):
if os.path.exists(out_file):
os.remove(out_file)
pp.convert_thumbnail(file.format(inp), out)
assert os.path.exists(out_file)
self.assertTrue(os.path.exists(out_file))
for _, out in tests:
os.remove(file.format(out))
os.remove(initial_file)
class TestExec(unittest.TestCase):
def test_parse_cmd(self):
@@ -610,3 +625,7 @@ def test_quote_for_concat_QuotesAtEnd(self):
self.assertEqual(
r"'special '\'' characters '\'' galore'\'\'\'",
self._pp._quote_for_ffmpeg("special ' characters ' galore'''"))
if __name__ == '__main__':
unittest.main()

View File

@@ -11,7 +11,7 @@ class TestGetWebPoContentBinding:
@pytest.mark.parametrize('client_name, context, is_authenticated, expected', [
*[(client, context, is_authenticated, expected) for client in [
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
for context, is_authenticated, expected in [
(PoTokenContext.GVS, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
(PoTokenContext.PLAYER, False, ('example-video-id', ContentBindingType.VIDEO_ID)),

View File

@@ -49,7 +49,7 @@ def test_not_supports(self, ie, logger, pot_request, client_name, context, is_au
@pytest.mark.parametrize('client_name, context, is_authenticated, remote_host, source_address, request_proxy, expected', [
*[(client, context, is_authenticated, remote_host, source_address, request_proxy, expected) for client in [
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
for context, is_authenticated, remote_host, source_address, request_proxy, expected in [
(PoTokenContext.GVS, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id'}),
(PoTokenContext.PLAYER, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'video_id'}),

View File

@@ -416,18 +416,8 @@ def test_traversal_unbranching(self):
'`any` should allow further branching'
def test_traversal_morsel(self):
values = {
'expires': 'a',
'path': 'b',
'comment': 'c',
'domain': 'd',
'max-age': 'e',
'secure': 'f',
'httponly': 'g',
'version': 'h',
'samesite': 'i',
}
morsel = http.cookies.Morsel()
values = dict(zip(morsel, 'abcdefghijklmnop'))
morsel.set('item_key', 'item_value', 'coded_value')
morsel.update(values)
values['key'] = 'item_key'

View File

@@ -1373,6 +1373,7 @@ def test_parse_resolution(self):
self.assertEqual(parse_resolution('pre_1920x1080_post'), {'width': 1920, 'height': 1080})
self.assertEqual(parse_resolution('ep1x2'), {})
self.assertEqual(parse_resolution('1920, 1080'), {'width': 1920, 'height': 1080})
self.assertEqual(parse_resolution('1920w', lenient=True), {'width': 1920})
def test_parse_bitrate(self):
self.assertEqual(parse_bitrate(None), None)

View File

@@ -133,6 +133,11 @@
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
),
(
'https://www.youtube.com/s/player/e12fbea4/player_ias.vflset/en_US/base.js',
'gN7a-hudCuAuPH6fByOk1_GNXN0yNMHShjZXS2VOgsEItAJz0tipeavEOmNdYN-wUtcEqD3bCXjc0iyKfAyZxCBGgIARwsSdQfJ2CJtt',
'JC2JfQdSswRAIgGBCxZyAfKyi0cjXCb3DqEctUw-NYdNmOEvaepit0zJAtIEsgOV2SXZjhSHMNy0NXNG_1kOyBf6HPuAuCduh-a',
),
]
_NSIG_TESTS = [
@@ -320,6 +325,58 @@
'https://www.youtube.com/s/player/59b252b9/player_ias.vflset/en_US/base.js',
'D3XWVpYgwhLLKNK4AGX', 'aZrQ1qWJ5yv5h',
),
(
'https://www.youtube.com/s/player/fc2a56a5/player_ias.vflset/en_US/base.js',
'qTKWg_Il804jd2kAC', 'OtUAm2W6gyzJjB9u',
),
(
'https://www.youtube.com/s/player/fc2a56a5/tv-player-ias.vflset/tv-player-ias.js',
'qTKWg_Il804jd2kAC', 'OtUAm2W6gyzJjB9u',
),
(
'https://www.youtube.com/s/player/a74bf670/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', 'hQP7k1hA22OrNTnq',
),
(
'https://www.youtube.com/s/player/6275f73c/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '-I03XF0iyf6I_X0A',
),
(
'https://www.youtube.com/s/player/20c72c18/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '-I03XF0iyf6I_X0A',
),
(
'https://www.youtube.com/s/player/9fe2e06e/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '6r5ekNIiEMPutZy',
),
(
'https://www.youtube.com/s/player/680f8c75/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '0ml9caTwpa55Jf',
),
(
'https://www.youtube.com/s/player/14397202/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', 'ozZFAN21okDdJTa',
),
(
'https://www.youtube.com/s/player/5dcb2c1f/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', 'p7iTbRZDYAF',
),
(
'https://www.youtube.com/s/player/a10d7fcc/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '9Zue7DDHJSD',
),
(
'https://www.youtube.com/s/player/8e20cb06/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', '5-4tTneTROTpMzba',
),
(
'https://www.youtube.com/s/player/e12fbea4/player_ias_tce.vflset/en_US/base.js',
'kM5r52fugSZRAKHfo3', 'XkeRfXIPOkSwfg',
),
(
'https://www.youtube.com/s/player/ef259203/player_ias_tce.vflset/en_US/base.js',
'rPqBC01nJpqhhi2iA2U', 'hY7dbiKFT51UIA',
),
]

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.8 KiB

View File

View File

@@ -36,6 +36,7 @@
from .globals import (
IN_CLI,
LAZY_EXTRACTORS,
WINDOWS_VT_MODE,
plugin_ies,
plugin_ies_overrides,
plugin_pps,
@@ -52,7 +53,7 @@
SSLError,
network_exceptions,
)
from .networking.impersonate import ImpersonateRequestHandler
from .networking.impersonate import ImpersonateRequestHandler, ImpersonateTarget
from .plugins import directories as plugin_directories, load_all_plugins
from .postprocessor import (
EmbedThumbnailPP,
@@ -72,6 +73,7 @@
from .update import (
REPOSITORY,
_get_system_deprecation,
_get_outdated_warning,
_make_label,
current_git_head,
detect_variant,
@@ -482,7 +484,8 @@ class YoutubeDL:
The following options do not work when used through the API:
filename, abort-on-error, multistreams, no-live-chat,
format-sort, no-clean-infojson, no-playlist-metafiles,
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort.
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort,
mtime-by-default.
Refer __init__.py for their implementation
progress_template: Dictionary of templates for progress outputs.
Allowed keys are 'download', 'postprocess',
@@ -490,7 +493,7 @@ class YoutubeDL:
The template is mapped on a dictionary with keys 'progress' and 'info'
retry_sleep_functions: Dictionary of functions that takes the number of attempts
as argument and returns the time to sleep in seconds.
Allowed keys are 'http', 'fragment', 'file_access'
Allowed keys are 'http', 'fragment', 'file_access', 'extractor'
download_ranges: A callback function that gets called for every video with
the signature (info_dict, ydl) -> Iterable[Section].
Only the returned sections will be downloaded.
@@ -502,6 +505,7 @@ class YoutubeDL:
force_keyframes_at_cuts: Re-encode the video when downloading ranges to get precise cuts
noprogress: Do not print the progress bar
live_from_start: Whether to download livestreams videos from the start
warn_when_outdated: Emit a warning if the yt-dlp version is older than 90 days
The following parameters are not used by YoutubeDL itself, they are used by
the downloader (see yt_dlp/downloader/common.py):
@@ -528,6 +532,7 @@ class YoutubeDL:
discontinuities such as ad breaks (default: False)
extractor_args: A dictionary of arguments to be passed to the extractors.
See "EXTRACTOR ARGUMENTS" for details.
Argument values must always be a list of string(s).
E.g. {'youtube': {'skip': ['dash', 'hls']}}
mark_watched: Mark videos watched (even with --simulate). Only for YouTube
@@ -610,7 +615,7 @@ class YoutubeDL:
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'extra_param_to_key_url',
'hls_aes', 'downloader_options', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
'hls_aes', 'downloader_options', 'impersonate', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time',
}
_deprecated_multivalue_fields = {
@@ -700,6 +705,9 @@ def process_color_policy(stream):
system_deprecation = _get_system_deprecation()
if system_deprecation:
self.deprecated_feature(system_deprecation.replace('\n', '\n '))
elif self.params.get('warn_when_outdated'):
if outdated_warning := _get_outdated_warning():
self.report_warning(outdated_warning)
if self.params.get('allow_unplayable_formats'):
self.report_warning(
@@ -746,8 +754,6 @@ def check_deprecated(param, option, suggestion):
if self.params.get('geo_verification_proxy') is None:
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
check_deprecated('useid', '--id', '-o "%(id)s.%(ext)s"')
for msg in self.params.get('_warnings', []):
@@ -2194,7 +2200,7 @@ def _filter(f):
return op(actual_value, comparison_value)
return _filter
def _check_formats(self, formats):
def _check_formats(self, formats, warning=True):
for f in formats:
working = f.get('__working')
if working is not None:
@@ -2207,6 +2213,9 @@ def _check_formats(self, formats):
continue
temp_file = tempfile.NamedTemporaryFile(suffix='.tmp', delete=False, dir=path or None)
temp_file.close()
# If FragmentFD fails when testing a fragment, it will wrongly set a non-zero return code.
# Save the actual return code for later. See https://github.com/yt-dlp/yt-dlp/issues/13750
original_retcode = self._download_retcode
try:
success, _ = self.dl(temp_file.name, f, test=True)
except (DownloadError, OSError, ValueError, *network_exceptions):
@@ -2217,11 +2226,18 @@ def _check_formats(self, formats):
os.remove(temp_file.name)
except OSError:
self.report_warning(f'Unable to delete temporary file "{temp_file.name}"')
# Restore the actual return code
self._download_retcode = original_retcode
f['__working'] = success
if success:
f.pop('__needs_testing', None)
yield f
else:
self.to_screen('[info] Unable to download format {}. Skipping...'.format(f['format_id']))
msg = f'Unable to download format {f["format_id"]}. Skipping...'
if warning:
self.report_warning(msg)
else:
self.to_screen(f'[info] {msg}')
def _select_formats(self, formats, selector):
return list(selector({
@@ -2947,7 +2963,7 @@ def is_wellformed(f):
)
if self.params.get('check_formats') is True:
formats = LazyList(self._check_formats(formats[::-1]), reverse=True)
formats = LazyList(self._check_formats(formats[::-1], warning=False), reverse=True)
if not formats or formats[0] is not info_dict:
# only set the 'formats' fields if the original info_dict list them
@@ -3220,6 +3236,7 @@ def dl(self, name, info, subtitle=False, test=False):
}
else:
params = self.params
fd = get_suitable_downloader(info, params, to_stdout=(name == '-'))(self, params)
if not test:
for ph in self._progress_hooks:
@@ -3695,6 +3712,8 @@ def filter_fn(obj):
return {k: filter_fn(v) for k, v in obj.items() if not reject(k, v)}
elif isinstance(obj, (list, tuple, set, LazyList)):
return list(map(filter_fn, obj))
elif isinstance(obj, ImpersonateTarget):
return str(obj)
elif obj is None or isinstance(obj, (str, int, float, bool)):
return obj
else:
@@ -3963,6 +3982,7 @@ def simplified_codec(f, field):
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),
self._format_out('Untested', self.Styles.WARNING) if f.get('__needs_testing') else None,
format_field(f, 'format_note'),
format_field(f, 'container', ignore=(None, f.get('ext'))),
delim=', '), delim=' '),
@@ -4024,8 +4044,7 @@ def get_encoding(stream):
if os.environ.get('TERM', '').lower() == 'dumb':
additional_info.append('dumb')
if not supports_terminal_sequences(stream):
from .utils import WINDOWS_VT_MODE # Must be imported locally
additional_info.append('No VT' if WINDOWS_VT_MODE is False else 'No ANSI')
additional_info.append('No VT' if WINDOWS_VT_MODE.value is False else 'No ANSI')
if additional_info:
ret = f'{ret} ({",".join(additional_info)})'
return ret
@@ -4171,6 +4190,31 @@ def _impersonate_target_available(self, target):
for rh in self._request_director.handlers.values()
if isinstance(rh, ImpersonateRequestHandler))
def _parse_impersonate_targets(self, impersonate):
if impersonate in (True, ''):
impersonate = ImpersonateTarget()
requested_targets = [
t if isinstance(t, ImpersonateTarget) else ImpersonateTarget.from_str(t)
for t in variadic(impersonate)
] if impersonate else []
available_target = next(filter(self._impersonate_target_available, requested_targets), None)
return available_target, requested_targets
@staticmethod
def _unavailable_targets_message(requested_targets, note=None, is_error=False):
note = note or 'The extractor specified to use impersonation for this download'
specific_targets = ', '.join(filter(None, map(str, requested_targets)))
message = (
'no impersonate target is available' if not specific_targets
else f'none of these impersonate targets are available: {specific_targets}')
return (
f'{note}, but {message}. {"See" if is_error else "If you encounter errors, then see"}'
f' https://github.com/yt-dlp/yt-dlp#impersonation '
f'for information on installing the required dependencies')
def urlopen(self, req):
""" Start an HTTP download """
if isinstance(req, str):

View File

@@ -159,6 +159,12 @@ def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
elif 'prefer-vp9-sort' in opts.compat_opts:
opts.format_sort.extend(FormatSorter._prefer_vp9_sort)
if 'mtime-by-default' in opts.compat_opts:
if opts.updatetime is None:
opts.updatetime = True
else:
_unused_compat_opt('mtime-by-default')
_video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
_audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
if _video_multistreams_set is False and _audio_multistreams_set is False:
@@ -965,6 +971,7 @@ def parse_options(argv=None):
'geo_bypass': opts.geo_bypass,
'geo_bypass_country': opts.geo_bypass_country,
'geo_bypass_ip_block': opts.geo_bypass_ip_block,
'warn_when_outdated': opts.update_self is None,
'_warnings': warnings,
'_deprecation_warnings': deprecation_warnings,
'compat_opts': opts.compat_opts,
@@ -1024,6 +1031,7 @@ def _real_main(argv=None):
(ImpersonateTarget('safari'), 'curl_cffi'),
(ImpersonateTarget('firefox'), 'curl_cffi>=0.10'),
(ImpersonateTarget('edge'), 'curl_cffi'),
(ImpersonateTarget('tor'), 'curl_cffi>=0.11'),
]
available_targets = ydl._get_available_impersonate_targets()

View File

@@ -435,7 +435,7 @@ def sub_bytes_inv(data):
def rotate(data):
return data[1:] + [data[0]]
return [*data[1:], data[0]]
def key_schedule_core(data, rcon_iteration):

View File

@@ -37,7 +37,7 @@
from ..dependencies.Cryptodome import AES as compat_pycrypto_AES # noqa: F401
from ..networking.exceptions import HTTPError as compat_HTTPError
passthrough_module(__name__, '...utils', ('WINDOWS_VT_MODE', 'windows_enable_vt_mode'))
passthrough_module(__name__, '...utils', ('windows_enable_vt_mode',))
# compat_ctypes_WINFUNCTYPE = ctypes.WINFUNCTYPE

View File

@@ -1335,7 +1335,7 @@ def prepare_line(line):
if len(cookie_list) != self._ENTRY_LEN:
raise http.cookiejar.LoadError(f'invalid length {len(cookie_list)}')
cookie = self._CookieFileEntry(*cookie_list)
if cookie.expires_at and not cookie.expires_at.isdigit():
if cookie.expires_at and not re.fullmatch(r'[0-9]+(?:\.[0-9]+)?', cookie.expires_at):
raise http.cookiejar.LoadError(f'invalid expires at {cookie.expires_at}')
return line

View File

@@ -99,7 +99,7 @@ def _get_suitable_downloader(info_dict, protocol, params, default):
if external_downloader is None:
if info_dict['to_stdout'] and FFmpegFD.can_merge_formats(info_dict, params):
return FFmpegFD
elif external_downloader.lower() != 'native':
elif external_downloader.lower() != 'native' and info_dict.get('impersonate') is None:
ed = get_external_downloader(external_downloader)
if ed.can_download(info_dict, external_downloader):
return ed

View File

@@ -495,3 +495,14 @@ def _debug_cmd(self, args, exe=None):
exe = os.path.basename(args[0])
self.write_debug(f'{exe} command line: {shell_quote(args)}')
def _get_impersonate_target(self, info_dict):
impersonate = info_dict.get('impersonate')
if impersonate is None:
return None
available_target, requested_targets = self.ydl._parse_impersonate_targets(impersonate)
if available_target:
return available_target
elif requested_targets:
self.report_warning(self.ydl._unavailable_targets_message(requested_targets))
return None

View File

@@ -3,7 +3,7 @@
from . import get_suitable_downloader
from .fragment import FragmentFD
from ..utils import update_url_query, urljoin
from ..utils import ReExtractInfo, update_url_query, urljoin
class DashSegmentsFD(FragmentFD):
@@ -28,6 +28,11 @@ def real_download(self, filename, info_dict):
requested_formats = [{**info_dict, **fmt} for fmt in info_dict.get('requested_formats', [])]
args = []
for fmt in requested_formats or [info_dict]:
# Re-extract if --load-info-json is used and 'fragments' was originally a generator
# See https://github.com/yt-dlp/yt-dlp/issues/13906
if isinstance(fmt['fragments'], str):
raise ReExtractInfo('the stream needs to be re-extracted', expected=True)
try:
fragment_count = 1 if self.params.get('test') else len(fmt['fragments'])
except TypeError:

View File

@@ -572,7 +572,21 @@ def _call_downloader(self, tmpfilename, info_dict):
if end_time:
args += ['-t', str(end_time - start_time)]
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', fmt['url']]
url = fmt['url']
if self.params.get('enable_file_urls') and url.startswith('file:'):
# The default protocol_whitelist is 'file,crypto,data' when reading local m3u8 URLs,
# so only local segments can be read unless we also include 'http,https,tcp,tls'
args += ['-protocol_whitelist', 'file,crypto,data,http,https,tcp,tls']
# ffmpeg incorrectly handles 'file:' URLs by only removing the
# 'file:' prefix and treating the rest as if it's a normal filepath.
# FFmpegPostProcessor also depends on this behavior, so we need to fixup the URLs:
# - On Windows/Cygwin, replace 'file:///' and 'file://localhost/' with 'file:'
# - On *nix, replace 'file://localhost/' with 'file:/'
# Ref: https://github.com/yt-dlp/yt-dlp/issues/13781
# https://trac.ffmpeg.org/ticket/2702
url = re.sub(r'^file://(?:localhost)?/', 'file:' if os.name == 'nt' else 'file:/', url)
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', url]
if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):
args += ['-c', 'copy']

View File

@@ -302,7 +302,7 @@ def _finish_frag_download(self, ctx, info_dict):
elif to_file:
self.try_rename(ctx['tmpfilename'], ctx['filename'])
filetime = ctx.get('fragment_filetime')
if self.params.get('updatetime', True) and filetime:
if self.params.get('updatetime') and filetime:
with contextlib.suppress(Exception):
os.utime(ctx['filename'], (time.time(), filetime))

View File

@@ -94,12 +94,19 @@ def real_download(self, filename, info_dict):
can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None
if can_download:
has_ffmpeg = FFmpegFD.available()
no_crypto = not Cryptodome.AES and '#EXT-X-KEY:METHOD=AES-128' in s
if no_crypto and has_ffmpeg:
can_download, message = False, 'The stream has AES-128 encryption and pycryptodomex is not available'
elif no_crypto:
message = ('The stream has AES-128 encryption and neither ffmpeg nor pycryptodomex are available; '
'Decryption will be performed natively, but will be extremely slow')
if not Cryptodome.AES and '#EXT-X-KEY:METHOD=AES-128' in s:
# Even if pycryptodomex isn't available, force HlsFD for m3u8s that won't work with ffmpeg
ffmpeg_can_dl = not traverse_obj(info_dict, ((
'extra_param_to_segment_url', 'extra_param_to_key_url',
'hls_media_playlist_data', ('hls_aes', ('uri', 'key', 'iv')),
), any))
message = 'The stream has AES-128 encryption and {} available'.format(
'neither ffmpeg nor pycryptodomex are' if ffmpeg_can_dl and not has_ffmpeg else
'pycryptodomex is not')
if has_ffmpeg and ffmpeg_can_dl:
can_download = False
else:
message += '; decryption will be performed natively, but will be extremely slow'
elif info_dict.get('extractor_key') == 'Generic' and re.search(r'(?m)#EXT-X-MEDIA-SEQUENCE:(?!0$)', s):
install_ffmpeg = '' if has_ffmpeg else 'install ffmpeg and '
message = ('Live HLS streams are not supported by the native downloader. If this is a livestream, '
@@ -198,7 +205,7 @@ def is_ad_fragment_end(s):
line = line.strip()
if line:
if not line.startswith('#'):
if format_index and discontinuity_count != format_index:
if format_index is not None and discontinuity_count != format_index:
continue
if ad_frag_next:
continue
@@ -224,7 +231,7 @@ def is_ad_fragment_end(s):
byte_range = {}
elif line.startswith('#EXT-X-MAP'):
if format_index and discontinuity_count != format_index:
if format_index is not None and discontinuity_count != format_index:
continue
if frag_index > 0:
self.report_error(

View File

@@ -27,6 +27,10 @@ class HttpFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
request_data = info_dict.get('request_data', None)
request_extensions = {}
impersonate_target = self._get_impersonate_target(info_dict)
if impersonate_target is not None:
request_extensions['impersonate'] = impersonate_target
class DownloadContext(dict):
__getattr__ = dict.get
@@ -109,7 +113,7 @@ def establish_connection():
if try_call(lambda: range_end >= ctx.content_len):
range_end = ctx.content_len - 1
request = Request(url, request_data, headers)
request = Request(url, request_data, headers, extensions=request_extensions)
has_range = range_start is not None
if has_range:
request.headers['Range'] = f'bytes={int(range_start)}-{int_or_none(range_end) or ""}'
@@ -348,7 +352,7 @@ def retry(e):
self.try_rename(ctx.tmpfilename, ctx.filename)
# Update file modification time
if self.params.get('updatetime', True):
if self.params.get('updatetime'):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None))
self._hook_progress({

View File

@@ -5,47 +5,46 @@
from .common import FileDownloader
from .external import FFmpegFD
from ..networking import Request
from ..utils import DownloadError, str_or_none, try_get
from ..networking.websocket import WebSocketResponse
from ..utils import DownloadError, str_or_none, truncate_string
from ..utils.traversal import traverse_obj
class NiconicoLiveFD(FileDownloader):
""" Downloads niconico live without being stopped """
def real_download(self, filename, info_dict):
video_id = info_dict['video_id']
ws_url = info_dict['url']
ws_extractor = info_dict['ws']
ws_origin_host = info_dict['origin']
live_quality = info_dict.get('live_quality', 'high')
live_latency = info_dict.get('live_latency', 'high')
video_id = info_dict['id']
opts = info_dict['downloader_options']
quality, ws_extractor, ws_url = opts['max_quality'], opts['ws'], opts['ws_url']
dl = FFmpegFD(self.ydl, self.params or {})
new_info_dict = info_dict.copy()
new_info_dict.update({
'protocol': 'm3u8',
})
new_info_dict['protocol'] = 'm3u8'
def communicate_ws(reconnect):
if reconnect:
ws = self.ydl.urlopen(Request(ws_url, headers={'Origin': f'https://{ws_origin_host}'}))
# Support --load-info-json as if it is a reconnect attempt
if reconnect or not isinstance(ws_extractor, WebSocketResponse):
ws = self.ydl.urlopen(Request(
ws_url, headers={'Origin': 'https://live.nicovideo.jp'}))
if self.ydl.params.get('verbose', False):
self.to_screen('[debug] Sending startWatching request')
self.write_debug('Sending startWatching request')
ws.send(json.dumps({
'type': 'startWatching',
'data': {
'reconnect': True,
'room': {
'commentable': True,
'protocol': 'webSocket',
},
'stream': {
'quality': live_quality,
'protocol': 'hls+fmp4',
'latency': live_latency,
'accessRightMethod': 'single_cookie',
'chasePlay': False,
'latency': 'high',
'protocol': 'hls',
'quality': quality,
},
'room': {
'protocol': 'webSocket',
'commentable': True,
},
'reconnect': True,
},
'type': 'startWatching',
}))
else:
ws = ws_extractor
@@ -58,7 +57,6 @@ def communicate_ws(reconnect):
if not data or not isinstance(data, dict):
continue
if data.get('type') == 'ping':
# pong back
ws.send(r'{"type":"pong"}')
ws.send(r'{"type":"keepSeat"}')
elif data.get('type') == 'disconnect':
@@ -66,12 +64,10 @@ def communicate_ws(reconnect):
return True
elif data.get('type') == 'error':
self.write_debug(data)
message = try_get(data, lambda x: x['body']['code'], str) or recv
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
return DownloadError(message)
elif self.ydl.params.get('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.to_screen(f'[debug] Server said: {recv}')
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
def ws_main():
reconnect = False
@@ -81,7 +77,8 @@ def ws_main():
if ret is True:
return
except BaseException as e:
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
self.to_screen(
f'[niconico:live] {video_id}: Connection error occured, reconnecting after 10 seconds: {e}')
time.sleep(10)
continue
finally:

View File

@@ -201,7 +201,6 @@
BanByeChannelIE,
BanByeIE,
)
from .bandaichannel import BandaiChannelIE
from .bandcamp import (
BandcampAlbumIE,
BandcampIE,
@@ -229,7 +228,6 @@
from .beatport import BeatportIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
from .berufetv import BerufeTVIE
from .bet import BetIE
from .bfi import BFIPlayerIE
@@ -275,7 +273,10 @@
BitChuteChannelIE,
BitChuteIE,
)
from .blackboardcollaborate import BlackboardCollaborateIE
from .blackboardcollaborate import (
BlackboardCollaborateIE,
BlackboardCollaborateLaunchIE,
)
from .bleacherreport import (
BleacherReportCMSIE,
BleacherReportIE,
@@ -300,7 +301,6 @@
BrainPOPIlIE,
BrainPOPJrIE,
)
from .bravotv import BravoTVIE
from .breitbart import BreitBartIE
from .brightcove import (
BrightcoveLegacyIE,
@@ -310,6 +310,7 @@
BrilliantpalaClassesIE,
BrilliantpalaElearnIE,
)
from .btvplus import BTVPlusIE
from .bundesliga import BundesligaIE
from .bundestag import BundestagIE
from .bunnycdn import BunnyCdnIE
@@ -447,7 +448,6 @@
CSpanIE,
)
from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .curiositystream import (
@@ -571,10 +571,6 @@
DWIE,
DWArticleIE,
)
from .eagleplatform import (
ClipYouEmbedIE,
EaglePlatformIE,
)
from .ebaumsworld import EbaumsWorldIE
from .ebay import EbayIE
from .egghead import (
@@ -640,6 +636,7 @@
FancodeVodIE,
)
from .fathom import FathomIE
from .faulio import FaulioLiveIE
from .faz import FazIE
from .fc2 import (
FC2IE,
@@ -806,9 +803,7 @@
from .hotnewhiphop import HotNewHipHopIE
from .hotstar import (
HotStarIE,
HotStarPlaylistIE,
HotStarPrefixIE,
HotStarSeasonIE,
HotStarSeriesIE,
)
from .hrefli import HrefLiRedirectIE
@@ -922,10 +917,6 @@
ShugiinItvVodIE,
)
from .jeuxvideo import JeuxVideoIE
from .jiocinema import (
JioCinemaIE,
JioCinemaSeriesIE,
)
from .jiosaavn import (
JioSaavnAlbumIE,
JioSaavnArtistIE,
@@ -935,7 +926,6 @@
JioSaavnSongIE,
)
from .joj import JojIE
from .joqrag import JoqrAgIE
from .jove import JoveIE
from .jstream import JStreamIE
from .jtbc import (
@@ -1038,11 +1028,6 @@
LikeeIE,
LikeeUserIE,
)
from .limelight import (
LimelightChannelIE,
LimelightChannelListIE,
LimelightMediaIE,
)
from .linkedin import (
LinkedInEventsIE,
LinkedInIE,
@@ -1108,6 +1093,7 @@
from .massengeschmacktv import MassengeschmackTVIE
from .masters import MastersIE
from .matchtv import MatchTVIE
from .mave import MaveIE
from .mbn import MBNIE
from .mdr import MDRIE
from .medaltv import MedalTVIE
@@ -1153,6 +1139,7 @@
MindsIE,
)
from .minoto import MinotoIE
from .mir24tv import Mir24TvIE
from .mirrativ import (
MirrativIE,
MirrativUserIE,
@@ -1173,6 +1160,10 @@
MixcloudPlaylistIE,
MixcloudUserIE,
)
from .mixlr import (
MixlrIE,
MixlrRecoringIE,
)
from .mlb import (
MLBIE,
MLBTVIE,
@@ -1262,6 +1253,7 @@
)
from .nbc import (
NBCIE,
BravoTVIE,
NBCNewsIE,
NBCOlympicsIE,
NBCOlympicsStreamIE,
@@ -1269,6 +1261,7 @@
NBCSportsStreamIE,
NBCSportsVPlayerIE,
NBCStationsIE,
SyfyIE,
)
from .ndr import (
NDRIE,
@@ -1381,7 +1374,6 @@
from .noice import NoicePodcastIE
from .nonktube import NonkTubeIE
from .noodlemagazine import NoodleMagazineIE
from .noovo import NoovoIE
from .nosnl import NOSNLArticleIE
from .nova import (
NovaEmbedIE,
@@ -1562,6 +1554,7 @@
PlatziCourseIE,
PlatziIE,
)
from .playerfm import PlayerFmIE
from .playplustv import PlayPlusTVIE
from .playsuisse import PlaySuisseIE
from .playtvak import PlaytvakIE
@@ -1572,6 +1565,7 @@
)
from .plutotv import PlutoTVIE
from .plvideo import PlVideoIE
from .plyr import PlyrEmbedIE
from .podbayfm import (
PodbayFMChannelIE,
PodbayFMIE,
@@ -1787,6 +1781,7 @@
RTVEALaCartaIE,
RTVEAudioIE,
RTVELiveIE,
RTVEProgramIE,
RTVETelevisionIE,
)
from .rtvs import RTVSIE
@@ -1828,6 +1823,7 @@
from .saitosan import SaitosanIE
from .samplefocus import SampleFocusIE
from .sapo import SapoIE
from .sauceplus import SaucePlusIE
from .sbs import SBSIE
from .sbscokr import (
SBSCoKrAllvodProgramIE,
@@ -1870,6 +1866,7 @@
from .sharepoint import SharePointIE
from .sharevideos import ShareVideosEmbedIE
from .shemaroome import ShemarooMeIE
from .shiey import ShieyIE
from .showroomlive import ShowRoomLiveIE
from .sibnet import SibnetEmbedIE
from .simplecast import (
@@ -2016,13 +2013,11 @@
SverigesRadioPublicationIE,
)
from .svt import (
SVTIE,
SVTPageIE,
SVTPlayIE,
SVTSeriesIE,
)
from .swearnet import SwearnetEpisodeIE
from .syfy import SyfyIE
from .syvdk import SYVDKIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE
@@ -2101,6 +2096,7 @@
TheGuardianPodcastIE,
TheGuardianPodcastPlaylistIE,
)
from .thehighwire import TheHighWireIE
from .theholetv import TheHoleTvIE
from .theintercept import TheInterceptIE
from .theplatform import (
@@ -2147,6 +2143,7 @@
from .toggo import ToggoIE
from .tonline import TOnlineIE
from .toongoggles import ToonGogglesIE
from .toutiao import ToutiaoIE
from .toutv import TouTvIE
from .toypics import (
ToypicsIE,
@@ -2169,7 +2166,6 @@
from .trueid import TrueIDIE
from .trunews import TruNewsIE
from .truth import TruthIE
from .trutv import TruTVIE
from .tube8 import Tube8IE
from .tubetugraz import (
TubeTuGrazIE,
@@ -2240,6 +2236,7 @@
from .tvplayer import TVPlayerIE
from .tvw import (
TvwIE,
TvwNewsIE,
TvwTvChannelsIE,
)
from .tweakers import TweakersIE
@@ -2288,6 +2285,7 @@
)
from .umg import UMGDeIE
from .unistra import UnistraIE
from .unitednations import UnitedNationsWebTvIE
from .unity import UnityIE
from .unsupported import (
KnownDRMIE,

View File

@@ -3,6 +3,7 @@
import re
import time
import urllib.parse
import uuid
import xml.etree.ElementTree as etree
from .common import InfoExtractor
@@ -10,6 +11,7 @@
from ..utils import (
NO_DEFAULT,
ExtractorError,
parse_qs,
unescapeHTML,
unified_timestamp,
urlencode_postdata,
@@ -45,6 +47,7 @@
'name': 'Comcast XFINITY',
'username_field': 'user',
'password_field': 'passwd',
'login_hostname': 'login.xfinity.com',
},
'TWC': {
'name': 'Time Warner Cable | Spectrum',
@@ -74,6 +77,12 @@
'name': 'Verizon FiOS',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
'login_hostname': 'ssoauth.verizon.com',
},
'Fubo': {
'name': 'Fubo',
'username_field': 'username',
'password_field': 'password',
},
'Cablevision': {
'name': 'Optimum/Cablevision',
@@ -1338,6 +1347,7 @@
'name': 'Sling TV',
'username_field': 'username',
'password_field': 'password',
'login_hostname': 'identity.sling.com',
},
'Suddenlink': {
'name': 'Suddenlink',
@@ -1355,7 +1365,6 @@
class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MODERN_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0'
_MVPD_CACHE = 'ap-mvpd'
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
@@ -1367,6 +1376,11 @@ def _download_webpage_handle(self, *args, **kwargs):
return super()._download_webpage_handle(
*args, **kwargs)
@staticmethod
def _get_mso_headers(mso_info):
# Not needed currently
return {}
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
@@ -1382,7 +1396,13 @@ def _get_mvpd_resource(provider_id, title, guid, rating):
resource_rating.text = rating
return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource, software_statement):
mso_id = self.get_param('ap_mso')
if mso_id:
mso_info = MSO_INFO[mso_id]
else:
mso_info = {}
def xml_text(xml_str, tag):
return self._search_regex(
f'<{tag}>(.+?)</{tag}>', xml_str, tag)
@@ -1391,15 +1411,27 @@ def is_expired(token, date_ele):
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
return token_expires and token_expires <= int(time.time())
def post_form(form_page_res, note, data={}):
def post_form(form_page_res, note, data={}, validate_url=False):
form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = urllib.parse.urljoin(urlh.url, post_url)
if validate_url:
# This request is submitting credentials so we should validate it when possible
url_parsed = urllib.parse.urlparse(post_url)
expected_hostname = mso_info.get('login_hostname')
if expected_hostname and expected_hostname != url_parsed.hostname:
raise ExtractorError(
f'Unexpected login URL hostname; expected "{expected_hostname}" but got '
f'"{url_parsed.hostname}". Aborting before submitting credentials')
if url_parsed.scheme != 'https':
self.write_debug('Upgrading login URL scheme to https')
post_url = urllib.parse.urlunparse(url_parsed._replace(scheme='https'))
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
post_url, video_id, note, data=urlencode_postdata(form_data), headers={
**self._get_mso_headers(mso_info),
'Content-Type': 'application/x-www-form-urlencoded',
})
@@ -1432,40 +1464,72 @@ def extract_redirect_url(html, url=None, fatal=False):
}
guid = xml_text(resource, 'guid') if '<' in resource else resource
count = 0
while count < 2:
for _ in range(2):
requestor_info = self.cache.load(self._MVPD_CACHE, requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
authn_token = None
if not authn_token:
mso_id = self.get_param('ap_mso')
if mso_id:
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
if not username or not password:
raise_mvpd_required()
mso_info = MSO_INFO[mso_id]
provider_redirect_page_res = self._download_webpage_handle(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
}, headers={
# yt-dlp's default user-agent is usually too old for Comcast_SSO
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
'User-Agent': self._MODERN_USER_AGENT,
} if mso_id == 'Comcast_SSO' else None)
elif not self._cookies_passed:
if not mso_id:
raise_mvpd_required()
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
if not username or not password:
raise_mvpd_required()
if not mso_id:
pass
elif mso_id == 'Comcast_SSO':
device_info, urlh = self._download_json_handle(
'https://sp.auth.adobe.com/indiv/devices',
video_id, 'Registering device with Adobe',
data=json.dumps({'fingerprint': uuid.uuid4().hex}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
device_id = device_info['deviceId']
mvpd_headers['pass_sfp'] = urlh.get_header('pass_sfp')
mvpd_headers['Ap_21'] = device_id
registration = self._download_json(
'https://sp.auth.adobe.com/o/client/register',
video_id, 'Registering client with Adobe',
data=json.dumps({'software_statement': software_statement}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
access_token = self._download_json(
'https://sp.auth.adobe.com/o/client/token', video_id,
'Obtaining access token', data=urlencode_postdata({
'grant_type': 'client_credentials',
'client_id': registration['client_id'],
'client_secret': registration['client_secret'],
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
})['access_token']
mvpd_headers['Authorization'] = f'Bearer {access_token}'
reg_code = self._download_json(
f'https://sp.auth.adobe.com/reggie/v1/{requestor_id}/regcode',
video_id, 'Obtaining registration code',
data=urlencode_postdata({
'requestor': requestor_id,
'deviceId': device_id,
'format': 'json',
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Authorization': f'Bearer {access_token}',
})['code']
provider_redirect_page_res = self._download_webpage_handle(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
'reg_code': reg_code,
}, headers=self._get_mso_headers(mso_info))
if mso_id == 'Comcast_SSO':
# Comcast page flow varies by video site and whether you
# are on Comcast's network.
provider_redirect_page, urlh = provider_redirect_page_res
@@ -1489,8 +1553,8 @@ def extract_redirect_url(html, url=None, fatal=False):
oauth_redirect_url = extract_redirect_url(
provider_redirect_page, fatal=True)
provider_login_page_res = self._download_webpage_handle(
oauth_redirect_url, video_id,
self._DOWNLOADING_LOGIN_PAGE)
oauth_redirect_url, video_id, self._DOWNLOADING_LOGIN_PAGE,
headers=self._get_mso_headers(mso_info))
else:
provider_login_page_res = post_form(
provider_redirect_page_res,
@@ -1500,24 +1564,35 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
mvpd_confirm_page, urlh = mvpd_confirm_page_res
if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Philo':
# Philo has very unique authentication method
self._download_webpage(
'https://idp.philo.com/auth/init/login_code', video_id, 'Requesting auth code', data=urlencode_postdata({
self._request_webpage(
'https://idp.philo.com/auth/init/login_code', video_id,
'Requesting Philo auth code', data=json.dumps({
'ident': username,
'device': 'web',
'send_confirm_link': False,
'send_token': True,
}))
'device_ident': f'web-{uuid.uuid4().hex}',
'include_login_link': True,
}).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
philo_code = getpass.getpass('Type auth code you have received [Return]: ')
self._download_webpage(
'https://idp.philo.com/auth/update/login_code', video_id, 'Submitting token', data=urlencode_postdata({
'token': philo_code,
}))
self._request_webpage(
'https://idp.philo.com/auth/update/login_code', video_id,
'Submitting token', data=json.dumps({'token': philo_code}).encode(),
headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
mvpd_confirm_page_res = self._download_webpage_handle('https://idp.philo.com/idp/submit', video_id, 'Confirming Philo Login')
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Verizon':
@@ -1539,7 +1614,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_redirect_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
saml_login_page, urlh = saml_login_page_res
if 'Please try again.' in saml_login_page:
raise ExtractorError(
@@ -1560,7 +1635,7 @@ def extract_redirect_url(html, url=None, fatal=False):
[saml_login_page, saml_redirect_url], 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
if 'Please try again.' in saml_login_page:
raise ExtractorError(
'Failed to login, incorrect User ID or Password.')
@@ -1631,7 +1706,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1682,7 +1757,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1699,6 +1774,27 @@ def extract_redirect_url(html, url=None, fatal=False):
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Fubo':
_, urlh = provider_redirect_page_res
fubo_response = self._download_json(
'https://api.fubo.tv/partners/tve/connect', video_id,
'Authenticating with Fubo', 'Unable to authenticate with Fubo',
query=parse_qs(urlh.url), data=json.dumps({
'username': username,
'password': password,
}).encode(), headers={
'Accept': 'application/json',
'Content-Type': 'application/json',
})
self._request_webpage(
'https://sp.auth.adobe.com/adobe-services/oauth2', video_id,
'Authenticating with Adobe', 'Failed to authenticate with Adobe',
query={
'code': fubo_response['code'],
'state': fubo_response['state'],
})
else:
# Some providers (e.g. DIRECTV NOW) have another meta refresh
# based redirect that should be followed.
@@ -1717,7 +1813,8 @@ def extract_redirect_url(html, url=None, fatal=False):
}
if mso_id in ('Cablevision', 'AlticeOne'):
form_data['_eventId_proceed'] = ''
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', form_data)
mvpd_confirm_page_res = post_form(
provider_login_page_res, 'Logging in', form_data, validate_url=True)
if mso_id != 'Rogers':
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1727,6 +1824,7 @@ def extract_redirect_url(html, url=None, fatal=False):
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
'reg_code': reg_code,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -1734,7 +1832,6 @@ def extract_redirect_url(html, url=None, fatal=False):
raise
if '<pendingLogout' in session:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
requestor_info['authn_token'] = authn_token
@@ -1755,7 +1852,6 @@ def extract_redirect_url(html, url=None, fatal=False):
}), headers=mvpd_headers)
if '<pendingLogout' in authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
if '<error' in authorize:
raise ExtractorError(xml_text(authorize, 'details'), expected=True)
@@ -1778,6 +1874,5 @@ def extract_redirect_url(html, url=None, fatal=False):
}), headers=mvpd_headers)
if '<pendingLogout' in short_authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
return short_authorize

View File

@@ -84,9 +84,10 @@ def _parse_video_data(self, video_data):
class AdobeTVEmbedIE(AdobeTVBaseIE):
_WORKING = False
IE_NAME = 'adobetv:embed'
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'https://tv.adobe.com/embed/22/4153',
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
'info_dict': {
@@ -94,12 +95,12 @@ class AdobeTVEmbedIE(AdobeTVBaseIE):
'ext': 'flv',
'title': 'Creating Graphics Optimized for BlackBerry',
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
'thumbnail': r're:https?://.*\.jpg$',
'thumbnail': r're:https?://.+\.jpg',
'upload_date': '20091109',
'duration': 377,
'view_count': int,
},
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -110,10 +111,10 @@ def _real_extract(self, url):
class AdobeTVIE(AdobeTVBaseIE):
_WORKING = False
IE_NAME = 'adobetv'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
_TESTS = [{
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
@@ -121,12 +122,12 @@ class AdobeTVIE(AdobeTVBaseIE):
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': r're:https?://.*\.jpg$',
'thumbnail': r're:https?://.+\.jpg',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
}]
def _real_extract(self, url):
language, show_urlname, urlname = self._match_valid_url(url).groups()
@@ -159,10 +160,10 @@ def _extract_playlist_entries(self, display_id, query):
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
_WORKING = False
IE_NAME = 'adobetv:show'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
_TESTS = [{
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
'info_dict': {
'id': '36',
@@ -170,7 +171,7 @@ class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
},
'playlist_mincount': 136,
}
}]
_RESOURCE = 'episode'
_process_data = AdobeTVBaseIE._parse_video_data
@@ -195,16 +196,16 @@ def _real_extract(self, url):
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
_WORKING = False
IE_NAME = 'adobetv:channel'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
_TESTS = [{
'url': 'http://tv.adobe.com/channel/development',
'info_dict': {
'id': 'development',
},
'playlist_mincount': 96,
}
}]
_RESOURCE = 'show'
def _process_data(self, show_data):
@@ -231,8 +232,7 @@ class AdobeTVVideoIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:video'
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
_TEST = {
_TESTS = [{
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
'url': 'https://video.tv.adobe.com/v/2456/',
'md5': '43662b577c018ad707a63766462b1e87',
@@ -242,8 +242,20 @@ class AdobeTVVideoIE(AdobeTVBaseIE):
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
},
}
}]
_WEBPAGE_TESTS = [{
# FIXME: Invalid extension
'url': 'https://www.adobe.com/learn/acrobat/web/customize-toolbar',
'info_dict': {
'id': '3463980',
'ext': 'm3u8',
'title': 'Adobe Acrobat: How to Customize the Toolbar for Faster PDF Editing',
'description': 'md5:94368ab95ae24f9c1bee0cb346e03dc3',
'duration': 97.557,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -84,6 +84,8 @@ class AdultSwimIE(TurnerBaseIE):
'skip': '404 Not Found',
}]
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwNjg5ZmU2My00OTc5LTQxZmQtYWYxNC1hYjVlNmJjNWVkZWIiLCJuYmYiOjE1MzcxOTA2NzQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwNjc0fQ.Xl3AEduM0s1TxDQ6-XssdKIiLm261hhsEv1C1yo_nitIajZThSI9rXILqtIzO0aujoHhdzUnu_dUCq9ffiSBzEG632tTa1la-5tegHtce80cMhewBN4n2t8n9O5tiaPx8MPY8ALdm5wS7QzWE6DO_LTJKgE8Bl7Yv-CWJT4q4SywtNiQWLVOuhBRnDyfsRezxRwptw8qTn9dv5ZzUrVJaby5fDZ_nOncMKvegOgaKd5KEuCAGQ-mg-PSuValMjGuf6FwDguGaK7IyI5Y2oOrzXmD4Dj7q4WBg8w9QoZhtLeAU56mcsGILolku2R5FHlVLO9xhjResyt-pfmegOkpSw'
def _real_extract(self, url):
show_path, episode_path = self._match_valid_url(url).groups()
display_id = episode_path or show_path
@@ -152,7 +154,7 @@ def _real_extract(self, url):
# CDN_TOKEN_APP_ID from:
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
}, {
}, self._SOFTWARE_STATEMENT, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': auth,

View File

@@ -1,3 +1,5 @@
import json
from .theplatform import ThePlatformIE
from ..utils import (
ExtractorError,
@@ -6,7 +8,6 @@
remove_start,
traverse_obj,
update_url_query,
urlencode_postdata,
)
@@ -20,13 +21,13 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
'biography.com': (None, 'biography'),
'history.com': ('HISTORY', 'history', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzZlMTQ3ZS0zMzFhLTQxY2YtYTMwNC01MDA2NzNlOGYwYjYiLCJuYmYiOjE1Mzg2NjMzMDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMzA5fQ.n24-FVHLGXJe2D4atIQZ700aiXKIajKh5PWFoHJ40Az4itjtwwSFHnvufnoal3T8lYkwNLxce7H-IEGxIykRkZEdwq09pMKMT-ft9ASzE4vQ8fAWbf5ZgDME86x4Jq_YaxkRc9Ne0eShGhl8fgTJHvk07sfWcol61HJ7kU7K8FzzcHR0ucFQgA5VNd8RyjoGWY7c6VxnXR214LOpXsywmit04-vGJC102b_WA2EQfqI93UzG6M6l0EeV4n0_ijP3s8_i8WMJZ_uwnTafCIY6G_731i01dKXDLSFzG1vYglAwDa8DTcdrAAuIFFDF6QNGItCCmwbhjufjmoeVb7R1Gg'),
'aetv.com': ('AETV', 'aetv', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI5Y2IwNjg2Yy03ODUxLTRiZDUtODcyMC00MjNlZTg1YTQ1NzMiLCJuYmYiOjE1Mzg2NjMyOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMjkwfQ.T5Elf0X4TndO4NEgqBas1gDxNHGPVk_daO2Ha5FBzVO6xi3zM7eavdAKfYMCN7gpWYJx03iADaVPtczO_t_aGZczDjpwJHgTUzDgvcLZAVsVDqtDIAMy3S846rPgT6UDbVoxurA7B2VTPm9phjrSXhejvd0LBO8MQL4AZ3sy2VmiPJ2noT1ily5PuHCYlkrT1fheO064duR__Cd9DQ5VTMnKjzY3Cx345CEwKDkUk5gwgxhXM-aY0eblehrq8VD81_aRM_O3tvh7nbTydHOnUpV-k_iKVi49gqz7Sf8zb6Zh5z2Uftn3vYCfE5NQuesitoRMnsH17nW7o_D59hkRgg'),
'mylifetime.com': ('LIFETIME', 'lifetime', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJmODg0MDM1ZC1mZGRmLTRmYjgtYmRkMC05MzRhZDdiYTAwYTciLCJuYmYiOjE1NDkzOTI2NDQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQ5MzkyNjQ0fQ.vkTIaCpheKdKQd__2-3ec4qkcpbAhyCTvwe5iTl922ItSQfVhpEJG4wseVSNmBTrpBi0hvLedcw6Hj1_UuzBMVuVcCqLprU-pI8recEwL0u7G-eVkylsxe1OTUm1o3V6OykXQ9KlA-QQLL1neUhdhR1n5B1LZ4cmtBmiEpfgf4rFwXD1ScFylIcaWKLBqHoRBNUmxyTmoXXvn_A-GGSj9eCizFzY8W5uBwUcsoiw2Cr1skx7PbB2RSP1I5DsoIJKG-8XV1KS7MWl-fNLjE-hVAsI9znqfEEFcPBiv3LhCP4Nf4OIs7xAselMn0M0c8igRUZhURWX_hdygUAxkbKFtQ'),
'fyi.tv': ('FYI', 'fyi', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxOGZiOWM3Ny1mYmMzLTQxYTktYmE1Yi1lMzM0ZmUzNzU4NjEiLCJuYmYiOjE1ODc1ODAzNzcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NTgwMzc3fQ.AYDuipKswmIfLBfOjHRsfc5fMV5NmJUmiJnkpiep4VEw9QiXkygFj4bN06Si5tFc5Mee5TDrGzDpV6iuKbVpLT5kuqXhAn-Wozf5zKPsg_IpdEKO7gsiCq4calt72ct44KTqtKD_hVcoxQU24_HaJsRgXzu3B-6Ff6UrmsXkyvYifYVC9v2DSkdCuA02_IrlllzVT2kRuefUXgL4vQRtTFf77uYa0RKSTG7uVkiQ_AU41eXevKlO2qgtc14Hk5cZ7-ZNrDyMCXYA5ngdIHP7Gs9PWaFXT36PFHI_rC4EfxUABPzjQFxjpP75aX5qn8SH__HbM9q3hoPWgaEaf76qIQ'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc', None),
'historyvault.com': (None, 'historyvault', None),
'biography.com': (None, 'biography', None),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
@@ -71,7 +72,7 @@ def _extract_aen_smil(self, smil_url, video_id, auth=None):
}
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
requestor_id, brand, software_statement = self._DOMAIN_MAP[domain]
result = self._download_json(
f'https://feeds.video.aetnd.com/api/v2/{brand}/videos',
filter_value, query={f'filter[{filter_key}]': filter_value})
@@ -95,7 +96,7 @@ def _extract_aetn_info(self, domain, filter_key, filter_value, url):
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
traverse_obj(theplatform_metadata, ('ratings', 0, 'rating')))
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, requestor_id, resource, software_statement)
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
@@ -110,11 +111,9 @@ class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
shows/[^/?#]+/season-\d+/episode-\d+|
(?P<type>movie|special)s/[^/?#]+(?P<extra>/[^/?#]+)?|
(?:shows/[^/?#]+/)?videos/[^/?#]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
@@ -127,20 +126,18 @@ class AENetworksIE(AENetworksBaseIE):
'upload_date': '20120529',
'uploader': 'AENE-NEW',
'duration': 2592.0,
'thumbnail': r're:^https?://.*\.jpe?g$',
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:5',
'tags': 'count:14',
'categories': ['Mountain Men'],
'episode_number': 1,
'episode': 'Episode 1',
'episode': 'Winter Is Coming',
'season': 'Season 1',
'season_number': 1,
'series': 'Mountain Men',
'age_limit': 0,
},
'params': {
# m3u8 download
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
'skip': 'Geo-restricted - This content is not available in your location.',
}, {
@@ -154,21 +151,64 @@ class AENetworksIE(AENetworksBaseIE):
'upload_date': '20160112',
'uploader': 'AENE-NEW',
'duration': 1277.695,
'thumbnail': r're:^https?://.*\.jpe?g$',
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:4',
'tags': 'count:23',
'episode': 'Episode 1',
'episode': 'Inlawful Entry',
'episode_number': 1,
'season': 'Season 9',
'season_number': 9,
'series': 'Duck Dynasty',
'age_limit': 0,
},
'params': {
# m3u8 download
'skip_download': True,
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
}, {
'url': 'https://play.mylifetime.com/movies/v-c-andrews-web-of-dreams',
'info_dict': {
'id': '1590627395981',
'ext': 'mp4',
'title': 'VC Andrews\' Web of Dreams',
'description': 'md5:2a8ba13ae64271c79eb65c0577d312ce',
'uploader': 'AENE-NEW',
'age_limit': 14,
'duration': 5253.665,
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:8',
'tags': ['lifetime', 'mylifetime', 'lifetime channel', "VC Andrews' Web of Dreams"],
'series': '',
'season': 'Season 0',
'season_number': 0,
'episode': 'VC Andrews\' Web of Dreams',
'episode_number': 0,
'timestamp': 1566489703.0,
'upload_date': '20190822',
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story',
'info_dict': {
'id': '1488235587551',
'ext': 'mp4',
'title': 'Hunting JonBenet\'s Killer: The Untold Story',
'description': 'md5:209869425ee392d74fe29201821e48b4',
'uploader': 'AENE-NEW',
'age_limit': 14,
'duration': 5003.903,
'thumbnail': r're:https?://.+/.+\.jpg',
'chapters': 'count:10',
'tags': 'count:11',
'series': '',
'season': 'Season 0',
'season_number': 0,
'episode': 'Hunting JonBenet\'s Killer: The Untold Story',
'episode_number': 0,
'timestamp': 1554987697.0,
'upload_date': '20190411',
},
'params': {'skip_download': 'm3u8'},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True,
@@ -196,25 +236,28 @@ class AENetworksIE(AENetworksBaseIE):
}]
def _real_extract(self, url):
domain, canonical = self._match_valid_url(url).groups()
domain, canonical, url_type, extra = self._match_valid_url(url).group('domain', 'id', 'type', 'extra')
if url_type in ('movie', 'special') and not extra:
canonical += f'/full-{url_type}'
return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'https://yoga.appsvcs.aetnd.com/graphql', slug,
query={'brand': brand}, headers={'Content-Type': 'application/json'},
data=json.dumps({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields), # noqa: UP031
}))['data'][resource]
}).encode())['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
_, brand, _ = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = f'http://watch.{domain}'

View File

@@ -11,12 +11,11 @@ class APAIE(InfoExtractor):
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@@ -28,6 +27,15 @@ class APAIE(InfoExtractor):
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.vol.at/blue-man-group/5593454',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:https?://kf-vn\.sf\.apa\.at/vn/.+\.jpg',
},
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)

View File

@@ -16,6 +16,7 @@
dict_get,
extract_attributes,
get_element_by_id,
get_element_text_and_html_by_tag,
int_or_none,
join_nonempty,
js_to_json,
@@ -32,7 +33,6 @@
unified_timestamp,
url_or_none,
urlhandle_detect_ext,
variadic,
)
@@ -72,6 +72,7 @@ class ArchiveOrgIE(InfoExtractor):
'display_id': 'Cops-v2.mp4',
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'duration': 1091.96,
'track': 'Cops-v2',
},
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
@@ -86,6 +87,7 @@ class ArchiveOrgIE(InfoExtractor):
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'duration': 59.77,
'display_id': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
'track': 'Commercial-JFK1960ElectionAdCampaignJingle',
},
}, {
'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
@@ -102,6 +104,7 @@ class ArchiveOrgIE(InfoExtractor):
'duration': 59.51,
'license': 'http://creativecommons.org/licenses/publicdomain/',
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'track': 'Commercial-Nixon1960ElectionAdToughonDefense',
},
}, {
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
@@ -182,6 +185,7 @@ class ArchiveOrgIE(InfoExtractor):
'duration': 130.46,
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_01_000117.jpg',
'display_id': 'irelandthemakingofarepublicreel1_01.mov',
'track': 'irelandthemakingofarepublicreel1 01',
},
}, {
'md5': '67335ee3b23a0da930841981c1e79b02',
@@ -192,6 +196,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'irelandthemakingofarepublicreel1_02.mov',
'display_id': 'irelandthemakingofarepublicreel1_02.mov',
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_02_001374.jpg',
'track': 'irelandthemakingofarepublicreel1 02',
},
}, {
'md5': 'e470e86787893603f4a341a16c281eb5',
@@ -202,6 +207,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'irelandthemakingofarepublicreel2.mov',
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
'display_id': 'irelandthemakingofarepublicreel2.mov',
'track': 'irelandthemakingofarepublicreel2',
},
},
],
@@ -225,19 +231,29 @@ class ArchiveOrgIE(InfoExtractor):
'release_date': '19950402',
'timestamp': 1084927901,
},
}, {
# metadata['metadata']['description'] is a list of strings instead of str
'url': 'https://archive.org/details/pra-KZ1908.02',
'info_dict': {
'id': 'pra-KZ1908.02',
'ext': 'mp3',
'display_id': 'KZ1908.02_01.wav',
'title': 'Crips and Bloods speak about gang life',
'description': 'md5:2b56b35ff021311e3554b47a285e70b3',
'uploader': 'jake@archive.org',
'duration': 1733.74,
'track': 'KZ1908.02 01',
'track_number': 1,
'timestamp': 1336026026,
'upload_date': '20120503',
'release_year': 1992,
},
}]
@staticmethod
def _playlist_data(webpage):
element = re.findall(r'''(?xs)
<input
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s+class=['"]?js-play8-playlist['"]?
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s*/>
''', webpage)[0]
return json.loads(extract_attributes(element)['value'])
element = get_element_text_and_html_by_tag('play-av', webpage)[1]
return json.loads(extract_attributes(element)['playlist'])
def _real_extract(self, url):
video_id = urllib.parse.unquote_plus(self._match_id(url))
@@ -274,34 +290,40 @@ def _real_extract(self, url):
m = metadata['metadata']
identifier = m['identifier']
info = {
info = traverse_obj(m, {
'title': ('title', {str}),
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
'uploader': (('uploader', 'adder'), {str}, any),
'creators': ('creator', (None, ...), {str}, filter, all, filter),
'license': ('licenseurl', {url_or_none}),
'release_date': ('date', {unified_strdate}),
'timestamp': (('publicdate', 'addeddate'), {unified_timestamp}, any),
'location': ('venue', {str}),
'release_year': ('year', {int_or_none}),
})
info.update({
'id': identifier,
'title': m['title'],
'description': clean_html(m.get('description')),
'uploader': dict_get(m, ['uploader', 'adder']),
'creators': traverse_obj(m, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'license': m.get('licenseurl'),
'release_date': unified_strdate(m.get('date')),
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
'webpage_url': f'https://archive.org/details/{identifier}',
'location': m.get('venue'),
'release_year': int_or_none(m.get('year'))}
})
for f in metadata['files']:
if f['name'] in entries:
entries[f['name']] = merge_dicts(entries[f['name']], {
'id': identifier + '/' + f['name'],
'title': f.get('title') or f['name'],
'display_id': f['name'],
'description': clean_html(f.get('description')),
'creators': traverse_obj(f, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'duration': parse_duration(f.get('length')),
'track_number': int_or_none(f.get('track')),
'album': f.get('album'),
'discnumber': int_or_none(f.get('disc')),
'release_year': int_or_none(f.get('year'))})
**traverse_obj(f, {
'title': (('title', 'name'), {str}, any),
'display_id': ('name', {str}),
'description': ('description', ({str}, (..., all, {' '.join})), {clean_html}, filter, any),
'creators': ('creator', (None, ...), {str}, filter, all, filter),
'duration': ('length', {parse_duration}),
'track_number': ('track', {int_or_none}),
'album': ('album', {str}),
'discnumber': ('disc', {int_or_none}),
'release_year': ('year', {int_or_none}),
}),
})
entry = entries[f['name']]
elif traverse_obj(f, 'original', expected_type=str) in entries:
elif traverse_obj(f, ('original', {str})) in entries:
entry = entries[f['original']]
else:
continue

View File

@@ -62,6 +62,20 @@ class ArcPublishingIE(InfoExtractor):
'url': 'arcpublishing:tronc:460f2931-8130-4719-8ea1-ffcb2d7cb685',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.uppermichiganssource.com/2025/07/18/scattered-showers-storms-bring-heavy-rain-potential/',
'info_dict': {
'id': '508116f7-e999-48db-b7c2-60a04842679b',
'ext': 'mp4',
'title': 'Scattered showers & storms bring heavy rain potential',
'description': 'Scattered showers & storms bring heavy rain potential',
'duration': 2016,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1752881287,
'upload_date': '20250718',
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
}]
_POWA_DEFAULTS = [
(['cmg', 'prisa'], '%s-config-prod.api.cdn.arcpublishing.com/video'),
([

View File

@@ -51,8 +51,8 @@ class ArteTVIE(ArteTVBaseIE):
'id': '109067-000-A',
'ext': 'mp4',
'description': 'md5:d2ca367b8ecee028dddaa8bd1aebc739',
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1713927600,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/3rR6PLzfbigSkkeHtkCZNF/940x530',
'duration': 7599,
'title': 'La loi de Téhéran',
'upload_date': '20240424',
@@ -62,6 +62,7 @@ class ArteTVIE(ArteTVBaseIE):
'fr-forced': 'mincount:1',
},
},
'skip': 'Invalid URL',
}, {
'note': 'age-restricted',
'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
@@ -69,9 +70,9 @@ class ArteTVIE(ArteTVBaseIE):
'id': '006785-000-A',
'description': 'md5:c2f94fdfefc8a280e4dab68ab96ab0ba',
'title': 'The Element of Crime',
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1696111200,
'duration': 5849,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/q82dTTfyuCXupPsGxXsd7B/940x530',
'upload_date': '20230930',
'ext': 'mp4',
},
@@ -252,6 +253,30 @@ class ArteTVEmbedIE(InfoExtractor):
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://timesofmalta.com/article/watch-sunken-warships-north-sea-arte.1108358',
'info_dict': {
'id': '110288-000-A',
'ext': 'mp4',
'title': 'Danger on the Seabed',
'alt_title': 'Sunken Warships in the North Sea',
'description': 'md5:a2c84cbad37d280bddb6484087120add',
'duration': 3148,
'thumbnail': r're:https?://api-cdn\.arte\.tv/img/v2/image/.+',
'timestamp': 1741686820,
'upload_date': '20250311',
},
'params': {'skip_download': 'm3u8'},
}, {
# FIXME: Embed detection
'url': 'https://www.eurockeennes.fr/en-live/',
'info_dict': {
'id': 'en-live',
'title': 'Les Eurocks en live | Les Eurockéennes de Belfort 3-4-5-6 juillet 2025 sur la Presqu&#039;Île du Malsaucy',
},
'playlist_count': 4,
}]
def _real_extract(self, url):
qs = parse_qs(url)
@@ -304,9 +329,9 @@ class ArteTVCategoryIE(ArteTVBaseIE):
'info_dict': {
'id': 'politics-and-society',
'title': 'Politics and society',
'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
'description': 'Watch documentaries and reportage about politics, society and current affairs.',
},
'playlist_mincount': 13,
'playlist_mincount': 3,
}]
@classmethod

View File

@@ -1,33 +0,0 @@
from .brightcove import BrightcoveNewBaseIE
from ..utils import extract_attributes
class BandaiChannelIE(BrightcoveNewBaseIE):
IE_NAME = 'bandaichannel'
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
_TESTS = [{
'url': 'https://www.b-ch.com/titles/514/001',
'md5': 'a0f2d787baa5729bed71108257f613a4',
'info_dict': {
'id': '6128044564001',
'ext': 'mp4',
'title': 'メタルファイターMIKU 第1話',
'timestamp': 1580354056,
'uploader_id': '5797077852001',
'upload_date': '20200130',
'duration': 1387.733,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(self._search_regex(
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
bc = self._download_json(
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
return self._parse_brightcove_metadata(bc, bc['id'])

View File

@@ -7,6 +7,7 @@
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
clean_html,
extract_attributes,
float_or_none,
int_or_none,
@@ -19,7 +20,7 @@
url_or_none,
urljoin,
)
from ..utils.traversal import find_element, traverse_obj
from ..utils.traversal import find_element, find_elements, traverse_obj
class BandcampIE(InfoExtractor):
@@ -35,14 +36,12 @@ class BandcampIE(InfoExtractor):
'duration': 9.8485,
'uploader': 'youtube-dl "\'/\\ä↭',
'upload_date': '20121129',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1354224127,
'track': 'youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
'album_artist': 'youtube-dl "\'/\\ä↭',
'track_id': '1812978515',
'artist': 'youtube-dl "\'/\\ä↭',
'uploader_url': 'https://youtube-dl.bandcamp.com',
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
'artists': ['youtube-dl "\'/\\ä↭'],
'album_artists': ['youtube-dl "\'/\\ä↭'],
},
@@ -53,10 +52,9 @@ class BandcampIE(InfoExtractor):
'info_dict': {
'id': '2650410135',
'ext': 'm4a',
'acodec': r're:[fa]lac',
'title': 'Ben Prunty - Lanius (Battle)',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ben Prunty',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1396508491,
'upload_date': '20140403',
'release_timestamp': 1396483200,
@@ -65,11 +63,12 @@ class BandcampIE(InfoExtractor):
'track': 'Lanius (Battle)',
'track_number': 1,
'track_id': '2650410135',
'artist': 'Ben Prunty',
'album_artist': 'Ben Prunty',
'album': 'FTL: Advanced Edition Soundtrack',
'uploader_url': 'https://benprunty.bandcamp.com',
'uploader_id': 'benprunty',
'tags': ['soundtrack', 'chiptunes', 'cinematic', 'electronic', 'video game music', 'California'],
'artists': ['Ben Prunty'],
'album_artists': ['Ben Prunty'],
},
}, {
# no free download, mp3 128
@@ -79,8 +78,8 @@ class BandcampIE(InfoExtractor):
'id': '2584466013',
'ext': 'mp3',
'title': 'Mastodon - Hail to Fire',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mastodon',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1322005399,
'upload_date': '20111122',
'release_timestamp': 1076112000,
@@ -89,11 +88,12 @@ class BandcampIE(InfoExtractor):
'track': 'Hail to Fire',
'track_number': 5,
'track_id': '2584466013',
'artist': 'Mastodon',
'album_artist': 'Mastodon',
'album': 'Call of the Mastodon',
'uploader_url': 'https://relapsealumni.bandcamp.com',
'uploader_id': 'relapsealumni',
'tags': ['Philadelphia'],
'artists': ['Mastodon'],
'album_artists': ['Mastodon'],
},
}, {
# track from compilation album (artist/album_artist difference)
@@ -103,8 +103,8 @@ class BandcampIE(InfoExtractor):
'id': '1978174799',
'ext': 'mp3',
'title': 'submerse - submerse - Safehouse',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'submerse',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1480779297,
'upload_date': '20161203',
'release_timestamp': 1481068800,
@@ -113,11 +113,36 @@ class BandcampIE(InfoExtractor):
'track': 'submerse - Safehouse',
'track_number': 3,
'track_id': '1978174799',
'artist': 'submerse',
'album_artist': 'Diskotopia',
'album': 'DSK F/W 2016-2017 Free Compilation',
'uploader_url': 'https://diskotopia.bandcamp.com',
'uploader_id': 'diskotopia',
'tags': ['Japan'],
'artists': ['submerse'],
'album_artists': ['Diskotopia'],
},
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.punknews.org/article/85809/stay-inside-super-sonic',
'info_dict': {
'id': '2475540375',
'ext': 'mp3',
'title': 'Stay Inside - Super Sonic',
'album': 'Lunger',
'album_artists': ['Stay Inside'],
'artists': ['Stay Inside'],
'duration': 166.157,
'release_date': '20251003',
'release_timestamp': 1759449600.0,
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1749473029.0,
'track': 'Super Sonic',
'track_id': '2475540375',
'track_number': 3,
'upload_date': '20250609',
'uploader': 'Stay Inside',
'uploader_id': 'stayinside',
'uploader_url': 'https://stayinside.bandcamp.com',
},
}]
@@ -252,6 +277,7 @@ def _real_extract(self, url):
'album': embed.get('album_title'),
'album_artist': album_artist,
'formats': formats,
'tags': traverse_obj(webpage, ({find_elements(cls='tag')}, ..., {clean_html})),
}
@@ -268,10 +294,10 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'id': '1353101989',
'ext': 'mp3',
'title': 'Blazo - Intro',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'album_artists': ['Blazo'],
'uploader_url': 'https://blazo.bandcamp.com',
'release_date': '20110727',
@@ -291,6 +317,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'id': '38097443',
'ext': 'mp3',
'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
'thumbnail': r're:https?://f4\.bcbits\.com/img/.+\.jpg',
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
@@ -304,7 +331,6 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'uploader_id': 'blazo',
'album_artists': ['Blazo'],
'artists': ['Blazo'],
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'release_timestamp': 1311724800.0,
},
},

View File

@@ -1,91 +0,0 @@
from .common import InfoExtractor
class BellMediaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?P<domain>
(?:
ctv|
tsn|
bnn(?:bloomberg)?|
thecomedynetwork|
discovery|
discoveryvelocity|
sciencechannel|
investigationdiscovery|
animalplanet|
bravo|
mtv|
space|
etalk|
marilyn
)\.ca|
(?:much|cp24)\.com
)/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
'md5': '3e5b8e38370741d5089da79161646635',
'info_dict': {
'id': '1403070',
'ext': 'flv',
'title': 'David Cockfield\'s Top Picks',
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
'upload_date': '20180525',
'timestamp': 1527288600,
'season_id': '73997',
'season': '2018',
'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg',
'tags': [],
'categories': ['ETFs'],
'season_number': 8,
'duration': 272.038,
'series': 'Market Call Tonight',
},
}, {
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
'only_matching': True,
}, {
'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
'only_matching': True,
}, {
'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
'only_matching': True,
}, {
'url': 'http://www.etalk.ca/video?videoid=663455',
'only_matching': True,
}, {
'url': 'https://www.cp24.com/video?clipId=1982548',
'only_matching': True,
}]
_DOMAINS = {
'thecomedynetwork': 'comedy',
'discoveryvelocity': 'discvel',
'sciencechannel': 'discsci',
'investigationdiscovery': 'invdisc',
'animalplanet': 'aniplan',
'etalk': 'ctv',
'bnnbloomberg': 'bnn',
'marilyn': 'ctv_marilyn',
}
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
domain = domain.split('.')[0]
return {
'_type': 'url_transparent',
'id': video_id,
'url': f'9c9media:{self._DOMAINS.get(domain, domain)}_web:{video_id}',
'ie_key': 'NineCNineMedia',
}

View File

@@ -353,7 +353,7 @@ class BiliBiliIE(BilibiliBaseIE):
'id': 'BV1bK411W797',
'title': '物语中的人物是如何吐槽自己的OP的',
},
'playlist_count': 18,
'playlist_count': 23,
'playlist': [{
'info_dict': {
'id': 'BV1bK411W797_p1',
@@ -373,6 +373,7 @@ class BiliBiliIE(BilibiliBaseIE):
'_old_archive_ids': ['bilibili 498159642_part1'],
},
}],
'params': {'playlist_items': '2'},
}, {
'note': 'Specific page of Anthology',
'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1',
@@ -816,6 +817,26 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'upload_date': '20111104',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'new playurlSSRData scheme',
'url': 'https://www.bilibili.com/bangumi/play/ep678060',
'info_dict': {
'id': '678060',
'ext': 'mp4',
'series': '去你家吃饭好吗',
'series_id': '6198',
'season': '第二季',
'season_id': '42542',
'season_number': 2,
'episode': '吴老二:你家大公鸡养不熟,能煮熟吗…',
'episode_id': '678060',
'episode_number': 61,
'title': '一只小九九丫 吴老二:你家大公鸡养不熟,能煮熟吗…',
'duration': 266.123,
'timestamp': 1663315904,
'upload_date': '20220916',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'url': 'https://www.bilibili.com/bangumi/play/ep267851',
'info_dict': {
@@ -879,12 +900,41 @@ def _real_extract(self, url):
'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id},
headers=headers))
premium_only = play_info.get('code') == -10403
play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
# play_info can be structured in at least three different ways, e.g.:
# 1.) play_info['result']['video_info'] and play_info['code']
# 2.) play_info['raw']['data']['video_info'] and play_info['code']
# 3.) play_info['data']['result']['video_info'] and play_info['data']['code']
# So we need to transform any of the above into a common structure
status_code = play_info.get('code')
if 'raw' in play_info:
play_info = play_info['raw']
if 'data' in play_info:
play_info = play_info['data']
if status_code is None:
status_code = play_info.get('code')
if 'result' in play_info:
play_info = play_info['result']
formats = self.extract_formats(play_info)
if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage):
self.raise_login_required('This video is for premium members only')
geo_blocked = traverse_obj(play_info, (
'plugins', lambda _, v: v['name'] == 'AreaLimitPanel', 'config', 'is_block', {bool}, any))
premium_only = status_code == -10403
video_info = traverse_obj(play_info, ('video_info', {dict})) or {}
formats = self.extract_formats(video_info)
if not formats:
if geo_blocked:
self.raise_geo_restricted()
elif premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage:
self.raise_login_required('This video is for premium members only')
if traverse_obj(play_info, ((
('play_check', 'play_detail'), # 'PLAY_PREVIEW' vs 'PLAY_WHOLE' vs 'PLAY_NONE'
'play_video_type', # 'preview' vs 'whole' vs 'none'
), any, {lambda x: x in ('PLAY_PREVIEW', 'preview')})):
self.report_warning(
'Only preview format is available, '
f'you have to become a premium member to access full video. {self._login_hint()}')
bangumi_info = self._download_json(
'https://api.bilibili.com/pgc/view/web/season', episode_id, 'Get episode details',
@@ -922,7 +972,7 @@ def _real_extract(self, url):
'season': str_or_none(season_title),
'season_id': str_or_none(season_id),
'season_number': season_number,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'duration': float_or_none(video_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': {'Referer': url},
@@ -966,6 +1016,7 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
'params': {'playlist_items': '2'},
}]
def _real_extract(self, url):
@@ -1021,6 +1072,7 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
'params': {'playlist_items': '2'},
}]
def _real_extract(self, url):
@@ -1192,6 +1244,26 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
'id': '313580179',
},
'playlist_mincount': 92,
}, {
# Hidden-mode collection
'url': 'https://space.bilibili.com/3669403/video',
'info_dict': {
'id': '3669403',
},
'playlist': [{
'info_dict': {
'_type': 'playlist',
'id': '3669403_3958082',
'title': '合集·直播回放',
'description': '',
'uploader': '月路Yuel',
'uploader_id': '3669403',
'timestamp': int,
'upload_date': str,
'thumbnail': str,
},
}],
'params': {'playlist_items': '7'},
}]
def _real_extract(self, url):
@@ -1248,8 +1320,14 @@ def get_metadata(page_data):
}
def get_entries(page_data):
for entry in traverse_obj(page_data, ('list', 'vlist')) or []:
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
for entry in traverse_obj(page_data, ('list', 'vlist', ..., {dict})):
if traverse_obj(entry, ('meta', 'attribute')) == 156:
# hidden-mode collection doesn't show its videos in uploads; extract as playlist instead
yield self.url_result(
f'https://space.bilibili.com/{entry["mid"]}/lists/{entry["meta"]["id"]}?type=season',
BilibiliCollectionListIE, f'{entry["mid"]}_{entry["meta"]["id"]}')
else:
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
return self.playlist_result(paged_list, playlist_id)
@@ -1785,7 +1863,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
'thumbnail': r're:^https?://.+\.jpg',
'timestamp': 1564836614,
'upload_date': '20190803',
'uploader': 'tsukimi-つきみぐ',
'uploader': '十六夜tsukimiつきみぐ',
'view_count': int,
},
}
@@ -1840,10 +1918,10 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
'url': 'https://www.bilibili.com/audio/am10624',
'info_dict': {
'id': '10624',
'title': '每日新曲推荐每日11:00更新',
'title': '新曲推荐',
'description': '每天11:00更新为你推送最新音乐',
},
'playlist_count': 19,
'playlist_count': 16,
}
def _real_extract(self, url):

View File

@@ -1,16 +1,27 @@
from .common import InfoExtractor
from ..utils import parse_iso8601
from ..utils import (
UnsupportedError,
float_or_none,
int_or_none,
join_nonempty,
jwt_decode_hs256,
mimetype2ext,
parse_iso8601,
parse_qs,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BlackboardCollaborateIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?P<region>[a-z-]+)\.bbcollab\.com/
(?P<region>[a-z]+)(?:-lti)?\.bbcollab\.com/
(?:
collab/ui/session/playback/load|
recording
)/
(?P<id>[^/]+)'''
(?P<id>[^/?#]+)'''
_TESTS = [
{
'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
@@ -19,9 +30,55 @@ class BlackboardCollaborateIE(InfoExtractor):
'id': '0a633b6a88824deb8c918f470b22b256',
'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
'ext': 'mp4',
'duration': 1896000,
'timestamp': 1620331399,
'duration': 1896,
'timestamp': 1620333295,
'upload_date': '20210506',
'subtitles': {
'live_chat': 'mincount:1',
},
},
},
{
'url': 'https://eu.bbcollab.com/collab/ui/session/playback/load/4bde2dee104f40289a10f8e554270600',
'md5': '108db6a8f83dcb0c2a07793649581865',
'info_dict': {
'id': '4bde2dee104f40289a10f8e554270600',
'title': 'Meeting - Azerbaycanca erize formasi',
'ext': 'mp4',
'duration': 880,
'timestamp': 1671176868,
'upload_date': '20221216',
},
},
{
'url': 'https://eu.bbcollab.com/recording/f83be390ecff46c0bf7dccb9dddcf5f6',
'md5': 'e3b0b88ddf7847eae4b4c0e2d40b83a5',
'info_dict': {
'id': 'f83be390ecff46c0bf7dccb9dddcf5f6',
'title': 'Keynote lecture by Laura Carvalho - recording_1',
'ext': 'mp4',
'duration': 5506,
'timestamp': 1662721705,
'upload_date': '20220909',
'subtitles': {
'live_chat': 'mincount:1',
},
},
},
{
'url': 'https://eu.bbcollab.com/recording/c3e1e7c9e83d4cd9981c93c74888d496',
'md5': 'fdb2d8c43d66fbc0b0b74ef5e604eb1f',
'info_dict': {
'id': 'c3e1e7c9e83d4cd9981c93c74888d496',
'title': 'International Ally User Group - recording_18',
'ext': 'mp4',
'duration': 3479,
'timestamp': 1721919621,
'upload_date': '20240725',
'subtitles': {
'en': 'mincount:1',
'live_chat': 'mincount:1',
},
},
},
{
@@ -42,22 +99,81 @@ class BlackboardCollaborateIE(InfoExtractor):
},
]
def _call_api(self, region, video_id, path=None, token=None, note=None, fatal=False):
# Ref: https://github.com/blackboard/BBDN-Collab-Postman-REST
return self._download_json(
join_nonempty(f'https://{region}.bbcollab.com/collab/api/csa/recordings', video_id, path, delim='/'),
video_id, note or 'Downloading JSON metadata', fatal=fatal,
headers={'Authorization': f'Bearer {token}'} if token else None)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
region = mobj.group('region')
video_id = mobj.group('id')
info = self._download_json(
f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
duration = info.get('duration')
title = info['name']
upload_date = info.get('created')
streams = info['streams']
formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
token = parse_qs(url).get('authToken', [None])[-1]
video_info = self._call_api(region, video_id, path='data/secure', token=token, note='Trying auth token')
if video_info:
video_extra = self._call_api(region, video_id, token=token, note='Retrieving extra attributes')
else:
video_info = self._call_api(region, video_id, path='data', note='Trying fallback', fatal=True)
video_extra = {}
formats = traverse_obj(video_info, ('extStreams', lambda _, v: url_or_none(v['streamUrl']), {
'url': 'streamUrl',
'ext': ('contentType', {mimetype2ext}),
'aspect_ratio': ('aspectRatio', {float_or_none}),
}))
if filesize := traverse_obj(video_extra, ('storageSize', {int_or_none})):
for fmt in formats:
fmt['filesize'] = filesize
subtitles = {}
for subs in traverse_obj(video_info, ('subtitles', lambda _, v: url_or_none(v['url']))):
subtitles.setdefault(subs.get('lang') or 'und', []).append({
'name': traverse_obj(subs, ('label', {str})),
'url': subs['url'],
})
for live_chat_url in traverse_obj(video_info, ('chats', ..., 'url', {url_or_none})):
subtitles.setdefault('live_chat', []).append({'url': live_chat_url})
return {
'duration': duration,
**traverse_obj(video_info, {
'title': ('name', {str}),
'timestamp': ('created', {parse_iso8601}),
'duration': ('duration', {int_or_none(scale=1000)}),
}),
'formats': formats,
'id': video_id,
'timestamp': parse_iso8601(upload_date),
'title': title,
'subtitles': subtitles,
}
class BlackboardCollaborateLaunchIE(InfoExtractor):
_VALID_URL = r'https?://[a-z]+\.bbcollab\.com/launch/(?P<id>[^/?#]+)'
_TESTS = [
{
'url': 'https://au.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.xuELw4EafEwUMoYcCHidGn4Tw9O1QCbYHzYGJUl0kKk',
'only_matching': True,
},
{
'url': 'https://us.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.yOhRZNaIjXYoMYMpcTzgjZJCnIFaYf2cAzbco8OAxlY',
'only_matching': True,
},
{
'url': 'https://eu.bbcollab.com/launch/eyJhbGciOiJIUzI1NiJ9.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.Xj4ymojYLwZ1vKPKZ-KxjpqQvFXoJekjRaG0npngwWs',
'only_matching': True,
},
]
def _real_extract(self, url):
token = self._match_id(url)
video_id = jwt_decode_hs256(token)['resourceAccessTicket']['resourceId']
redirect_url = self._request_webpage(url, video_id).url
if self.suitable(redirect_url):
raise UnsupportedError(redirect_url)
return self.url_result(redirect_url, BlackboardCollaborateIE, video_id)

View File

@@ -19,8 +19,19 @@ class BloggerIE(InfoExtractor):
'id': 'BLOGGER-video-3c740e3a49197e16-796',
'title': 'BLOGGER-video-3c740e3a49197e16-796',
'ext': 'mp4',
'thumbnail': r're:^https?://.*',
'duration': 76.068,
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://blog.tomeuvizoso.net/2019/01/a-panfrost-milestone.html',
'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
'info_dict': {
'id': 'BLOGGER-video-3c740e3a49197e16-12203',
'ext': 'mp4',
'title': 'BLOGGER-video-3c740e3a49197e16-12203',
'duration': 76.068,
'thumbnail': r're:https?://i9\.ytimg\.com/vi_blogger/.+',
},
}]

View File

@@ -1,188 +0,0 @@
from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import (
extract_attributes,
float_or_none,
get_element_html_by_class,
int_or_none,
merge_dicts,
parse_age_limit,
remove_end,
str_or_none,
traverse_obj,
unescapeHTML,
unified_timestamp,
update_url_query,
url_or_none,
)
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'info_dict': {
'id': '3923059',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'description': 'Find out who takes the title of Top Chef!',
'upload_date': '20190314',
'timestamp': 1552591860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'The Top Chef Season 16 Winner Is...',
'duration': 190.357,
'season': 'Season 16',
'thumbnail': r're:^https://.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
'info_dict': {
'id': '9000234570',
'ext': 'mp4',
'title': 'London Calling',
'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
'upload_date': '20230310',
'timestamp': 1678410000,
'season_number': 20,
'episode_number': 1,
'series': 'Top Chef',
'episode': 'London Calling',
'duration': 3266.03,
'season': 'Season 20',
'chapters': 'count:7',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
'info_dict': {
'id': '3692045',
'ext': 'mp4',
'title': 'Closing Night',
'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
'upload_date': '20180401',
'timestamp': 1522623600,
'season_number': 1,
'episode_number': 1,
'series': 'In Ice Cold Blood',
'episode': 'Closing Night',
'duration': 2629.051,
'season': 'Season 1',
'chapters': 'count:6',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'info_dict': {
'id': '3974019',
'ext': 'mp4',
'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
'upload_date': '20190617',
'timestamp': 1560790800,
'season_number': 2,
'episode_number': 16,
'series': 'In Ice Cold Blood',
'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'duration': 68.235,
'season': 'Season 2',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
settings = self._search_json(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
query = {
'manifest': 'm3u',
'formats': 'm3u,mpeg4',
}
if tve:
account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
account_id = tve['data-mpx-media-account-id']
metadata = self._parse_json(
tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
video_id = tve.get('data-guid') or metadata['guid']
if tve.get('data-entitlement') == 'auth':
auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
site = remove_end(site, 'tv')
release_pid = tve['data-release-pid']
resource = self._get_mvpd_resource(
tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
tve['data-title'], release_pid, tve.get('data-rating'))
query.update({
'switch': 'HLSServiceSecure',
'auth': self._extract_mvpd_auth(
url, release_pid, auth.get('adobePassRequestorId') or site, resource),
})
else:
ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
account_id = ls_playlist['mpxMediaAccountId']
video_id = ls_playlist['defaultGuid']
metadata = traverse_obj(
ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
}))
# prune pointless single chapters that span the entire duration from short videos
if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
chapters = None
m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
**merge_dicts(traverse_obj(tp_metadata, {
'title': 'title',
'description': 'description',
'duration': ('duration', {float_or_none(scale=1000)}),
'timestamp': ('pubDate', {float_or_none(scale=1000)}),
'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
}, get_all=False), traverse_obj(metadata, {
'title': 'title',
'description': 'description',
'duration': ('durationInSeconds', {int_or_none}),
'timestamp': ('airDate', {unified_timestamp}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode': 'episodeTitle',
'series': 'show',
})),
}

View File

@@ -495,8 +495,6 @@ def _real_extract(self, url):
class BrightcoveNewBaseIE(AdobePassIE):
def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
title = json_data['name'].strip()
formats, subtitles = [], {}
sources = json_data.get('sources') or []
for source in sources:
@@ -600,16 +598,18 @@ def build_format_id(kind):
return {
'id': video_id,
'title': title,
'description': clean_html(json_data.get('description')),
'thumbnails': thumbnails,
'duration': duration,
'timestamp': parse_iso8601(json_data.get('published_at')),
'uploader_id': json_data.get('account_id'),
'formats': formats,
'subtitles': subtitles,
'tags': json_data.get('tags', []),
'is_live': is_live,
**traverse_obj(json_data, {
'title': ('name', {clean_html}),
'description': ('description', {clean_html}),
'tags': ('tags', ..., {str}, filter, all, filter),
'timestamp': ('published_at', {parse_iso8601}),
'uploader_id': ('account_id', {str}),
}),
}
@@ -645,10 +645,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'uploader_id': '4036320279001',
'formats': 'mincount:39',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
@@ -709,7 +706,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD_01-032_5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1646078943,
'uploader_id': '1569565978001',
'upload_date': '20220228',
@@ -721,7 +717,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD 01-087 (Airs 05.25.22)_Segment 5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1651604591,
'uploader_id': '1569565978001',
'upload_date': '20220503',
@@ -923,10 +918,18 @@ def extract_policy_key():
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
missing_fields = ', '.join(
key for key in ('source_url', 'software_statement') if not smuggled_data.get(key))
if missing_fields:
raise ExtractorError(
f'Missing fields in smuggled data: {missing_fields}. '
f'This video can be only extracted from the webpage where it is embedded. '
f'Pass the URL of the embedding webpage instead of the Brightcove URL', expected=True)
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
custom_fields['bcadobepassresourceid'],
smuggled_data['software_statement'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': f'application/json;pk={policy_key}',

View File

@@ -0,0 +1,73 @@
from .common import InfoExtractor
from ..utils import (
bug_reports_message,
clean_html,
get_element_by_class,
js_to_json,
mimetype2ext,
strip_or_none,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class BTVPlusIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?btvplus\.bg/produkt/(?:predavaniya|seriali|novini)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://btvplus.bg/produkt/predavaniya/67271/btv-reporterite/btv-reporterite-12-07-2025-g',
'info_dict': {
'ext': 'mp4',
'id': '67271',
'title': 'bTV Репортерите - 12.07.2025 г.',
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jul2025/2113606319.jpg',
},
}, {
'url': 'https://btvplus.bg/produkt/seriali/66942/sezon-2/plen-sezon-2-epizod-55',
'info_dict': {
'ext': 'mp4',
'id': '66942',
'title': 'Плен - сезон 2, епизод 55',
'thumbnail': 'https://cdn.btv.bg/media/images/940x529/Jun2025/2113595104.jpg',
},
}, {
'url': 'https://btvplus.bg/produkt/novini/67270/btv-novinite-centralna-emisija-12-07-2025',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'var\s+videoUrl\s*=\s*[\'"]([^\'"]+)[\'"]',
webpage, 'player URL')
player_config = self._download_json(
urljoin('https://btvplus.bg', player_url), video_id)['config']
videojs_data = self._search_json(
r'videojs\(["\'][^"\']+["\'],', player_config, 'videojs data',
video_id, transform_source=js_to_json)
formats = []
subtitles = {}
for src in traverse_obj(videojs_data, ('sources', lambda _, v: url_or_none(v['src']))):
ext = mimetype2ext(src.get('type'))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
self.report_warning(f'Unknown format type {ext}{bug_reports_message()}')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'title': (
strip_or_none(self._og_search_title(webpage, default=None))
or clean_html(get_element_by_class('product-title', webpage))),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
}

View File

@@ -19,18 +19,16 @@ class CloudflareStreamIE(InfoExtractor):
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': 'm3u8',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://watch.cloudflarestream.com/embed/sdk-iframe-integration.fla9.latest.js?video=0e8e040aec776862e1d632a699edf59e',
'info_dict': {
'id': '0e8e040aec776862e1d632a699edf59e',
'ext': 'mp4',
'title': '0e8e040aec776862e1d632a699edf59e',
'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -54,11 +52,21 @@ class CloudflareStreamIE(InfoExtractor):
'id': 'eaef9dea5159cf968be84241b5cedfe7',
'ext': 'mp4',
'title': 'eaef9dea5159cf968be84241b5cedfe7',
'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
'params': {
'extractor_args': {'generic': {'impersonate': ['chrome']}},
'skip_download': 'm3u8',
},
}, {
# FIXME: Embed detection
'url': 'https://www.cloudflare.com/developer-platform/products/cloudflare-stream/',
'info_dict': {
'id': 'e7bd2dd67e0f8860b4ae81e33a966049',
'ext': 'mp4',
'title': 'e7bd2dd67e0f8860b4ae81e33a966049',
'thumbnail': r're:https?://cloudflarestream\.com/.+\.jpg',
},
}]
def _real_extract(self, url):

View File

@@ -11,7 +11,7 @@
class CloudyCDNIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//embed\.cloudycdn\.services/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_VALID_URL = r'(?:https?:)?//embed\.(?P<domain>cloudycdn\.services|backscreen\.com)/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://embed.cloudycdn.services/ltv/media/46k_d23-6000-105?',
@@ -23,7 +23,7 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
},
}, {
'url': 'https://embed.cloudycdn.services/izm/media/26e_lv-8-5-1',
@@ -33,7 +33,7 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'title': 'LV-8-5-1',
'timestamp': 1669767167,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'duration': 1205,
'upload_date': '20221130',
},
@@ -48,9 +48,21 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1673,
'title': 'D24-6000-074-cetstud',
'timestamp': 1718902233,
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
},
'params': {'format': 'bv'},
}, {
'url': 'https://embed.backscreen.com/ltv/media/32j_z25-0600-127?',
'md5': '9b6fa09ac1a4de53d4f42b94affc3b42',
'info_dict': {
'id': '32j_z25-0600-127',
'ext': 'mp4',
'title': 'Z25-0600-127-DZ',
'duration': 1906,
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/977427/placeholder1746633646.jpg',
'timestamp': 1746632402,
'upload_date': '20250507',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.tavaklase.lv/video/es-esmu-mina-um-2/',
@@ -60,17 +72,17 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'upload_date': '20230223',
'duration': 629,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'timestamp': 1677181513,
'title': 'LIB-2',
},
}]
def _real_extract(self, url):
site_id, video_id = self._match_valid_url(url).group('site_id', 'id')
domain, site_id, video_id = self._match_valid_url(url).group('domain', 'site_id', 'id')
data = self._download_json(
f'https://player.cloudycdn.services/player/{site_id}/media/{video_id}/',
f'https://player.{domain}/player/{site_id}/media/{video_id}/',
video_id, data=urlencode_postdata({
'version': '6.4.0',
'referer': url,

View File

@@ -1,5 +1,6 @@
import base64
import collections
import contextlib
import functools
import getpass
import http.client
@@ -37,7 +38,6 @@
TransportError,
network_exceptions,
)
from ..networking.impersonate import ImpersonateTarget
from ..utils import (
IDENTITY,
JSON_LD_RE,
@@ -101,6 +101,7 @@
xpath_with_ns,
)
from ..utils._utils import _request_dump_filename
from ..utils.jslib import devalue
class InfoExtractor:
@@ -242,7 +243,7 @@ class InfoExtractor:
* extra_param_to_segment_url A query string to append to each
fragment's URL, or to update each existing query string
with. If it is an HLS stream with an AES-128 decryption key,
the query paramaters will be passed to the key URI as well,
the query parameters will be passed to the key URI as well,
unless there is an `extra_param_to_key_url` given,
or unless an external key URI is provided via `hls_aes`.
Only applied by the native HLS/DASH downloaders.
@@ -257,11 +258,19 @@ class InfoExtractor:
* key The key (as hex) used to decrypt fragments.
If `key` is given, any key URI will be ignored
* iv The IV (as hex) used to decrypt fragments
* impersonate Impersonate target(s). Can be any of the following entities:
* an instance of yt_dlp.networking.impersonate.ImpersonateTarget
* a string in the format of CLIENT[:OS]
* a list or a tuple of CLIENT[:OS] strings or ImpersonateTarget instances
* a boolean value; True means any impersonate target is sufficient
* downloader_options A dictionary of downloader options
(For internal use only)
* http_chunk_size Chunk size for HTTP downloads
* ffmpeg_args Extra arguments for ffmpeg downloader (input)
* ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
* ws (NiconicoLiveFD only) WebSocketResponse
* ws_url (NiconicoLiveFD only) Websockets URL
* max_quality (NiconicoLiveFD only) Max stream quality string
* is_dash_periods Whether the format is a result of merging
multiple DASH periods.
RTMP formats can also have the additional fields: page_url,
@@ -331,6 +340,7 @@ class InfoExtractor:
* "name": Name or description of the subtitles
* "http_headers": A dictionary of additional HTTP headers
to add to the request.
* "impersonate": Impersonate target(s); same as the "formats" field
"ext" will be calculated from URL if missing
automatic_captions: Like 'subtitles'; contains automatically generated
captions instead of normal subtitles
@@ -387,6 +397,8 @@ class InfoExtractor:
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
(optional: core code can determine this value from
the next chapter's start_time or the video's duration)
* "title" (optional, string)
heatmap: A list of dictionaries, with the following entries:
* "start_time" - The start time of the data point in seconds
@@ -401,12 +413,13 @@ class InfoExtractor:
'unlisted' or 'public'. Use 'InfoExtractor._availability'
to set it
media_type: The type of media as classified by the site, e.g. "episode", "clip", "trailer"
_old_archive_ids: A list of old archive ids needed for backward compatibility
_old_archive_ids: A list of old archive ids needed for backward
compatibility. Use yt_dlp.utils.make_archive_id to generate ids
_format_sort_fields: A list of fields to use for sorting formats
__post_extractor: A function to be called just before the metadata is
written to either disk, logger or console. The function
must return a dict which will be added to the info_dict.
This is usefull for additional information that is
This is useful for additional information that is
time-consuming to extract. Note that the fields thus
extracted will not be available to output template and
match_filter. So, only "comments" and "comment_count" are
@@ -879,26 +892,17 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa
extensions = {}
if impersonate in (True, ''):
impersonate = ImpersonateTarget()
requested_targets = [
t if isinstance(t, ImpersonateTarget) else ImpersonateTarget.from_str(t)
for t in variadic(impersonate)
] if impersonate else []
available_target = next(filter(self._downloader._impersonate_target_available, requested_targets), None)
available_target, requested_targets = self._downloader._parse_impersonate_targets(impersonate)
if available_target:
extensions['impersonate'] = available_target
elif requested_targets:
message = 'The extractor is attempting impersonation, but '
message += (
'no impersonate target is available' if not str(impersonate)
else f'none of these impersonate targets are available: "{", ".join(map(str, requested_targets))}"')
info_msg = ('see https://github.com/yt-dlp/yt-dlp#impersonation '
'for information on installing the required dependencies')
msg = 'The extractor is attempting impersonation'
if require_impersonation:
raise ExtractorError(f'{message}; {info_msg}', expected=True)
self.report_warning(f'{message}; if you encounter errors, then {info_msg}', only_once=True)
raise ExtractorError(
self._downloader._unavailable_targets_message(requested_targets, note=msg, is_error=True),
expected=True)
self.report_warning(
self._downloader._unavailable_targets_message(requested_targets, note=msg), only_once=True)
try:
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query, extensions))
@@ -1675,9 +1679,9 @@ def extract_video_object(e):
'ext': mimetype2ext(e.get('encodingFormat')),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnails': [{'url': unescapeHTML(url)}
for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL'))
if url_or_none(url)],
'thumbnails': traverse_obj(e, (('thumbnailUrl', 'thumbnailURL', 'thumbnail_url'), (None, ...), {
'url': ({str}, {unescapeHTML}, {self._proto_relative_url}, {url_or_none}),
})),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
# author can be an instance of 'Organization' or 'Person' types.
@@ -1778,6 +1782,59 @@ def _search_nextjs_data(self, webpage, video_id, *, fatal=True, default=NO_DEFAU
r'<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>', webpage, 'next.js data',
video_id, end_pattern='</script>', fatal=fatal, default=default, **kw)
def _search_nextjs_v13_data(self, webpage, video_id, fatal=True):
"""Parses Next.js app router flight data that was introduced in Next.js v13"""
nextjs_data = {}
if not fatal and not isinstance(webpage, str):
return nextjs_data
def flatten(flight_data):
if not isinstance(flight_data, list):
return
if len(flight_data) == 4 and flight_data[0] == '$':
_, name, _, data = flight_data
if not isinstance(data, dict):
return
children = data.pop('children', None)
if data and isinstance(name, str) and re.fullmatch(r'\$L[0-9a-f]+', name):
# It is useful hydration JSON data
nextjs_data[name[2:]] = data
flatten(children)
return
for f in flight_data:
flatten(f)
flight_text = ''
# The pattern for the surrounding JS/tag should be strict as it's a hardcoded string in the next.js source
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L189
for flight_segment in re.findall(r'<script\b[^>]*>self\.__next_f\.push\((\[.+?\])\)</script>', webpage):
segment = self._parse_json(flight_segment, video_id, fatal=fatal, errnote=None if fatal else False)
# Some earlier versions of next.js "optimized" away this array structure; this is unsupported
# Ref: https://github.com/vercel/next.js/commit/0123a9d5c9a9a77a86f135b7ae30b46ca986d761
if not isinstance(segment, list) or len(segment) != 2:
self.write_debug(
f'{video_id}: Unsupported next.js flight data structure detected', only_once=True)
continue
# Only use the relevant payload type (1 == data)
# Ref: https://github.com/vercel/next.js/blob/5a4a08fdc/packages/next/src/server/app-render/use-flight-response.tsx#L11-L14
payload_type, chunk = segment
if payload_type == 1:
flight_text += chunk
for f in flight_text.splitlines():
prefix, _, body = f.lstrip().partition(':')
if not re.fullmatch(r'[0-9a-f]+', prefix):
continue
# The body still isn't guaranteed to be valid JSON, so parsing should always be non-fatal
if body.startswith('[') and body.endswith(']'):
flatten(self._parse_json(body, video_id, fatal=False, errnote=False))
elif body.startswith('{') and body.endswith('}'):
data = self._parse_json(body, video_id, fatal=False, errnote=False)
if data is not None:
nextjs_data[prefix] = data
return nextjs_data
def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal=True, traverse=('data', 0)):
"""Parses Nuxt.js metadata. This works as long as the function __NUXT__ invokes is a pure function"""
rectx = re.escape(context_name)
@@ -1795,6 +1852,63 @@ def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal
ret = self._parse_json(js, video_id, transform_source=functools.partial(js_to_json, vars=args), fatal=fatal)
return traverse_obj(ret, traverse) or {}
def _resolve_nuxt_array(self, array, video_id, *, fatal=True, default=NO_DEFAULT):
"""Resolves Nuxt rich JSON payload arrays"""
# Ref: https://github.com/nuxt/nuxt/commit/9e503be0f2a24f4df72a3ccab2db4d3e63511f57
# https://github.com/nuxt/nuxt/pull/19205
if default is not NO_DEFAULT:
fatal = False
if not isinstance(array, list) or not array:
error_msg = 'Unable to resolve Nuxt JSON data: invalid input'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id)
return {} if default is NO_DEFAULT else default
def indirect_reviver(data):
return data
def json_reviver(data):
return json.loads(data)
gen = devalue.parse_iter(array, revivers={
'NuxtError': indirect_reviver,
'EmptyShallowRef': json_reviver,
'EmptyRef': json_reviver,
'ShallowRef': indirect_reviver,
'ShallowReactive': indirect_reviver,
'Ref': indirect_reviver,
'Reactive': indirect_reviver,
})
while True:
try:
error_msg = f'Error resolving Nuxt JSON: {gen.send(None)}'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id, only_once=True)
else:
self.write_debug(f'{video_id}: {error_msg}', only_once=True)
except StopIteration as error:
return error.value or ({} if default is NO_DEFAULT else default)
def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT):
"""Parses metadata from Nuxt rich JSON payloads embedded in HTML"""
passed_default = default is not NO_DEFAULT
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage,
'Nuxt JSON data', video_id, contains_pattern=r'\[(?s:.+)\]',
fatal=fatal, default=NO_DEFAULT if not passed_default else None)
if not array:
return default if passed_default else {}
return self._resolve_nuxt_array(array, video_id, fatal=fatal, default=default)
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
@@ -2068,21 +2182,33 @@ def _extract_m3u8_formats_and_subtitles(
raise ExtractorError(errnote, video_id=video_id)
self.report_warning(f'{errnote}{bug_reports_message()}')
return [], {}
res = self._download_webpage_handle(
m3u8_url, video_id,
note='Downloading m3u8 information' if note is None else note,
errnote='Failed to download m3u8 information' if errnote is None else errnote,
if note is None:
note = 'Downloading m3u8 information'
if errnote is None:
errnote = 'Failed to download m3u8 information'
response = self._request_webpage(
m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
if response is False:
return [], {}
m3u8_doc, urlh = res
m3u8_url = urlh.url
with contextlib.closing(response):
prefix = response.read(512)
if not prefix.startswith(b'#EXTM3U'):
msg = 'Response data has no m3u header'
if fatal:
raise ExtractorError(msg, video_id=video_id)
self.report_warning(f'{msg}{bug_reports_message()}', video_id=video_id)
return [], {}
content = self._webpage_read_content(
response, m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, prefix=prefix, data=data)
if content is False:
return [], {}
return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
content, response.url, ext=ext, entry_protocol=entry_protocol,
preference=preference, quality=quality, m3u8_id=m3u8_id,
note=note, errnote=errnote, fatal=fatal, live=live, data=data,
headers=headers, query=query, video_id=video_id)

View File

@@ -96,6 +96,24 @@ class CondeNastIE(InfoExtractor):
'upload_date': '20150916',
'timestamp': 1442434920,
},
}, {
# FIXME: Subtitles
'url': 'https://www.vanityfair.com/video/watch/vf-quiz-show-squid-game-s3',
'info_dict': {
'id': '6862f999c1afbc5ff06b4803',
'ext': 'mp4',
'title': '\'Squid Game\' Cast Tests How Well They Know Each Other',
'categories': ['Arts & Culture', 'Hollywood'],
'description': 'md5:7a9c668a1fc87648e77da13842ec1534',
'duration': 955,
'season': 'Season 1',
'series': 'Quizzing Each Other',
'tags': 'count:2',
'thumbnail': r're:https?://dwgyu36up6iuz\.cloudfront\.net/.+\.jpg',
'timestamp': 1751341306,
'upload_date': '20250701',
'uploader': 'vanityfair',
},
}, {
'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
'only_matching': True,

View File

@@ -8,7 +8,6 @@
class CrooksAndLiarsIE(InfoExtractor):
_VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
_EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
_TESTS = [{
'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
'info_dict': {
@@ -16,7 +15,7 @@ class CrooksAndLiarsIE(InfoExtractor):
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
@@ -26,6 +25,20 @@ class CrooksAndLiarsIE(InfoExtractor):
'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'duration': 236,
'thumbnail': r're:https?://crooksandliars\.com/files/.+',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -1,49 +0,0 @@
from .common import InfoExtractor
class CTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P<id>(?:show|movie)s/[^/]+/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88',
'info_dict': {
'id': '2102249',
'ext': 'flv',
'title': 'Wednesday, December 23, 2020',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.',
'timestamp': 1608732000,
'upload_date': '20201223',
'series': 'Your Morning',
'season': '2020-2021',
'season_number': 5,
'episode_number': 88,
'tags': ['Your Morning'],
'categories': ['Talk Show'],
'duration': 7467.126,
},
}, {
'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
content = self._download_json(
'https://www.ctv.ca/space-graphql/graphql', display_id, query={
'query': '''{
resolvedPath(path: "/%s") {
lastSegment {
content {
... on AxisContent {
axisId
videoPlayerDestCode
}
}
}
}
}''' % display_id, # noqa: UP031
})['data']['resolvedPath']['lastSegment']['content']
video_id = content['axisId']
return self.url_result(
'9c9media:{}:{}'.format(content['videoPlayerDestCode'], video_id),
'NineCNineMedia', video_id)

View File

@@ -19,11 +19,22 @@ class DailyMailIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
},
}, {
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.daily-news.gr/lifestyle/%ce%b7-%cf%84%cf%81%ce%b1%ce%b3%ce%bf%cf%85%ce%b4%ce%af%cf%83%cf%84%cf%81%ce%b9%ce%b1-jessie-j-%ce%bc%ce%bf%ce%b9%cf%81%ce%ac%cf%83%cf%84%ce%b7%ce%ba%ce%b5-%cf%83%cf%85%ce%b3%ce%ba%ce%bb%ce%bf%ce%bd/',
'info_dict': {
'id': '3463585',
'ext': 'mp4',
'title': 'Jessie J reveals she has undergone surgery as she shares clips',
'description': 'md5:9fa9a25feca5b656b0b4a39c922fad1e',
'thumbnail': r're:https?://i\.dailymail\.co\.uk/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -119,13 +119,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
_EMBED_REGEX = [rf'(?ix)<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)["\'](?P<url>{_VALID_URL[5:]})']
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'info_dict': {
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'duration': 187,
'tags': 'count:5',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
@@ -133,18 +134,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'age_limit': 0,
'view_count': int,
'like_count': int,
'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1cmt4ZcZ9KiM/x1080',
},
}, {
'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
'md5': 'e2f9717c6604773f963f069ca53a07f8',
'info_dict': {
'id': 'x89eyek',
'ext': 'mp4',
'title': "En quête d'esprit du 27/03/2022",
'title': 'En quête d\'esprit du 27/03/2022',
'description': 'md5:66542b9f4df2eb23f314fc097488e553',
'duration': 2756,
'tags': 'count:1',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1648383669,
'upload_date': '20220327',
'uploader': 'CNEWS',
@@ -152,8 +152,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'age_limit': 0,
'view_count': int,
'like_count': int,
'tags': ['en_quete_d_esprit'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1clTH6StrxMP/x1080',
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
@@ -163,8 +161,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'ext': 'mp4',
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
'description': 'Several come bundled with the Steam Controller.',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 74,
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1425657362,
'upload_date': '20150306',
'uploader': 'IGN',
@@ -183,10 +181,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader': 'Katy Perry',
'upload_date': '20130905',
},
'params': {
'skip_download': True,
},
'skip': 'VEVO is only available in some countries',
'skip': 'Invalid URL',
}, {
# age-restricted video
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
@@ -259,9 +254,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader_id': 'x2vtgmm',
'age_limit': 0,
'tags': [],
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'view_count': int,
'like_count': int,
'thumbnail': r're:https://\w+.dmcdn.net/v/WnEY61cmvMxt2Fi6d/x1080',
},
}, {
# https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
@@ -276,18 +271,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'info_dict': {
'id': 'x8u4owg',
'ext': 'mp4',
'description': 'À bord du « véloto », lalternative à la voiture pour la campagne',
'like_count': int,
'uploader': 'Le Parisien',
'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
'upload_date': '20240309',
'view_count': int,
'tags': 'count:7',
'thumbnail': r're:https?://www\.leparisien\.fr/.+\.jpg',
'timestamp': 1709997866,
'age_limit': 0,
'uploader_id': 'x32f7b',
'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
'duration': 428.0,
'description': 'À bord du « véloto », lalternative à la voiture pour la campagne',
'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
},
}, {
# https://geo.dailymotion.com/player/xry80.html?video=x8vu47w
@@ -297,9 +292,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'ext': 'mp4',
'like_count': int,
'uploader': 'Metatube',
'thumbnail': r're:https://\w+.dmcdn.net/v/W1G_S1coGSFTfkTeR/x1080',
'upload_date': '20240326',
'view_count': int,
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1711496732,
'age_limit': 0,
'uploader_id': 'x2xpy74',
@@ -308,6 +303,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'description': 'Que lindura',
'tags': [],
},
'skip': 'Invalid URL',
}, {
# //geo.dailymotion.com/player/xysxq.html?video=k2Y4Mjp7krAF9iCuINM
'url': 'https://lcp.fr/programmes/avant-la-catastrophe-la-naissance-de-la-dictature-nazie-1933-1936-346819',
@@ -322,11 +318,30 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'like_count': int,
'age_limit': 0,
'duration': 3220,
'thumbnail': 'https://s1.dmcdn.net/v/Xvumk1djJBUZfjj2a/x1080',
'tags': [],
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1739919947,
'upload_date': '20250218',
},
'skip': 'Invalid URL',
}, {
'url': 'https://forum.ionicframework.com/t/ionic-2-jw-player-dailymotion-player/83248',
'info_dict': {
'id': 'xwr14q',
'ext': 'mp4',
'title': 'Macklemore & Ryan Lewis - Thrift Shop (feat. Wanz)',
'age_limit': 0,
'description': 'md5:47fbe168b5a6ddc4a205e20dd6c841b2',
'duration': 234,
'like_count': int,
'tags': 'count:5',
'thumbnail': r're:https?://s[12]\.dmcdn\.net/v/.+',
'timestamp': 1358177670,
'upload_date': '20130114',
'uploader': 'Macklemore Official',
'uploader_id': 'x19qlwr',
'view_count': int,
},
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
@@ -540,7 +555,7 @@ class DailymotionSearchIE(DailymotionPlaylistBaseIE):
'id': 'king of turtles',
'title': 'king of turtles',
},
'playlist_mincount': 90,
'playlist_mincount': 0,
}]
_SEARCH_QUERY = 'query SEARCH_QUERY( $query: String! $page: Int $limit: Int ) { search { videos( query: $query first: $limit page: $page ) { edges { node { xid } } } } } '
@@ -584,7 +599,7 @@ class DailymotionUserIE(DailymotionPlaylistBaseIE):
'info_dict': {
'id': 'nqtv',
},
'playlist_mincount': 152,
'playlist_mincount': 148,
}, {
'url': 'http://www.dailymotion.com/user/UnderProject',
'info_dict': {

View File

@@ -11,8 +11,14 @@
class DangalPlayBaseIE(InfoExtractor):
_NETRC_MACHINE = 'dangalplay'
_REGION = 'IN'
_OTV_USER_ID = None
_LOGIN_HINT = 'Pass credentials as -u "token" -p "USER_ID" where USER_ID is the `otv_user_id` in browser local storage'
_LOGIN_HINT = (
'Pass credentials as -u "token" -p "USER_ID" '
'(where USER_ID is the value of "otv_user_id" in your browser local storage). '
'Your login region can be optionally suffixed to the username as @REGION '
'(where REGION is the two-letter "region" code found in your browser local storage), '
'e.g.: -u "token@IN" -p "USER_ID"')
_API_BASE = 'https://ottapi.dangalplay.com'
_AUTH_TOKEN = 'jqeGWxRKK7FK5zEk3xCM' # from https://www.dangalplay.com/main.48ad19e24eb46acccef3.js
_SECRET_KEY = 'f53d31a4377e4ef31fa0' # same as above
@@ -20,8 +26,12 @@ class DangalPlayBaseIE(InfoExtractor):
def _perform_login(self, username, password):
if self._OTV_USER_ID:
return
if username != 'token' or not re.fullmatch(r'[\da-f]{32}', password):
mobj = re.fullmatch(r'token(?:@(?P<region>[A-Z]{2}))?', username)
if not mobj or not re.fullmatch(r'[\da-f]{32}', password):
raise ExtractorError(self._LOGIN_HINT, expected=True)
if region := mobj.group('region'):
self._REGION = region
self.write_debug(f'Setting login region to "{self._REGION}"')
self._OTV_USER_ID = password
def _real_initialize(self):
@@ -52,7 +62,7 @@ def _call_api(self, path, display_id, note='Downloading JSON metadata', fatal=Tr
f'{self._API_BASE}/{path}', display_id, note, fatal=fatal,
headers={'Accept': 'application/json'}, query={
'auth_token': self._AUTH_TOKEN,
'region': 'IN',
'region': self._REGION,
**query,
})
@@ -106,7 +116,7 @@ def _generate_api_data(self, data):
'catalog_id': catalog_id,
'content_id': content_id,
'category': '',
'region': 'IN',
'region': self._REGION,
'auth_token': self._AUTH_TOKEN,
'id': self._OTV_USER_ID,
'md5': hashlib.md5(unhashed.encode()).hexdigest(),
@@ -129,11 +139,14 @@ def _real_extract(self, url):
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 422:
error_info = traverse_obj(e.cause.response.read().decode(), ({json.loads}, 'error', {dict})) or {}
if error_info.get('code') == '1016':
error_code = error_info.get('code')
if error_code == '1016':
self.raise_login_required(
f'Your token has expired or is invalid. {self._LOGIN_HINT}', method=None)
elif msg := error_info.get('message'):
raise ExtractorError(msg)
elif error_code == '4028':
self.raise_login_required(
f'Your login region is unspecified or incorrect. {self._LOGIN_HINT}', method=None)
raise ExtractorError(join_nonempty(error_code, error_info.get('message'), delim=': '))
raise
m3u8_url = traverse_obj(details, (

View File

@@ -12,13 +12,13 @@ class DBTVIE(InfoExtractor):
'ext': 'mp4',
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
'thumbnail': r're:https?://.*\.jpg',
'thumbnail': r're:https?://.+\.jpg',
'upload_date': '20160916',
'duration': 69,
'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
'uploader': 'Dagbladet',
},
'add_ie': ['Youtube'],
'skip': 'Invalid URL',
}, {
'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
'only_matching': True,
@@ -26,6 +26,20 @@ class DBTVIE(InfoExtractor):
'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.dagbladet.no/nyheter/rekordstort-russisk-angrep/83325693',
'info_dict': {
'id': '1HW7fYry',
'ext': 'mp4',
'title': 'Putin taler - så skjer dette',
'description': 'md5:3e8bacee33de861a9663d9a3fcc54e5e',
'display_id': 'putin-taler-sa-skjer-dette',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1751043600,
'upload_date': '20250627',
},
}]
def _real_extract(self, url):
display_id, video_id = self._match_valid_url(url).groups()

View File

@@ -4,6 +4,7 @@
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
jwt_decode_hs256,
parse_codecs,
try_get,
@@ -222,11 +223,18 @@ def _entries(self, items, language, type_, **kwargs):
raise
formats = []
for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for fmt in formats:
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
fmt.update(parse_codecs(fmt['format_note']))
for fmt_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
ext = determine_ext(fmt_url)
if ext == 'm3u8':
fmts = self._extract_m3u8_formats(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
for fmt in fmts:
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
fmt.update(parse_codecs(fmt['format_note']))
formats.extend(fmts)
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(fmt_url, video_id, mpd_id='dash', fatal=False))
else:
self.report_warning(f'Skipping unsupported format extension "{ext}"')
yield {
'id': video_id,

View File

@@ -206,7 +206,7 @@ def _real_extract(self, url):
'is_live': True,
**traverse_obj(room, {
'display_id': ('url', {str}, {lambda i: i[1:]}),
'title': ('room_name', {unescapeHTML}),
'title': ('room_name', {str}, {unescapeHTML}),
'description': ('show_details', {str}),
'uploader': ('nickname', {str}),
'thumbnail': ('room_src', {url_or_none}),

View File

@@ -64,7 +64,7 @@ class DreiSatIE(ZDFBaseIE):
'title': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'description': 'md5:bae51bfc22f15563ce3acbf97d2e8844',
'duration': 5399.0,
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1743329640903',
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1747256996338',
'chapters': 'count:24',
'episode': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'episode_id': 'POS_1ef236cc-b390-401e-acd0-4fb4b04315fb',

View File

@@ -1,215 +0,0 @@
import functools
import re
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
smuggle_url,
unsmuggle_url,
url_or_none,
)
class EaglePlatformIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
eagleplatform:(?P<custom_host>[^/]+):|
https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
)
(?P<id>\d+)
'''
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
_TESTS = [{
# http://lenta.ru/news/2015/03/06/navalny/
'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
'info_dict': {
'id': '227304',
'ext': 'mp4',
'title': 'Навальный вышел на свободу',
'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 87,
'view_count': int,
'age_limit': 0,
},
}, {
# http://muz-tv.ru/play/7129/
# http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
'url': 'eagleplatform:media.clipyou.ru:12820',
'md5': '358597369cf8ba56675c1df15e7af624',
'info_dict': {
'id': '12820',
'ext': 'mp4',
'title': "'O Sole Mio",
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 216,
'view_count': int,
},
'skip': 'Georestricted',
}, {
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
'only_matching': True,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
add_referer = functools.partial(smuggle_url, data={'referrer': url})
res = tuple(super()._extract_embed_urls(url, webpage))
if res:
return map(add_referer, res)
PLAYER_JS_RE = r'''
<script[^>]+
src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
.+?
'''
# "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
mobj = re.search(
rf'''(?xs)
{PLAYER_JS_RE}
<div[^>]+
class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
data-id=["\'](?P<id>\d+)
''', webpage)
if mobj is not None:
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
# Generalization of "Javascript code usage", "Combined usage" and
# "Usage without attaching to DOM" embeddings (see
# http://dultonmedia.github.io/eplayer/)
mobj = re.search(
r'''(?xs)
%s
<script>
.+?
new\s+EaglePlayer\(
(?:[^,]+\s*,\s*)?
{
.+?
\bid\s*:\s*["\']?(?P<id>\d+)
.+?
}
\s*\)
.+?
</script>
''' % PLAYER_JS_RE, webpage) # noqa: UP031
if mobj is not None:
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
@staticmethod
def _handle_error(response):
status = int_or_none(response.get('status', 200))
if status != 200:
raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, *args, **kwargs):
try:
response = super()._download_json(
url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, HTTPError):
response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
self._handle_error(response)
raise
return response
def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
return self._download_json(url_or_request, video_id, note)['data'][0]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = self._match_valid_url(url)
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
headers = {}
query = {
'id': video_id,
}
referrer = smuggled_data.get('referrer')
if referrer:
headers['Referer'] = referrer
query['referrer'] = referrer
player_data = self._download_json(
f'http://{host}/api/player_data', video_id,
headers=headers, query=query)
media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
title = media['title']
description = media.get('description')
thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
duration = int_or_none(media.get('duration'))
view_count = int_or_none(media.get('views'))
age_restriction = media.get('age_restriction')
age_limit = None
if age_restriction:
age_limit = 0 if age_restriction == 'allow_all' else 18
secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
formats = []
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
m3u8_formats_dict = {}
for f in m3u8_formats:
if f.get('height') is not None:
m3u8_formats_dict[f['height']] = f
mp4_data = self._download_json(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from
# http://lentaru.media.eagleplatform.com/player/player.js
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
video_id, 'Downloading mp4 JSON', fatal=False)
if mp4_data:
for format_id, format_url in mp4_data.get('data', {}).items():
if not url_or_none(format_url):
continue
height = int_or_none(format_id)
if height is not None and m3u8_formats_dict.get(height):
f = m3u8_formats_dict[height].copy()
f.update({
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
else:
f = {
'format_id': f'http-{format_id}',
'height': int_or_none(format_id),
}
f['url'] = format_url
formats.append(f)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'age_limit': age_limit,
'formats': formats,
}
class ClipYouEmbedIE(InfoExtractor):
_VALID_URL = False
@classmethod
def _extract_embed_urls(cls, url, webpage):
mobj = re.search(
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
if mobj is not None:
yield smuggle_url('eagleplatform:{host}:{id}'.format(**mobj.groupdict()), {'referrer': url})

View File

@@ -64,14 +64,12 @@ class ERTFlixCodenameIE(ERTFlixBaseIE):
_VALID_URL = r'ertflix:(?P<id>[\w-]+)'
_TESTS = [{
'url': 'ertflix:monogramma-praxitelis-tzanoylinos',
'md5': '5b9c2cd171f09126167e4082fc1dd0ef',
'info_dict': {
'id': 'monogramma-praxitelis-tzanoylinos',
'ext': 'mp4',
'title': 'md5:ef0b439902963d56c43ac83c3f41dd0e',
'title': 'monogramma-praxitelis-tzanoylinos',
},
},
]
}]
def _extract_formats_and_subs(self, video_id):
media_info = self._call_api(video_id, codename=video_id)
@@ -131,13 +129,14 @@ class ERTFlixIE(ERTFlixBaseIE):
'duration': 3166,
'age_limit': 8,
},
'skip': 'Invalid URL',
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_mincount': 64,
}, {
@@ -145,28 +144,28 @@ class ERTFlixIE(ERTFlixBaseIE):
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_count': 22,
'playlist_mincount': 66,
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1&season=2021%20-%202022',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
'title': 'Monogramma',
'description': 'md5:e30cc640e6463da87f210a8ed10b2439',
},
'playlist_mincount': 36,
'playlist_mincount': 25,
}, {
'url': 'https://www.ertflix.gr/series/ser.164991-to-diktuo-1?season=1-9',
'info_dict': {
'id': 'ser.164991',
'age_limit': 8,
'description': 'Η πρώτη ελληνική εκπομπή με θεματολογία αποκλειστικά γύρω από το ίντερνετ.',
'title': 'Το δίκτυο',
'title': 'The Network',
'description': 'The first Greek show featuring topics exclusively around the internet.',
},
'playlist_mincount': 9,
'playlist_mincount': 0,
}, {
'url': 'https://www.ertflix.gr/en/vod/vod.127652-ta-kalytera-mas-chronia-ep1-mia-volta-sto-feggari',
'only_matching': True,
@@ -282,6 +281,16 @@ class ERTWebtvEmbedIE(InfoExtractor):
'ext': 'mp4',
'thumbnail': 'https://program.ert.gr/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
},
'skip': 'Invalid URL',
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.ertnews.gr/video/manolis-goyalles-o-anthropos-piso-apo-ti-diadiktyaki-vasilopita/',
'info_dict': {
'id': '2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
'ext': 'mp4',
'title': 'VOD - 2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
'thumbnail': r're:https?://www\.ert\.gr/themata/photos/.+\.jpg',
},
}]
def _real_extract(self, url):

View File

@@ -329,6 +329,7 @@ class WatchESPNIE(AdobePassIE):
}]
_API_KEY = 'ZXNwbiZicm93c2VyJjEuMC4w.ptUt7QxsteaRruuPmGZFaJByOoqKvDP2a5YkInHrc7c'
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIyZGJmZWM4My03OWE1LTQyNzEtYTVmZC04NTZjYTMxMjRjNjMiLCJuYmYiOjE1NDAyMTI3NjEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQwMjEyNzYxfQ.yaK3r4AI2uLVvsyN1GLzqzgzRlxMPtasSaiYYBV0wIstqih5tvjTmeoLmi8Xy9Kp_U7Md-bOffwiyK3srHkpUkhhwXLH2x6RPjmS1tPmhaG7-3LBcHTf2ySPvXhVf7cN4ngldawK4tdtLtsw6rF_JoZE2yaC6XbS2F51nXSFEDDnOQWIHEQRG3aYAj-38P2CLGf7g-Yfhbp5cKXeksHHQ90u3eOO4WH0EAjc9oO47h33U8KMEXxJbvjV5J8Va2G2fQSgLDZ013NBI3kQnE313qgqQh2feQILkyCENpB7g-TVBreAjOaH1fU471htSoGGYepcAXv-UDtpgitDiLy7CQ'
def _call_bamgrid_api(self, path, video_id, payload=None, headers={}):
if 'Authorization' not in headers:
@@ -405,8 +406,8 @@ def _real_extract(self, url):
# TV Provider required
else:
resource = self._get_mvpd_resource('ESPN', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource).encode()
resource = self._get_mvpd_resource('espn1', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource, self._SOFTWARE_STATEMENT).encode()
asset = self._download_json(
f'https://watch.auth.api.espn.com/video/auth/media/{video_id}/asset?apikey=uiqlbgzdwuru14v627vdusswb',

View File

@@ -81,13 +81,14 @@ class FacebookIE(InfoExtractor):
'description': 'md5:34675bda53336b1d16400265c2bb9b3b',
'uploader': 'RADIO KICKS FM',
'upload_date': '20230818',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1692346159,
'thumbnail': r're:^https?://.*',
'uploader_id': '100063551323670',
'duration': 3133.583,
'view_count': int,
'concurrent_view_count': 0,
},
'expected_warnings': ['Cannot parse data'],
}, {
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -106,17 +107,18 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'title': 'Asif',
'title': '119 reactions · 1.4K shares | Asif Nawab Butt on Reels',
'description': '',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1399398998,
'thumbnail': r're:^https?://.*',
'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl',
'uploader_id': 'pfbid028xue38TBXRyNbiqBSV2LFs3QK3yopvKjupbqFoL6U9SKbx4p2SMdJjQSBvnjsHGWl',
'duration': 131.03,
'concurrent_view_count': int,
'view_count': int,
},
'expected_warnings': ['Cannot parse data'],
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
@@ -158,7 +160,7 @@ class FacebookIE(InfoExtractor):
'id': '10153664894881749',
'ext': 'mp4',
'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1456259628,
'upload_date': '20160223',
'uploader': 'Barack Obama',
@@ -168,7 +170,7 @@ class FacebookIE(InfoExtractor):
# have 1080P, but only up to 720p in swf params
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
'md5': '1659aa21fb3dd1585874f668e81a72c8',
'md5': '70b82ebf5f0e9b91b2a49d3db3563611',
'info_dict': {
'id': '10155529876156509',
'ext': 'mp4',
@@ -177,7 +179,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1477818095,
'upload_date': '20161030',
'uploader': 'CNN',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'view_count': int,
'uploader_id': '100059479812265',
'concurrent_view_count': int,
@@ -198,13 +200,11 @@ class FacebookIE(InfoExtractor):
'uploader': 'Yaroslav Korpan',
'uploader_id': 'pfbid06AScABAWcW91qpiuGrLt99Ef9tvwHoXP6t8KeFYEqkSfreMtfa9nTveh8b2ZEVSWl',
'concurrent_view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'view_count': int,
'duration': 11736.446,
},
'params': {
'skip_download': True,
},
'skip': 'Invalid URL',
}, {
# FIXME: Cannot parse data error
'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
@@ -215,7 +215,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1477305000,
'upload_date': '20161024',
'uploader': 'La Guía Del Varón',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
},
'skip': 'Requires logging in',
}, {
@@ -244,9 +244,10 @@ class FacebookIE(InfoExtractor):
'upload_date': '20171124',
'uploader': 'Vickie Gentry',
'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'duration': 148.224,
},
'skip': 'Invalid URL',
}, {
# data.node.comet_sections.content.story.attachments[].styles.attachment.media
'url': 'https://www.facebook.com/attn/posts/pfbid0j1Czf2gGDVqeQ8KiMLFm3pWN8GxsQmeRrVhimWDzMuKQoR8r4b1knNsejELmUgyhl',
@@ -260,7 +261,7 @@ class FacebookIE(InfoExtractor):
'duration': 132.675,
'uploader_id': '100064451419378',
'view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1701975646,
},
}, {
@@ -271,9 +272,9 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'Lela Evans',
'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'uploader': 'Lela Evans',
'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl',
'uploader_id': 'pfbid02wjMpknobSMnyynK3TNKN4Ww1StcpAKXgowqTyge3bz7LwHZMQ68uiXzzbu7xeryBl',
'upload_date': '20231228',
'timestamp': 1703804085,
'duration': 394.347,
@@ -326,28 +327,27 @@ class FacebookIE(InfoExtractor):
'uploader_id': '100066514874195',
'duration': 4524.001,
'view_count': int,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'concurrent_view_count': int,
},
'params': {
'skip_download': True,
},
'params': {'skip_download': True},
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.all_subattachments.nodes[].media
'url': 'https://www.facebook.com/100033620354545/videos/106560053808006/',
'info_dict': {
'id': '106560053808006',
'ext': 'mp4',
'title': 'Josef',
'thumbnail': r're:^https?://.*',
'title': 'Josef Novak on Reels',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'concurrent_view_count': int,
'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl',
'uploader_id': 'pfbid0cjYJYXpePWqhZ9DgpB6gKXrN2q3obwducdKm4wT7K5nkhbfKg5cneocYbsdaji7fl',
'timestamp': 1549275572,
'duration': 3.283,
'uploader': 'Josef Novak',
'description': '',
'upload_date': '20190204',
},
'expected_warnings': ['Cannot parse data'],
}, {
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/watch/?v=647537299265662',
@@ -406,7 +406,7 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'ANALISI IN CAMPO OSCURO " Coaguli nel sangue dei vaccinati"',
'description': 'Other event by Comitato Liberi Pensatori on Tuesday, October 18 2022',
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'uploader': 'Comitato Liberi Pensatori',
'uploader_id': '100065709540881',
},
@@ -414,6 +414,56 @@ class FacebookIE(InfoExtractor):
'url': 'https://www.facebook.com/groups/1513990329015294/posts/d41d8cd9/2013209885760000/?app=fbl',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# <iframe> embed
'url': 'http://www.unique-almeria.com/mini-hollywood.html',
'md5': 'cba5d8c5021e9340dcefe925255e2c3e',
'info_dict': {
'id': '1529066599879',
'ext': 'mp4',
'title': 'Facebook video #1529066599879',
},
'expected_warnings': ['unable to extract uploader'],
}, {
# FIXME: Embed detection
# <iframe> embed, plugin video
'url': 'https://www.newsmemory.com/eedition/e-publishing-solutions/2-in-one-app/',
'md5': 'ae97d4a44f8cc9a8b1a4c03b9ed793af',
'info_dict': {
'id': '10155710648695814',
'ext': 'mp4',
'title': 'Download the all new and improved Trinidad Express App',
'concurrent_view_count': int,
'description': 'md5:4806195c99908e4189b45b1c23bd4f89',
'duration': 69.408,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1533919195,
'upload_date': '20180810',
'uploader': 'Trinidad Express Newspapers',
'uploader_id': '100064446413648',
'view_count': int,
},
'expected_warnings': ['Cannot parse data'],
}, {
# API embed
'url': 'https://www.curs.md/ro',
'md5': '090bae53b9bff2be993c896edc2ea205',
'info_dict': {
'id': '334484292523563',
'ext': 'mp4',
'title': 'md5:9abffe1c86cdd967ffa224e1ccc13b90',
'concurrent_view_count': int,
'description': 'md5:0ba98567a61c640f9fabf1882235b33d',
'duration': 8789.891,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1700603114,
'upload_date': '20231121',
'uploader': 'Istoria Moldovei',
'uploader_id': '100063529778592',
'view_count': int,
},
'params': {'extractor_args': {'generic': {'impersonate': ['chrome']}}},
}]
_SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
_api_config = {
'graphURI': '/api/graphql/',
@@ -898,20 +948,24 @@ def _real_extract(self, url):
class FacebookPluginsVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
_TESTS = [{
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
'md5': 'af83aeae1d595f377c6e47a450828155',
'info_dict': {
'id': '10154383743583686',
'ext': 'mp4',
# TODO: Fix title, uploader
'title': 'What to do during the haze?',
'uploader': 'Gov.sg',
'upload_date': '20160826',
'concurrent_view_count': int,
'description': 'md5:81839c0979803a014b20798df255ed0b',
'duration': 65.087,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1472184808,
'upload_date': '20160826',
'uploader': 'gov.sg',
'uploader_id': '100064718678925',
'view_count': int,
},
'add_ie': [FacebookIE.ie_key()],
'expected_warnings': ['Cannot parse data'],
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
'only_matching': True,
@@ -945,7 +999,7 @@ class FacebookRedirectURLIE(InfoExtractor):
'tags': 'count:11',
'duration': 3332,
'live_status': 'not_live',
'thumbnail': 'https://i.ytimg.com/vi/pO8h3EaFRdo/maxresdefault.jpg',
'thumbnail': r're:https?://i\.ytimg\.com/vi/.+',
'channel_url': 'https://www.youtube.com/channel/UCGBpxWJr9FNOcFYA5GkKrMg',
'availability': 'public',
'uploader_url': 'http://www.youtube.com/user/brtvofficial',
@@ -954,8 +1008,7 @@ class FacebookRedirectURLIE(InfoExtractor):
'view_count': int,
'like_count': int,
},
'add_ie': ['Youtube'],
'params': {'skip_download': 'Youtube'},
'skip': 'Youtube video is now private',
}]
def _real_extract(self, url):
@@ -968,22 +1021,20 @@ def _real_extract(self, url):
class FacebookReelIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/reel/(?P<id>\d+)'
IE_NAME = 'facebook:reel'
_TESTS = [{
'url': 'https://www.facebook.com/reel/1195289147628387',
'md5': 'a53256d10fc2105441fe0c4212ed8cea',
'md5': 'aeb0153ecb2eaacdf2dc2bf88f593fef',
'info_dict': {
'id': '1195289147628387',
'ext': 'mp4',
'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$',
'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$',
'uploader': 'Beast Camp Training',
'title': '9.7K views · 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the “Slapathon” commence!! 👊👋 | Beast Camp Training',
'description': 'md5:5a767dc7e78718667b150a7facc4a34f',
'uploader': '9.7K views &#xb7; 352 reactions | When your trying to help your partner out with an arrest and #FAAFO games begin. Let the &#x201c;Slapathon&#x201d; commence!! &#x1f44a;&#x1f44b; | Beast Camp Training',
'uploader_id': '100040874179269',
'duration': 9.579,
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1637502609,
'upload_date': '20211121',
'thumbnail': r're:^https?://.*',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
@@ -998,7 +1049,6 @@ def _real_extract(self, url):
class FacebookAdsIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/ads/library/?\?(?:[^#]+&)?id=(?P<id>\d+)'
IE_NAME = 'facebook:ads'
_TESTS = [{
'url': 'https://www.facebook.com/ads/library/?id=899206155126718',
'info_dict': {
@@ -1008,12 +1058,13 @@ class FacebookAdsIE(InfoExtractor):
'description': 'md5:0822724069e3aca97cbed5dabbab282e',
'uploader': 'Kandao',
'uploader_id': '774114102743284',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://facebook.com/KandaoVR',
'timestamp': 1702548330,
'thumbnail': r're:^https?://.*',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'upload_date': '20231214',
'like_count': int,
},
'skip': 'Invalid URL',
}, {
# key 'watermarked_video_sd_url' missing
'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
@@ -1024,9 +1075,9 @@ class FacebookAdsIE(InfoExtractor):
'description': 'md5:02a446ace7ff8c3c37a2892922492490',
'uploader': 'mat.nawrocki',
'uploader_id': '148586968341456',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://www.instagram.com/_u/mat.nawrocki',
'thumbnail': r're:https?://scontent\.fitm\d-1\.fna\.fbcdn\.net/.+',
'timestamp': 1723452305,
'thumbnail': r're:^https?://.*',
'upload_date': '20240812',
'like_count': int,
},
@@ -1037,12 +1088,13 @@ class FacebookAdsIE(InfoExtractor):
'title': 'Jusqu\u2019\u00e0 -25% sur une s\u00e9lection de vins p\u00e9tillants italiens ',
'uploader': 'Eataly Paris Marais',
'uploader_id': '2086668958314152',
'uploader_url': r're:^https?://.*',
'uploader_url': 'https://facebook.com/EatalyParisMarais',
'timestamp': 1703571529,
'upload_date': '20231226',
'like_count': int,
},
'playlist_count': 3,
'skip': 'Invalid URL',
}, {
'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
'only_matching': True,

105
yt_dlp/extractor/faulio.py Normal file
View File

@@ -0,0 +1,105 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import js_to_json, url_or_none
from ..utils.traversal import traverse_obj
class FaulioLiveIE(InfoExtractor):
_DOMAINS = (
'aloula.sba.sa',
'bahry.com',
'maraya.sba.net.ae',
'sat7plus.org',
)
_VALID_URL = fr'https?://(?:{"|".join(map(re.escape, _DOMAINS))})/(?:(?:en|ar|fa)/)?live/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'https://aloula.sba.sa/live/saudiatv',
'info_dict': {
'id': 'aloula.faulio.com_saudiatv',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://bahry.com/live/1',
'info_dict': {
'id': 'bahry.faulio.com_1',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://maraya.sba.net.ae/live/1',
'info_dict': {
'id': 'maraya.faulio.com_1',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://sat7plus.org/live/pars',
'info_dict': {
'id': 'sat7.faulio.com_pars',
'title': str,
'description': str,
'ext': 'mp4',
'live_status': 'is_live',
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://sat7plus.org/fa/live/arabic',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
config_data = self._search_json(
r'window\.__NUXT__\.config=', webpage, 'config', video_id, transform_source=js_to_json)
api_base = config_data['public']['TRANSLATIONS_API_URL']
channel = traverse_obj(
self._download_json(f'{api_base}/channels', video_id),
(lambda k, v: v['url'] == video_id, any))
formats = []
subtitles = {}
if hls_url := traverse_obj(channel, ('streams', 'hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', m3u8_id='hls', live=True, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if mpd_url := traverse_obj(channel, ('streams', 'mpd', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
mpd_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': f'{urllib.parse.urlparse(api_base).hostname}_{video_id}',
**traverse_obj(channel, {
'title': ('title', {str}),
'description': ('description', {str}),
}),
'formats': formats,
'subtitles': subtitles,
'is_live': True,
}

View File

@@ -22,8 +22,23 @@ class FC2IE(InfoExtractor):
'md5': 'a6ebe8ebe0396518689d963774a54eb7',
'info_dict': {
'id': '20121103kUan1KHs',
'ext': 'flv',
'title': 'Boxing again with Puff',
'ext': 'mp4',
'thumbnail': r're:https?://.+\.jpe?g',
},
'params': {
'skip_download': 'm3u8',
},
}, {
# Direct video url
'url': 'https://video.fc2.com/content/20121209FP73fxDx',
'md5': '066bdb9b3a56a97f49cbf0d0b8a75a1f',
'info_dict': {
'id': '20121209FP73fxDx',
'title': 'Farewelling The Wiggles Live in Sydney Dec 8 2012',
'ext': 'mp4',
'thumbnail': r're:https?://.+\.jpe?g',
'description': 'Saying goodbye to the Wiggles at their Celebration Concert in Sydney, and what a concert that was!',
},
}, {
'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
@@ -104,7 +119,7 @@ def _real_extract(self, url):
'title': title,
'url': vid_url,
'ext': 'mp4',
'protocol': 'm3u8_native',
'protocol': 'm3u8_native' if vidplaylist.get('type') == 2 else 'https',
'description': description,
'thumbnail': thumbnail,
}

View File

@@ -17,8 +17,140 @@
from ..utils.traversal import traverse_obj
class FloatplaneIE(InfoExtractor):
class FloatplaneBaseIE(InfoExtractor):
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
f'{self._BASE_URL}/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data',
impersonate=self._IMPERSONATE_TARGET)
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], f'{self._BASE_URL}/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
stream = self._download_json(
f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
'type': 'vod' if media_typ == 'video' else 'aod',
'guid': metadata['guid'],
}, note=f'Downloading {media_typ} stream data',
impersonate=self._IMPERSONATE_TARGET)
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
formats = []
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
url = urljoin(stream['cdn'], format_path(traverse_obj(
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
format_id = traverse_obj(quality, ('name', {str}))
hls_aes = {}
m3u8_data = None
# If we need impersonation for the API, then we need it for HLS keys too: extract in advance
if self._IMPERSONATE_TARGET is not None:
m3u8_data = self._download_webpage(
url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
if not m3u8_data:
continue
key_url = self._search_regex(
r'#EXT-X-KEY:METHOD=AES-128,URI="(https?://[^"]+)"',
m3u8_data, 'HLS AES key URI', default=None)
if key_url:
urlh = self._request_webpage(
key_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'HLS AES key', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'HLS AES key', delim=' '))
if urlh:
hls_aes['key'] = urlh.read().hex()
formats.append({
**traverse_obj(quality, {
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
'format_id': format_id,
'hls_media_playlist_data': m3u8_data,
'hls_aes': hls_aes or None,
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'http_headers': self._HEADERS,
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneIE(FloatplaneBaseIE):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/post/(?P<id>\w+)'
_BASE_URL = 'https://www.floatplane.com'
_IMPERSONATE_TARGET = None
_HEADERS = {
'Origin': _BASE_URL,
'Referer': f'{_BASE_URL}/',
}
_TESTS = [{
'url': 'https://www.floatplane.com/post/2Yf3UedF7C',
'info_dict': {
@@ -170,105 +302,9 @@ class FloatplaneIE(InfoExtractor):
}]
def _real_initialize(self):
if not self._get_cookies('https://www.floatplane.com').get('sails.sid'):
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
self.raise_login_required()
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
'https://www.floatplane.com/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data')
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], 'https://www.floatplane.com/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'https://www.floatplane.com/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata')
stream = self._download_json(
'https://www.floatplane.com/api/v2/cdn/delivery', media_id, query={
'type': 'vod' if media_typ == 'video' else 'aod',
'guid': metadata['guid'],
}, note=f'Downloading {media_typ} stream data')
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
formats = []
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
url = urljoin(stream['cdn'], format_path(traverse_obj(
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
formats.append({
**traverse_obj(quality, {
'format_id': ('name', {str}),
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'

View File

@@ -1,9 +1,7 @@
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
url_or_none,
)
@@ -58,16 +56,7 @@ class FrancaisFacileIE(InfoExtractor):
def _real_extract(self, url):
display_id = urllib.parse.unquote(self._match_id(url))
try: # yt-dlp's default user-agents are too old and blocked by the site
webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient
webpage = self._download_webpage(url, display_id, impersonate=True)
webpage = self._download_webpage(url, display_id)
data = self._search_json(
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',

View File

@@ -1,4 +1,3 @@
import json
import re
import urllib.parse
@@ -19,7 +18,11 @@
unsmuggle_url,
url_or_none,
)
from ..utils.traversal import find_element, traverse_obj
from ..utils.traversal import (
find_element,
get_first,
traverse_obj,
)
class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -121,9 +124,10 @@ def _extract_video(self, video_id, hostname=None):
elif code := traverse_obj(dinfo, ('code', {int})):
if code == 2009:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
elif code in (2015, 2017):
elif code in (2015, 2017, 2019):
# 2015: L'accès à cette vidéo est impossible. (DRM-only)
# 2017: Cette vidéo n'est pas disponible depuis le site web mobile (b/c DRM)
# 2019: L'accès à cette vidéo est incompatible avec votre configuration. (DRM-only)
drm_formats = True
continue
self.report_warning(
@@ -258,7 +262,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
_TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': {
'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', # old: c5bda21d-2c6f-4470-8849-3d8327adb2ba'
'id': 'b2cf9fd8-e971-4757-8651-848f2772df61', # old: ec217ecc-0733-48cf-ac06-af1347b849d1
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'timestamp': 1502623500,
@@ -269,7 +273,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
'skip': 'Unfortunately, this video is no longer available',
}, {
# geo-restricted
'url': 'https://www.france.tv/enfants/six-huit-ans/foot2rue/saison-1/3066387-duel-au-vieux-port.html',
@@ -287,7 +291,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1441,
},
'skip': 'No longer available',
'skip': 'Unfortunately, this video is no longer available',
}, {
# geo-restricted livestream (workflow == 'token-akamai')
'url': 'https://www.france.tv/france-4/direct.html',
@@ -308,6 +312,19 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'live_status': 'is_live',
},
'params': {'skip_download': 'livestream'},
}, {
# Not geo-restricted
'url': 'https://www.france.tv/france-2/la-maison-des-maternelles/5574051-nous-sommes-amis-et-nous-avons-fait-un-enfant-ensemble.html',
'info_dict': {
'id': 'b448bfe4-9fe7-11ee-97d8-2ba3426fa3df',
'ext': 'mp4',
'title': 'Nous sommes amis et nous avons fait un enfant ensemble - Émission du jeudi 21 décembre 2023',
'duration': 1065,
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1703147921,
'upload_date': '20231221',
},
'params': {'skip_download': 'm3u8'},
}, {
# france3
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
@@ -342,30 +359,16 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'only_matching': True,
}]
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.goplay
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
nextjs_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {json.loads}, ..., {self._find_json}, ..., 'children', ..., ..., 'children', ..., ..., 'children'))
if traverse_obj(nextjs_data, (..., ..., 'children', ..., 'isLive', {bool}, any)):
if get_first(nextjs_data, ('isLive', {bool})):
# For livestreams we need the id of the stream instead of the currently airing episode id
video_id = traverse_obj(nextjs_data, (
..., ..., 'children', ..., 'children', ..., 'children', ..., 'children', ..., ...,
'children', ..., ..., 'children', ..., ..., 'children', (..., (..., ...)),
'options', 'id', {str}, any))
video_id = get_first(nextjs_data, ('options', 'id', {str}))
else:
video_id = traverse_obj(nextjs_data, (
..., ..., ..., 'children',
lambda _, v: v['video']['url'] == urllib.parse.urlparse(url).path,
'video', ('playerReplayId', 'siId'), {str}, any))
video_id = get_first(nextjs_data, ('video', ('playerReplayId', 'siId'), {str}))
if not video_id:
raise ExtractorError('Unable to extract video ID')

File diff suppressed because it is too large Load Diff

View File

@@ -112,16 +112,17 @@ class GlomexIE(GlomexBaseIE):
_TESTS = [{
'url': 'https://video.glomex.com/sport/v-cb24uwg77hgh-nach-2-0-sieg-guardiola-mit-mancity-vor-naechstem-titel',
'md5': 'cec33a943c4240c9cb33abea8c26242e',
'info_dict': {
'id': 'v-cb24uwg77hgh',
'ext': 'mp4',
'title': 'md5:38a90cedcfadd72982c81acf13556e0c',
'title': 'Nach 2:0-Sieg: Guardiola mit ManCity vor nächstem Titel',
'description': 'md5:1ea6b6caff1443fcbbba159e432eedb8',
'duration': 29600,
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1619895017,
'upload_date': '20210501',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
@@ -140,16 +141,17 @@ class GlomexEmbedIE(GlomexBaseIE):
_TESTS = [{
'url': 'https://player.glomex.com/integration/1/iframe-player.html?integrationId=4059a013k56vb2yd&playlistId=v-cfa6lye0dkdd-sf',
'md5': '68f259b98cc01918ac34180142fce287',
'info_dict': {
'id': 'v-cfa6lye0dkdd-sf',
'ext': 'mp4',
'title': 'Φώφη Γεννηματά: Ο επικήδειος λόγος του 17χρονου γιου της, Γιώργου',
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1635337199,
'duration': 133080,
'upload_date': '20211027',
'description': 'md5:e741185fc309310ff5d0c789b437be66',
'title': 'md5:35647293513a6c92363817a0fb0a7961',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://player.glomex.com/integration/1/iframe-player.html?origin=fullpage&integrationId=19syy24xjn1oqlpc&playlistId=rl-vcb49w1fb592p&playlistIndex=0',
'info_dict': {
@@ -157,12 +159,27 @@ class GlomexEmbedIE(GlomexBaseIE):
},
'playlist_count': 100,
}, {
# Geo-restricted
'url': 'https://player.glomex.com/integration/1/iframe-player.html?playlistId=cl-bgqaata6aw8x&integrationId=19syy24xjn1oqlpc',
'info_dict': {
'id': 'cl-bgqaata6aw8x',
},
'playlist_mincount': 2,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.skai.gr/news/world/iatrikos-syllogos-tourkias-to-turkovac-aplo-dialyma-erntogan-eiste-apateones-kai-pseytes',
'info_dict': {
'id': 'v-ch2nkhcirwc9-sf',
'ext': 'mp4',
'title': 'Ιατρικός Σύλλογος Τουρκίας: Το Turkovac είναι ένα απλό διάλυμα –Ερντογάν: Είστε απατεώνες και ψεύτες',
'description': 'md5:8b517a61d577efe7e36fde72fd535995',
'duration': 460000,
'thumbnail': r're:https?://i[a-z0-9]thumbs\.glomex\.com/.+',
'timestamp': 1641885019,
'upload_date': '20220111',
},
'params': {'skip_download': 'm3u8'},
}]
@classmethod
def build_player_url(cls, video_id, integration, origin_url=None):

View File

@@ -7,161 +7,157 @@
int_or_none,
join_nonempty,
parse_age_limit,
remove_end,
remove_start,
traverse_obj,
try_get,
unified_timestamp,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
'requestor_id': 'ABC',
'requestor_id': 'dtci',
'provider_id': 'ABC',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI4OTcwMjlkYS0yYjM1LTQyOWUtYWQ0NS02ZjZiZjVkZTdhOTUiLCJuYmYiOjE2MjAxNzM5NjksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNjIwMTczOTY5fQ.SC69DVJWSL8sIe-vVUrP6xS_kzHKqwz9PdKYexs_y-f7Vin6mM-7S-W1TE_-K55O0pyf-TL4xYgvm6LIye8CckG-nZfVwNPV4huduov0jmIcxCQFeUwkHULG2IaA44wfBVUBdaHgkhPweZ2amjycO_IXtez-gBXOLbE3B7Gx9j_5ISCFtyVUblThKfoGyQv6KT6t8Vpmc4ZSKCCQp74KWFFypydb9ucego1taW_nQD06Cdf4yByLd6NaTBceMcIKbug9b9gxFm3XBgJ5q3z7KGo1Kr6XalAV5j4m-fQ91wczlTilX8FM4AljMupyRM9mA_aEADILQ4hS79q4SM0w6w',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
},
'watchdisneychannel': {
'brand': '004',
'resource_id': 'Disney',
},
'watchdisneyjunior': {
'brand': '008',
'resource_id': 'DisneyJunior',
},
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
'provider_id': 'ABCFamily',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhZWM2MGYyNC0xYzRjLTQ1NzQtYjc0Zi03ZmM4N2E5YWMzMzgiLCJuYmYiOjE1ODc2NjU5MjMsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NjY1OTIzfQ.flCn3dhvmvPnWmV0JV8Fm0YFyj07yPez9-n1GFEwVIm_S2wQVWbWyJhqsAyLZVFrhOMZYTqmPS3OHxGwTwXkEYn6PD7o_vIVG3oqi-Xn1m5jRt_Gazw5qEtpat6VE7bvKGSD3ZhcidOrsCk8NcYyq75u61NHDvSl81pcedJjVRVUpsqrEwmo0aVbA0C8PX3ri0mEbGvkMKvHn8E60xp-PSE-VK8SDT0plwPu_TwUszkZ6-_I8_2xcv_WBqcXFkAVg7Q-iNJXgQvmNsrpcrYuLvi6hEH4ZLtoDcXU6MhwTQAJTiHSo8x9aHX1_qFP09CzlNOFQbC2ZEJdP9SvA53SLQ',
},
'disneynow': {
'brand': '011',
'brand': '011', # also: '004', '008', '009'
'requestor_id': 'DisneyChannels',
'provider_id': 'DisneyChannels',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzAzNTRiOS04NDNiLTRkNjAtYTQ3ZS0yNzk1MzlkOTIyNTciLCJuYmYiOjE1NTg5ODc0NDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTU4OTg3NDQ5fQ.Jud6YS6-J2h0h6po0oMheDym0qRTJQGj4kzacrz4DFuEwhcBkkykW6pF5pKuAUJy9HCZ40oDAHe2KcTlDJjCZF5tDaUEfdihakZ9cC_rG7MU-QoRne8qaB_dPDKwGuk-ZyWD8eV3zwTJmbGo8hDxYTEU81YNCxwhyc_BPDr5TYiubbmpP3_pTnXmSpuL58isJ2peSKWlX9BacuXtBY25c_QnPFKk-_EETm7IHkTpDazde1QfHWGu4s4yJpKGk8RVVujVG6h6ELlL-ZeYLilBm7iS7h1TYG1u7fJhyZRL7isaom6NvAzsvN3ngss1fLwt8decP8wzdFHrbYTdTjW8qw',
'resource_id': 'Disney',
},
'fxnow.fxnetworks': {
'brand': '025',
'fxnetworks': {
'brand': '025', # also: '020'
'requestor_id': 'dtci',
'provider_id': 'fx', # also 'fxx', 'fxm'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIzYWRhYWZiNC02OTAxLTRlYzktOTdmNy1lYWZkZTJkODJkN2EiLCJuYmYiOjE1NjIwMjQwNzYsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDI0MDc2fQ.dhKMpZK50AObbZYrMiYPSfWtzXHUaeMP3jrIY4Cgfvh0GaEgk0Mns_zp78jypFeZgRtPVleQMQDNq2YEloRLcAGqP1aa6WVDglnK77ZWUm4IKai14Rwf3A6YBhSRoO2_lMmUGkuTf6gZY-kMIPqBYKqzTQiQl4HbniPFodIzFRiuI9QJVrkoyTGrJL4oqiX08PoFI3Z-TOti1Heu3EbFC-GveQHhlinYrzU7rbiAqLEz7FImtfBDsnXX1Y3uJDLYM3Bq4Oh0nrzTv1Fd62wNsCNErHHIbELidh1zZF0ujvt7ReuZUwAitm0UhEJ7OxNOUbEQWtae6pVNscvdvTFMpg',
},
'nationalgeographic': {
'brand': '026', # also '023'
'requestor_id': 'dtci',
'provider_id': 'ngc', # also 'ngw'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxMzE4YTM1Ni05Mjc4LTQ4NjEtYTFmNi1jMTIzMzg1ZWMzYzMiLCJuYmYiOjE1NjIwMjM4MjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDIzODI4fQ.Le-2OzF9-jrhJ7ZfWtLWk5iSHGVZoxeU1w0_fO--Heli0OwRZsRq2slSmx-oZTzxuWmAgDEiBkWSDcDK6sM25DrCLsdsJa3MBuZ-slBRtH8aq3HpNoqqLkU-vg6gRUEKMtwBUtwCu_9aKUCayYtndWv4b1DjVQeSrteOW5NNudWVYleAe0kxeNJQHo5If9SCzDudKVJktFUjhNks4QPOC_uONPkRRlL9D0fNvtOY-LRFckfcHhf5z9l1iZjeukV0YhdKnuw1wyiaWrQXBUDiBfbkCRd2DM-KnelqPxfiXCaTjGKDURRBO3pz33ebge3IFXSiU5vl4qHQ8xvunzGpFw',
},
}
_VALID_URL = r'''(?x)
https?://
(?P<sub_domain>
(?:{}\.)?go|fxnow\.fxnetworks|
(?:www\.)?(?:abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
'''.format(r'\.|'.join(list(_SITE_INFO.keys())))
_URL_PATH_RE = r'(?:video|episode|movies-and-specials)/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_VALID_URL = [
fr'https?://(?:www\.)?(?P<site>abc)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>freeform)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>disneynow)\.com/{_URL_PATH_RE}',
fr'https?://fxnow\.(?P<site>fxnetworks)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>nationalgeographic)\.com/tv/{_URL_PATH_RE}',
]
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'url': 'https://abc.com/episode/4192c0e6-26e5-47a8-817b-ce8272b9e440/playlist/PL551127435',
'info_dict': {
'id': 'VDKA3807643',
'id': 'VDKA10805898',
'ext': 'mp4',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'This content is no longer available.',
}, {
'url': 'https://disneynow.com/shows/big-hero-6-the-series',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'title': 'Switch the Flip',
'description': 'To help get Brians life in order, Stewie and Brian swap bodies using a machine that Stewie invents.',
'age_limit': 14,
'duration': 1297,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Family Guy',
'season': 'Season 16',
'season_number': 16,
'episode': 'Episode 17',
'episode_number': 17,
'timestamp': 1746082800.0,
'upload_date': '20250501',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://disneynow.com/episode/21029660-ba06-4406-adb0-a9a78f6e265e/playlist/PL553044961',
'info_dict': {
'id': 'VDKA39546942',
'ext': 'mp4',
'title': 'Zero Friends Again',
'description': 'Relationships fray under the pressures of a difficult journey.',
'age_limit': 0,
'duration': 1721,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Star Wars: Skeleton Crew',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 6',
'episode_number': 6,
'timestamp': 1746946800.0,
'upload_date': '20250511',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://fxnow.fxnetworks.com/episode/09f4fa6f-c293-469e-aebe-32c9ca5842a7/playlist/PL554408064',
'info_dict': {
'id': 'VDKA38112033',
'ext': 'mp4',
'title': 'The Return of Jerry',
'description': 'The vampires long-lost fifth roommate returns. Written by Paul Simms; directed by Kyle Newacheck.',
'age_limit': 17,
'duration': 1493,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'What We Do in the Shadows',
'season': 'Season 6',
'season_number': 6,
'episode': 'Episode 1',
'upload_date': '20170102',
'season': 'Season 2',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
'duration': 2544,
'season_number': 2,
'series': 'Shadowhunters',
'episode_number': 1,
'timestamp': 1483387200,
'ext': 'mp4',
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'timestamp': 1729573200.0,
'upload_date': '20241022',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
'url': 'https://www.freeform.com/episode/bda0eaf7-761a-4838-aa44-96f794000844/playlist/PL553044961',
'info_dict': {
'id': 'VDKA26050359',
'title': 'The Knock',
'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
'age_limit': 14,
'id': 'VDKA39007340',
'ext': 'mp4',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
'episode': 'Episode 12',
'season_number': 4,
'season': 'Season 4',
'timestamp': 1642975200,
'episode_number': 12,
'upload_date': '20220123',
'series': 'The Rookie',
'duration': 2572,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Angel\'s Landing',
'description': 'md5:91bf084e785c968fab16734df7313446',
'age_limit': 14,
'duration': 2523,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'How I Escaped My Cult',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'timestamp': 1740038400.0,
'upload_date': '20250220',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
'url': 'https://www.nationalgeographic.com/tv/episode/ca694661-1186-41ae-8089-82f64d69b16d/playlist/PL554408064',
'info_dict': {
'id': 'VDKA12782841',
'title': 'First Look: Better Things - Season 2',
'description': 'md5:fa73584a95761c605d9d54904e35b407',
'id': 'VDKA39492078',
'ext': 'mp4',
'age_limit': 14,
'upload_date': '20170825',
'duration': 161,
'series': 'Better Things',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
'timestamp': 1503661074,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Heart of the Emperors',
'description': 'md5:4fc50a2878f030bb3a7eac9124dca677',
'age_limit': 0,
'duration': 2775,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Secrets of the Penguins',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
'timestamp': 1745204400.0,
'upload_date': '20250421',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'url': 'https://www.freeform.com/movies-and-specials/c38281fc-9f8f-47c7-8220-22394f9df2e1',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
'only_matching': True,
}, {
# brand 004
'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
'only_matching': True,
}, {
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
'url': 'https://abc.com/video/219a454a-172c-41bf-878a-d169e6bc0bdc/playlist/PL5523098420',
'only_matching': True,
}]
@@ -171,58 +167,29 @@ def _extract_videos(self, brand, video_id='-1', show_id='-1'):
f'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/{brand}/001/-1/{show_id}/-1/{video_id}/-1/-1.json',
display_id)['video']
def _extract_global_var(self, name, webpage, video_id):
return self._search_json(
fr'window\[["\']{re.escape(name)}["\']\]\s*=',
webpage, f'{name.strip("_")} JSON', video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
data = self._parse_json(
self._search_regex(
r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
'data', default='{}'),
display_id or video_id, fatal=False)
# https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
video_id = None
if layout:
video_id = try_get(
layout,
(lambda x: x['videoid'], lambda x: x['video']['id']),
str)
if not video_id:
video_id = self._search_regex(
(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)',
# page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)',
), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
default='004')
site_info = next(
si for _, si in self._SITE_INFO.items()
if si.get('brand') == brand)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
config = self._extract_global_var('__CONFIG__', webpage, display_id)
data = self._extract_global_var(config['globalVar'], webpage, display_id)
video_id = traverse_obj(data, (
'page', 'content', 'video', 'layout', (('video', 'id'), 'videoid'), {str}, any))
if not video_id:
video_id = self._search_regex([
# data-track-video_id="VDKA39492078"
# data-track-video_id_code="vdka39492078"
# data-video-id="'VDKA3609139'"
r'data-(?:track-)?video[_-]id(?:_code)?=["\']*((?:vdka|VDKA)\d+)',
# page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\d+)'], webpage, 'video ID')
site_info = self._SITE_INFO[site]
brand = site_info['brand']
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
@@ -238,26 +205,31 @@ def _real_extract(self, url):
if ext == 'm3u8':
video_type = video_data.get('type')
data = {
'video_id': video_data['id'],
'video_id': video_id,
'video_type': video_type,
'brand': brand,
'device': '001',
'app_name': 'webplayer-abc',
}
if video_data.get('accesslevel') == '1':
requestor_id = site_info.get('requestor_id', 'DisneyChannels')
provider_id = site_info['provider_id']
software_statement = traverse_obj(data, ('app', 'config', (
('features', 'auth', 'softwareStatement'),
('tvAuth', 'SOFTWARE_STATEMENTS', 'PRODUCTION'),
), {str}, any)) or site_info['software_statement']
resource = site_info.get('resource_id') or self._get_mvpd_resource(
requestor_id, title, video_id, None)
provider_id, title, video_id, None)
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, site_info['requestor_id'], resource, software_statement)
data.update({
'token': auth,
'token_type': 'ap',
'adobe_requestor_id': requestor_id,
'adobe_requestor_id': provider_id,
})
else:
self._initialize_geo_bypass({'countries': ['US']})
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
'https://prod.gatekeeper.us-abc.symphony.edgedatg.go.com/vp2/ws-secure/entitlement/2020/playmanifest_secure.json',
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
@@ -267,7 +239,7 @@ def _real_extract(self, url):
error['message'], countries=['US'])
error_message = ', '.join([error['message'] for error in errors])
raise ExtractorError(f'{self.IE_NAME} said: {error_message}', expected=True)
asset_url += '?' + entitlement['uplynkData']['sessionKey']
asset_url += '?' + entitlement['entitlement']['uplynkData']['sessionKey']
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
formats.extend(fmts)

View File

@@ -5,16 +5,11 @@
import hmac
import json
import os
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
remove_end,
traverse_obj,
)
from ..utils import ExtractorError, int_or_none
from ..utils.traversal import get_first, traverse_obj
class GoPlayIE(InfoExtractor):
@@ -27,10 +22,10 @@ class GoPlayIE(InfoExtractor):
'info_dict': {
'id': '2baa4560-87a0-421b-bffc-359914e3c387',
'ext': 'mp4',
'title': 'S22 - Aflevering 1',
'title': 'De Slimste Mens ter Wereld - S22 - Aflevering 1',
'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
'series': 'De Slimste Mens ter Wereld',
'episode': 'Episode 1',
'episode': 'Wordt aangekondigd',
'season_number': 22,
'episode_number': 1,
'season': 'Season 22',
@@ -52,7 +47,7 @@ class GoPlayIE(InfoExtractor):
'info_dict': {
'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
'ext': 'mp4',
'title': 'S11 - Aflevering 1',
'title': 'De Mol - S11 - Aflevering 1',
'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
'episode': 'Episode 1',
'series': 'De Mol',
@@ -75,21 +70,13 @@ def _real_initialize(self):
if not self._id_token:
raise self.raise_login_required(method='password')
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.francetv
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {json.loads}, ..., {self._find_json}, ...))
meta = traverse_obj(nextjs_data, (
..., ..., 'children', ..., ..., 'children',
lambda _, v: v['video']['path'] == urllib.parse.urlparse(url).path, 'video', any))
nextjs_data = self._search_nextjs_v13_data(webpage, display_id)
meta = get_first(nextjs_data, (
lambda k, v: k in ('video', 'meta') and v['path'] == urllib.parse.urlparse(url).path))
video_id = meta['uuid']
info_dict = traverse_obj(meta, {
@@ -98,19 +85,18 @@ def _real_extract(self, url):
})
if traverse_obj(meta, ('program', 'subtype')) != 'movie':
for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
episode_data = traverse_obj(
season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
for season_data in traverse_obj(nextjs_data, (..., 'playlists', ..., {dict})):
episode_data = traverse_obj(season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
if not episode_data:
continue
episode_title = traverse_obj(
episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
season_number = traverse_obj(season_data, ('season', {int_or_none}))
info_dict.update({
'title': episode_title or info_dict.get('title'),
'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
'season_number': traverse_obj(season_data, ('season', {int_or_none})),
'episode': traverse_obj(episode_data, ('episodeTitle', {str})),
'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
'season_number': season_number,
'series': self._search_regex(
fr'^(.+)? - S{season_number} - ', info_dict.get('title'), 'series', default=None),
})
break

View File

@@ -1,3 +1,4 @@
import functools
import hashlib
import hmac
import json
@@ -9,77 +10,126 @@
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
filter_dict,
int_or_none,
join_nonempty,
jwt_decode_hs256,
parse_iso8601,
str_or_none,
traverse_obj,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class HotStarBaseIE(InfoExtractor):
_TOKEN_NAME = 'userUP'
_BASE_URL = 'https://www.hotstar.com'
_API_URL = 'https://api.hotstar.com'
_API_URL_V2 = 'https://apix.hotstar.com/v2'
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
_FREE_HEADERS = {
'user-agent': 'Hotstar;in.startv.hotstar/25.06.30.0.11580 (Android/12)',
'x-hs-client': 'platform:android;app_id:in.startv.hotstar;app_version:25.06.30.0;os:Android;os_version:12;schema_version:0.0.1523',
'x-hs-platform': 'android',
}
_SUB_HEADERS = {
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
'x-hs-client': 'platform:androidtv;app_id:in.startv.hotstar.dplus.tv;app_version:23.08.14.4;os:Android;os_version:13;schema_version:0.0.970',
'x-hs-platform': 'androidtv',
}
def _has_active_subscription(self, cookies, server_time):
server_time = int_or_none(server_time) or int(time.time())
expiry = traverse_obj(cookies, (
self._TOKEN_NAME, 'value', {jwt_decode_hs256}, 'sub', {json.loads},
'subscriptions', 'in', ..., 'expiry', {parse_iso8601}, all, {max})) or 0
return expiry > server_time
def _call_api_v1(self, path, *args, **kwargs):
return self._download_json(
f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
def _call_api_impl(self, path, video_id, query, cookies=None, st=None):
st = int_or_none(st) or int(time.time())
exp = st + 6000
auth = f'st={st}~exp={exp}~acl=/*'
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
if cookies and cookies.get('userUP'):
token = cookies.get('userUP').value
else:
token = self._download_json(
f'{self._API_URL}/um/v3/users',
video_id, note='Downloading token',
data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
headers={
'hotstarauth': auth,
'x-hs-platform': 'PCTV', # or 'web'
'Content-Type': 'application/json',
})['user_identity']
response = self._download_json(
f'{self._API_URL}/{path}', video_id, query=query,
headers={
f'{self._API_URL_V2}/{path}', video_id, query=query,
headers=filter_dict({
**(self._SUB_HEADERS if self._has_active_subscription(cookies, st) else self._FREE_HEADERS),
'hotstarauth': auth,
'x-hs-appversion': '6.72.2',
'x-hs-platform': 'web',
'x-hs-usertoken': token,
})
'x-hs-usertoken': traverse_obj(cookies, (self._TOKEN_NAME, 'value')),
'x-hs-device-id': traverse_obj(cookies, ('deviceId', 'value')) or str(uuid.uuid4()),
'content-type': 'application/json',
}))
if response['message'] != "Playback URL's fetched successfully":
raise ExtractorError(
response['message'], expected=True)
return response['data']
if not traverse_obj(response, ('success', {dict})):
raise ExtractorError('API call was unsuccessful')
return response['success']
def _call_api_v2(self, path, video_id, st=None, cookies=None):
return self._call_api_impl(
f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
'os-name': 'Windows',
'os-version': '10',
})
def _call_api_v2(self, path, video_id, content_type, cookies=None, st=None):
return self._call_api_impl(f'{path}', video_id, query={
'content_id': video_id,
'filters': f'content_type={content_type}',
'client_capabilities': json.dumps({
'package': ['dash', 'hls'],
'container': ['fmp4', 'fmp4br', 'ts'],
'ads': ['non_ssai', 'ssai'],
'audio_channel': ['stereo', 'dolby51', 'atmos'],
'encryption': ['plain', 'widevine'], # wv only so we can raise appropriate error
'video_codec': ['h264', 'h265'],
'video_codec_non_secure': ['h264', 'h265', 'vp9'],
'ladder': ['phone', 'tv', 'full'],
'resolution': ['hd', '4k'],
'true_resolution': ['hd', '4k'],
'dynamic_range': ['sdr', 'hdr'],
}, separators=(',', ':')),
'drm_parameters': json.dumps({
'widevine_security_level': ['SW_SECURE_DECODE', 'SW_SECURE_CRYPTO'],
'hdcp_version': ['HDCP_V2_2', 'HDCP_V2_1', 'HDCP_V2', 'HDCP_V1'],
}, separators=(',', ':')),
}, cookies=cookies, st=st)
def _playlist_entries(self, path, item_id, root=None, **kwargs):
results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', ...)):
if video.get('contentId'):
yield self.url_result(
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
@staticmethod
def _parse_metadata_v1(video_data):
return traverse_obj(video_data, {
'id': ('contentId', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': (('broadcastDate', 'startDate'), {int_or_none}, any),
'release_year': ('year', {int_or_none}),
'channel': ('channelName', {str}),
'channel_id': ('channelId', {int}, {str_or_none}),
'series': ('showName', {str}),
'season': ('seasonName', {str}),
'season_number': ('seasonNo', {int_or_none}),
'season_id': ('seasonId', {int}, {str_or_none}),
'episode': ('title', {str}),
'episode_number': ('episodeNo', {int_or_none}),
})
def _fetch_page(self, path, item_id, name, query, root, page):
results = self._call_api_v1(
path, item_id, note=f'Downloading {name} page {page + 1} JSON', query={
**query,
'tao': page * self._PAGE_SIZE,
'tas': self._PAGE_SIZE,
})['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', lambda _, v: v['contentId'])):
yield self.url_result(
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
class HotStarIE(HotStarBaseIE):
IE_NAME = 'hotstar'
IE_DESC = 'JioHotstar'
_VALID_URL = r'''(?x)
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
(?:
@@ -114,15 +164,16 @@ class HotStarIE(HotStarBaseIE):
'upload_date': '20190501',
'duration': 1219,
'channel': 'StarPlus',
'channel_id': '3',
'channel_id': '821',
'series': 'Ek Bhram - Sarvagun Sampanna',
'season': 'Chapter 1',
'season_number': 1,
'season_id': '6771',
'season_id': '1260004607',
'episode': 'Janhvi Targets Suman',
'episode_number': 8,
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
'info_dict': {
'id': '1000282843',
@@ -134,14 +185,14 @@ class HotStarIE(HotStarBaseIE):
'channel': 'StarPlus',
'series': 'Anupama',
'season_number': 1,
'season_id': '7399',
'season_id': '1260022018',
'upload_date': '20230307',
'episode': 'Anupama, Anuj Share a Moment',
'episode_number': 853,
'duration': 1272,
'channel_id': '3',
'duration': 1266,
'channel_id': '821',
},
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
'info_dict': {
@@ -154,14 +205,15 @@ class HotStarIE(HotStarBaseIE):
'channel': 'Hotstar Specials',
'series': 'Kana Kaanum Kaalangal',
'season_number': 1,
'season_id': '9441',
'season_id': '1260097089',
'upload_date': '20220421',
'episode': 'Back To School',
'episode_number': 1,
'duration': 1810,
'channel_id': '54',
'channel_id': '1260003991',
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
'info_dict': {
'id': '1000262286',
@@ -173,6 +225,7 @@ class HotStarIE(HotStarBaseIE):
'timestamp': 1622943900,
'duration': 5395,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
'info_dict': {
@@ -180,12 +233,13 @@ class HotStarIE(HotStarBaseIE):
'ext': 'mp4',
'title': 'Premam',
'release_year': 2015,
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
'timestamp': 1462149000,
'upload_date': '20160502',
'episode': 'Premam',
'duration': 8994,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
'only_matching': True,
@@ -208,6 +262,13 @@ class HotStarIE(HotStarBaseIE):
None: 'content',
}
_CONTENT_TYPE = {
'movie': 'MOVIE',
'episode': 'EPISODE',
'match': 'SPORT',
'content': 'CLIPS',
}
_IGNORE_MAP = {
'res': 'resolution',
'vcodec': 'video_codec',
@@ -229,38 +290,50 @@ def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
video_type = self._TYPE.get(video_type, video_type)
video_type = self._TYPE[video_type]
cookies = self._get_cookies(url) # Cookies before any request
if not cookies or not cookies.get(self._TOKEN_NAME):
self.raise_login_required()
video_data = traverse_obj(
self._call_api_v1(
f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
('body', 'results', 'item', {dict})) or {}
if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
self._call_api_v1(f'{video_type}/detail', video_id, fatal=False, query={
'tas': 5, # See https://github.com/yt-dlp/yt-dlp/issues/7946
'contentId': video_id,
}), ('body', 'results', 'item', {dict})) or {}
if video_data.get('drmProtected'):
self.report_drm(video_id)
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
geo_restricted = False
formats, subs = [], {}
formats, subs, has_drm = [], {}, False
headers = {'Referer': f'{self._BASE_URL}/in'}
content_type = traverse_obj(video_data, ('contentType', {str})) or self._CONTENT_TYPE[video_type]
# change to v2 in the future
playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
for playback_set in playback_sets:
if not isinstance(playback_set, dict):
continue
tags = str_or_none(playback_set.get('tagsCombination')) or ''
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._request_webpage(
f'{self._BASE_URL}/in', video_id, 'Fetching server time').get_header('x-origin-date')
watch = self._call_api_v2('pages/watch', video_id, content_type, cookies, st)
player_config = traverse_obj(watch, (
'page', 'spaces', 'player', 'widget_wrappers', lambda _, v: v['template'] == 'PlayerWidget',
'widget', 'data', 'player_config', {dict}, any, {require('player config')}))
for playback_set in traverse_obj(player_config, (
('media_asset', 'media_asset_v2'),
('primary', 'fallback'),
all, lambda _, v: url_or_none(v['content_url']),
)):
tags = str_or_none(playback_set.get('playback_tags')) or ''
if any(f'{prefix}:{ignore}' in tags
for key, prefix in self._IGNORE_MAP.items()
for ignore in self._configuration_arg(key)):
continue
format_url = url_or_none(playback_set.get('playbackUrl'))
if not format_url:
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
has_drm = True
continue
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
ext = determine_ext(format_url)
current_formats, current_subs = [], {}
@@ -280,14 +353,12 @@ def _real_extract(self, url):
'height': int_or_none(playback_set.get('height')),
}]
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
geo_restricted = True
else:
self.write_debug(e)
continue
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
for f in current_formats:
f['has_drm'] = True
for f in current_formats:
for k, v in self._TAG_FIELDS.items():
if not f.get(k):
@@ -299,6 +370,11 @@ def _real_extract(self, url):
'stereo': 2,
'dolby51': 6,
}.get(tag_dict.get('audio_channel'))
if (
'Audio_Description' in f['format_id']
or 'Audio Description' in (f.get('format_note') or '')
):
f['source_preference'] = -99 + (f.get('source_preference') or -1)
f['format_note'] = join_nonempty(
tag_dict.get('ladder'),
tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
@@ -308,29 +384,22 @@ def _real_extract(self, url):
formats.extend(current_formats)
subs = self._merge_subtitles(subs, current_subs)
if not formats and geo_restricted:
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
if not formats:
if geo_restricted:
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
elif has_drm:
self.report_drm(video_id)
elif not self._has_active_subscription(cookies, st):
self.raise_no_formats('Your account does not have access to this content', expected=True)
self._remove_duplicate_formats(formats)
for f in formats:
f.setdefault('http_headers', {}).update(headers)
return {
**self._parse_metadata_v1(video_data),
'id': video_id,
'title': video_data.get('title'),
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
'release_year': int_or_none(video_data.get('year')),
'formats': formats,
'subtitles': subs,
'channel': video_data.get('channelName'),
'channel_id': str_or_none(video_data.get('channelId')),
'series': video_data.get('showName'),
'season': video_data.get('seasonName'),
'season_number': int_or_none(video_data.get('seasonNo')),
'season_id': str_or_none(video_data.get('seasonId')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episodeNo')),
}
@@ -371,64 +440,6 @@ def _real_extract(self, url):
return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
class HotStarPlaylistIE(HotStarBaseIE):
IE_NAME = 'hotstar:playlist'
_VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'info_dict': {
'id': '3_2_26',
},
'playlist_mincount': 20,
}, {
'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
'only_matching': True,
}]
def _real_extract(self, url):
id_ = self._match_id(url)
return self.playlist_result(
self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
class HotStarSeasonIE(HotStarBaseIE):
IE_NAME = 'hotstar:season'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
'info_dict': {
'id': '8028',
},
'playlist_mincount': 35,
}, {
'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
'info_dict': {
'id': '4357',
},
'playlist_mincount': 30,
}, {
'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
'info_dict': {
'id': '8208',
},
'playlist_mincount': 19,
}, {
'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
'only_matching': True,
}]
def _real_extract(self, url):
url, season_id = self._match_valid_url(url).groups()
return self.playlist_result(self._playlist_entries(
'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
class HotStarSeriesIE(HotStarBaseIE):
IE_NAME = 'hotstar:series'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
@@ -443,25 +454,29 @@ class HotStarSeriesIE(HotStarBaseIE):
'info_dict': {
'id': '1260050431',
},
'playlist_mincount': 43,
'playlist_mincount': 42,
}, {
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
'info_dict': {
'id': '435',
},
'playlist_mincount': 267,
}, {
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
'info_dict': {
'id': '1260022017',
},
'playlist_mincount': 940,
'playlist_mincount': 1601,
}]
_PAGE_SIZE = 100
def _real_extract(self, url):
url, series_id = self._match_valid_url(url).groups()
id_ = self._call_api_v1(
url, series_id = self._match_valid_url(url).group('url', 'id')
eid = self._call_api_v1(
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
return self.playlist_result(self._playlist_entries(
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, 'tray/g/1/items', series_id,
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
return self.playlist_result(entries, series_id)

View File

@@ -7,12 +7,13 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
parse_duration,
str_or_none,
try_get,
unescapeHTML,
unified_strdate,
update_url,
update_url_query,
url_or_none,
)
@@ -22,8 +23,8 @@
class HuyaLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
IE_NAME = 'huya:live'
IE_DESC = 'huya.com'
TESTS = [{
IE_DESC = '虎牙直播'
_TESTS = [{
'url': 'https://www.huya.com/572329',
'info_dict': {
'id': '572329',
@@ -149,63 +150,94 @@ class HuyaVideoIE(InfoExtractor):
'id': '1002412640',
'ext': 'mp4',
'title': '8月3日',
'thumbnail': r're:https?://.*\.jpg',
'duration': 14,
'categories': ['主机游戏'],
'duration': 14.0,
'uploader': '虎牙-ATS欧卡车队青木',
'uploader_id': '1564376151',
'upload_date': '20240803',
'view_count': int,
'comment_count': int,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1722675433,
},
},
{
}, {
'url': 'https://www.huya.com/video/play/556054543.html',
'info_dict': {
'id': '556054543',
'ext': 'mp4',
'title': '我不挑事 也不怕事',
'thumbnail': r're:https?://.*\.jpg',
'duration': 1864,
'categories': ['英雄联盟'],
'description': 'md5:58184869687d18ce62dc7b4b2ad21201',
'duration': 1864.0,
'uploader': '卡尔',
'uploader_id': '367138632',
'upload_date': '20210811',
'view_count': int,
'comment_count': int,
'like_count': int,
'tags': 'count:4',
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1628675950,
},
}, {
# Only m3u8 available
'url': 'https://www.huya.com/video/play/1063345618.html',
'info_dict': {
'id': '1063345618',
'ext': 'mp4',
'title': '峡谷第一中黑铁上钻石顶级教学对抗elo',
'categories': ['英雄联盟'],
'comment_count': int,
'duration': 21603.0,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1749668803,
'upload_date': '20250611',
'uploader': '北枫CC',
'uploader_id': '2183525275',
'view_count': int,
},
}]
def _real_extract(self, url: str):
video_id = self._match_id(url)
video_data = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent', video_id,
query={'videoId': video_id})['data']['moment']['videoInfo']
moment = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent',
video_id, query={'videoId': video_id})['data']['moment']
formats = []
for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))):
formats.append({
'url': definition['url'],
**traverse_obj(definition, {
'format_id': ('defName', {str}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
for definition in traverse_obj(moment, (
'videoInfo', 'definitions', lambda _, v: url_or_none(v['m3u8']),
)):
fmts = self._extract_m3u8_formats(definition['m3u8'], video_id, 'mp4', fatal=False)
for fmt in fmts:
fmt.update(**traverse_obj(definition, {
'filesize': ('size', {int_or_none}),
}),
})
'format_id': ('defName', {str}),
'height': ('height', {int_or_none}),
'quality': ('definition', {int_or_none}),
'width': ('width', {int_or_none}),
}))
formats.extend(fmts)
return {
'id': video_id,
'formats': formats,
**traverse_obj(video_data, {
**traverse_obj(moment, {
'comment_count': ('commentCount', {int_or_none}),
'description': ('content', {clean_html}, filter),
'like_count': ('favorCount', {int_or_none}),
'timestamp': ('cTime', {int_or_none}),
}),
**traverse_obj(moment, ('videoInfo', {
'title': ('videoTitle', {str}),
'thumbnail': ('videoCover', {url_or_none}),
'categories': ('category', {str}, filter, all, filter),
'duration': ('videoDuration', {parse_duration}),
'tags': ('tags', ..., {str}, filter, all, filter),
'thumbnail': (('videoBigCover', 'videoCover'), {url_or_none}, {update_url(query=None)}, any),
'uploader': ('nickName', {str}),
'uploader_id': ('uid', {str_or_none}),
'upload_date': ('videoUploadTime', {unified_strdate}),
'view_count': ('videoPlayNum', {int_or_none}),
'comment_count': ('videoCommentNum', {int_or_none}),
'like_count': ('favorCount', {int_or_none}),
}),
})),
}

View File

@@ -1,32 +1,66 @@
from .common import InfoExtractor
from ..utils import js_to_json, traverse_obj
from ..utils import (
ExtractorError,
clean_html,
url_or_none,
)
from ..utils.traversal import subs_list_to_dict, traverse_obj
class MonsterSirenHypergryphMusicIE(InfoExtractor):
IE_NAME = 'monstersiren'
IE_DESC = '塞壬唱片'
_API_BASE = 'https://monster-siren.hypergryph.com/api'
_VALID_URL = r'https?://monster-siren\.hypergryph\.com/music/(?P<id>\d+)'
_TESTS = [{
'url': 'https://monster-siren.hypergryph.com/music/514562',
'info_dict': {
'id': '514562',
'ext': 'wav',
'artists': ['塞壬唱片-MSR'],
'album': 'Flame Shadow',
'title': 'Flame Shadow',
'album': 'Flame Shadow',
'artists': ['塞壬唱片-MSR'],
'description': 'md5:19e2acfcd1b65b41b29e8079ab948053',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}, {
'url': 'https://monster-siren.hypergryph.com/music/514518',
'info_dict': {
'id': '514518',
'ext': 'wav',
'title': 'Heavenly Me (Instrumental)',
'album': 'Heavenly Me',
'artists': ['塞壬唱片-MSR', 'AIYUE blessed : 理名'],
'description': 'md5:ce790b41c932d1ad72eb791d1d8ae598',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}]
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
json_data = self._search_json(
r'window\.g_initialProps\s*=', webpage, 'data', audio_id, transform_source=js_to_json)
song = self._download_json(f'{self._API_BASE}/song/{audio_id}', audio_id)
if traverse_obj(song, 'code') != 0:
msg = traverse_obj(song, ('msg', {str}, filter))
raise ExtractorError(
msg or 'API returned an error response', expected=bool(msg))
album = None
if album_id := traverse_obj(song, ('data', 'albumCid', {str})):
album = self._download_json(
f'{self._API_BASE}/album/{album_id}/detail', album_id, fatal=False)
return {
'id': audio_id,
'title': traverse_obj(json_data, ('player', 'songDetail', 'name')),
'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')),
'ext': 'wav',
'vcodec': 'none',
'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)),
'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')),
**traverse_obj(song, ('data', {
'title': ('name', {str}),
'artists': ('artists', ..., {str}),
'subtitles': ({'url': 'lyricUrl'}, all, {subs_list_to_dict(lang='en')}),
'url': ('sourceUrl', {url_or_none}),
})),
**traverse_obj(album, ('data', {
'album': ('name', {str}),
'description': ('intro', {clean_html}),
'thumbnail': ('coverUrl', {url_or_none}),
})),
}

View File

@@ -11,7 +11,6 @@
class IndavideoEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
# Some example URLs covered by generic extractor:
# https://indavideo.hu/video/Vicces_cica_1
# https://index.indavideo.hu/video/Hod_Nemetorszagban
# https://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
# https://film.indavideo.hu/video/f_farkaslesen
@@ -25,14 +24,14 @@ class IndavideoEmbedIE(InfoExtractor):
'ext': 'mp4',
'title': 'Cicatánc',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'cukiajanlo',
'uploader_id': '83729',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'timestamp': 1439193826,
'upload_date': '20150810',
'duration': 72,
'age_limit': 0,
'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
'tags': 'count:5',
},
}, {
'url': 'https://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
@@ -45,14 +44,30 @@ class IndavideoEmbedIE(InfoExtractor):
'ext': 'mp4',
'title': 'Vicces cica',
'description': 'Játszik a tablettel. :D',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'uploader': 'Jet_Pack',
'uploader_id': '491217',
'timestamp': 1390821212,
'upload_date': '20140127',
'duration': 7,
'age_limit': 0,
'tags': ['cica', 'Jet_Pack'],
'tags': 'count:2',
},
}, {
'url': 'https://palyazat.indavideo.hu/video/RUSH_1',
'info_dict': {
'id': '3808180',
'ext': 'mp4',
'title': 'RUSH',
'age_limit': 0,
'description': '',
'duration': 650,
'tags': 'count:2',
'thumbnail': r're:https?://pics\.indavideo\.hu/videos/.+\.jpg',
'timestamp': 1729136266,
'upload_date': '20241017',
'uploader': '7summerfilms',
'uploader_id': '1628496',
},
}]

View File

@@ -1,408 +0,0 @@
import base64
import itertools
import json
import random
import re
import string
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
jwt_decode_hs256,
parse_age_limit,
try_call,
url_or_none,
)
from ..utils.traversal import traverse_obj
class JioCinemaBaseIE(InfoExtractor):
_NETRC_MACHINE = 'jiocinema'
_GEO_BYPASS = False
_ACCESS_TOKEN = None
_REFRESH_TOKEN = None
_GUEST_TOKEN = None
_USER_ID = None
_DEVICE_ID = None
_API_HEADERS = {'Origin': 'https://www.jiocinema.com', 'Referer': 'https://www.jiocinema.com/'}
_APP_NAME = {'appName': 'RJIL_JioCinema'}
_APP_VERSION = {'appVersion': '5.0.0'}
_API_SIGNATURES = 'o668nxgzwff'
_METADATA_API_BASE = 'https://content-jiovoot.voot.com/psapi'
_ACCESS_HINT = 'the `accessToken` from your browser local storage'
_LOGIN_HINT = (
'Log in with "-u phone -p <PHONE_NUMBER>" to authenticate with OTP, '
f'or use "-u token -p <ACCESS_TOKEN>" to log in with {_ACCESS_HINT}. '
'If you have previously logged in with yt-dlp and your session '
'has been cached, you can use "-u device -p <DEVICE_ID>"')
def _cache_token(self, token_type):
assert token_type in ('access', 'refresh', 'all')
if token_type in ('access', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-access', JioCinemaBaseIE._ACCESS_TOKEN)
if token_type in ('refresh', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh', JioCinemaBaseIE._REFRESH_TOKEN)
def _call_api(self, url, video_id, note='Downloading API JSON', headers={}, data={}):
return self._download_json(
url, video_id, note, data=json.dumps(data, separators=(',', ':')).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
**self._API_HEADERS,
**headers,
}, expected_status=(400, 403, 474))
def _call_auth_api(self, service, endpoint, note, headers={}, data={}):
return self._call_api(
f'https://auth-jiocinema.voot.com/{service}service/apis/v4/{endpoint}',
None, note=note, headers=headers, data=data)
def _refresh_token(self):
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._DEVICE_ID:
raise ExtractorError('User token has expired', expected=True)
response = self._call_auth_api(
'token', 'refreshtoken', 'Refreshing token',
headers={'accesstoken': self._ACCESS_TOKEN}, data={
**self._APP_NAME,
'deviceId': self._DEVICE_ID,
'refreshToken': self._REFRESH_TOKEN,
**self._APP_VERSION,
})
refresh_token = response.get('refreshTokenId')
if refresh_token and refresh_token != JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
self._cache_token('refresh')
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
self._cache_token('access')
def _fetch_guest_token(self):
JioCinemaBaseIE._DEVICE_ID = ''.join(random.choices(string.digits, k=10))
guest_token = self._call_auth_api(
'token', 'guest', 'Downloading guest token', data={
**self._APP_NAME,
'deviceType': 'phone',
'os': 'ios',
'deviceId': self._DEVICE_ID,
'freshLaunch': False,
'adId': self._DEVICE_ID,
**self._APP_VERSION,
})
self._GUEST_TOKEN = guest_token['authToken']
self._USER_ID = guest_token['userId']
def _call_login_api(self, endpoint, guest_token, data, note):
return self._call_auth_api(
'user', f'loginotp/{endpoint}', note, headers={
**self.geo_verification_headers(),
'accesstoken': self._GUEST_TOKEN,
**self._APP_NAME,
**traverse_obj(guest_token, 'data', {
'deviceType': ('deviceType', {str}),
'os': ('os', {str}),
})}, data=data)
def _is_token_expired(self, token):
return (try_call(lambda: jwt_decode_hs256(token)['exp']) or 0) <= int(time.time() - 180)
def _perform_login(self, username, password):
if self._ACCESS_TOKEN and not self._is_token_expired(self._ACCESS_TOKEN):
return
UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
if username.lower() == 'token':
if try_call(lambda: jwt_decode_hs256(password)):
JioCinemaBaseIE._ACCESS_TOKEN = password
refresh_hint = 'the `refreshToken` UUID from your browser local storage'
refresh_token = self._configuration_arg('refresh_token', [''], ie_key=JioCinemaIE)[0]
if not refresh_token:
self.to_screen(
'To extend the life of your login session, in addition to your access token, '
'you can pass --extractor-args "jiocinema:refresh_token=REFRESH_TOKEN" '
f'where REFRESH_TOKEN is {refresh_hint}')
elif re.fullmatch(UUID_RE, refresh_token):
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
else:
self.report_warning(f'Invalid refresh_token value. Use {refresh_hint}')
else:
raise ExtractorError(
f'The password given could not be decoded as a token; use {self._ACCESS_HINT}', expected=True)
elif username.lower() == 'device' and re.fullmatch(rf'(?:{UUID_RE}|\d+)', password):
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-refresh')
JioCinemaBaseIE._ACCESS_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-access')
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._ACCESS_TOKEN:
raise ExtractorError(f'Failed to load cached tokens for device ID "{password}"', expected=True)
elif username.lower() == 'phone' and re.fullmatch(r'\+?\d+', password):
self._fetch_guest_token()
guest_token = jwt_decode_hs256(self._GUEST_TOKEN)
initial_data = {
'number': base64.b64encode(password.encode()).decode(),
**self._APP_VERSION,
}
response = self._call_login_api('send', guest_token, initial_data, 'Requesting OTP')
if not traverse_obj(response, ('OTPInfo', {dict})):
raise ExtractorError('There was a problem with the phone number login attempt')
is_iphone = guest_token.get('os') == 'ios'
response = self._call_login_api('verify', guest_token, {
'deviceInfo': {
'consumptionDeviceName': 'iPhone' if is_iphone else 'Android',
'info': {
'platform': {'name': 'iPhone OS' if is_iphone else 'Android'},
'androidId': self._DEVICE_ID,
'type': 'iOS' if is_iphone else 'Android',
},
},
**initial_data,
'otp': self._get_tfa_info('the one-time password sent to your phone'),
}, 'Submitting OTP')
if traverse_obj(response, 'code') == 1043:
raise ExtractorError('Wrong OTP', expected=True)
JioCinemaBaseIE._REFRESH_TOKEN = response['refreshToken']
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
else:
raise ExtractorError(self._LOGIN_HINT, expected=True)
user_token = jwt_decode_hs256(JioCinemaBaseIE._ACCESS_TOKEN)['data']
JioCinemaBaseIE._USER_ID = user_token['userId']
JioCinemaBaseIE._DEVICE_ID = user_token['deviceId']
if JioCinemaBaseIE._REFRESH_TOKEN and username != 'device':
self._cache_token('all')
if self.get_param('cachedir') is not False:
self.to_screen(
f'NOTE: For subsequent logins you can use "-u device -p {JioCinemaBaseIE._DEVICE_ID}"')
elif not JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh')
if JioCinemaBaseIE._REFRESH_TOKEN:
self._cache_token('access')
self.to_screen(f'Logging in as device ID "{JioCinemaBaseIE._DEVICE_ID}"')
if self._is_token_expired(JioCinemaBaseIE._ACCESS_TOKEN):
self._refresh_token()
class JioCinemaIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/?(?:movies?/[^/?#]+/|tv-shows/(?:[^/?#]+/){3})(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/agnisakshi-ek-samjhauta/1/pradeep-to-stop-the-wedding/3759931',
'info_dict': {
'id': '3759931',
'ext': 'mp4',
'title': 'Pradeep to stop the wedding?',
'description': 'md5:75f72d1d1a66976633345a3de6d672b1',
'episode': 'Pradeep to stop the wedding?',
'episode_number': 89,
'season': 'Agnisakshi…Ek Samjhauta-S1',
'season_number': 1,
'series': 'Agnisakshi Ek Samjhauta',
'duration': 1238.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'season_id': '3698031',
'upload_date': '20230606',
'timestamp': 1686009600,
'release_date': '20230607',
'genres': ['Drama'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.jiocinema.com/movies/bhediya/3754021/watch',
'info_dict': {
'id': '3754021',
'ext': 'mp4',
'title': 'Bhediya',
'description': 'md5:a6bf2900371ac2fc3f1447401a9f7bb0',
'episode': 'Bhediya',
'duration': 8500.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'upload_date': '20230525',
'timestamp': 1685026200,
'release_date': '20230524',
'genres': ['Comedy'],
},
'params': {'skip_download': 'm3u8'},
}]
def _extract_formats_and_subtitles(self, playback, video_id):
m3u8_url = traverse_obj(playback, (
'data', 'playbackUrls', lambda _, v: v['streamtype'] == 'hls', 'url', {url_or_none}, any))
if not m3u8_url: # DRM-only content only serves dash urls
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls')
self._remove_duplicate_formats(formats)
return {
# '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
'formats': traverse_obj(formats, (
lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
'subtitles': subtitles,
}
def _real_extract(self, url):
video_id = self._match_id(url)
if not self._ACCESS_TOKEN and self._is_token_expired(self._GUEST_TOKEN):
self._fetch_guest_token()
elif self._ACCESS_TOKEN and self._is_token_expired(self._ACCESS_TOKEN):
self._refresh_token()
playback = self._call_api(
f'https://apis-jiovoot.voot.com/playbackjv/v3/{video_id}', video_id,
'Downloading playback JSON', headers={
**self.geo_verification_headers(),
'accesstoken': self._ACCESS_TOKEN or self._GUEST_TOKEN,
**self._APP_NAME,
'deviceid': self._DEVICE_ID,
'uniqueid': self._USER_ID,
'x-apisignatures': self._API_SIGNATURES,
'x-platform': 'androidweb',
'x-platform-token': 'web',
}, data={
'4k': False,
'ageGroup': '18+',
'appVersion': '3.4.0',
'bitrateProfile': 'xhdpi',
'capability': {
'drmCapability': {
'aesSupport': 'yes',
'fairPlayDrmSupport': 'none',
'playreadyDrmSupport': 'none',
'widevineDRMSupport': 'none',
},
'frameRateCapability': [{
'frameRateSupport': '30fps',
'videoQuality': '1440p',
}],
},
'continueWatchingRequired': False,
'dolby': False,
'downloadRequest': False,
'hevc': False,
'kidsSafe': False,
'manufacturer': 'Windows',
'model': 'Windows',
'multiAudioRequired': True,
'osVersion': '10',
'parentalPinValid': True,
'x-apisignatures': self._API_SIGNATURES,
})
status_code = traverse_obj(playback, ('code', {int}))
if status_code == 474:
self.raise_geo_restricted(countries=['IN'])
elif status_code == 1008:
error_msg = 'This content is only available for premium users'
if self._ACCESS_TOKEN:
raise ExtractorError(error_msg, expected=True)
self.raise_login_required(f'{error_msg}. {self._LOGIN_HINT}', method=None)
elif status_code == 400:
raise ExtractorError('The requested content is not available', expected=True)
elif status_code is not None and status_code != 200:
raise ExtractorError(
f'JioCinema says: {traverse_obj(playback, ("message", {str})) or status_code}')
metadata = self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/query/asset-details',
video_id, fatal=False, query={
'ids': f'include:{video_id}',
'responseType': 'common',
'devicePlatformType': 'desktop',
})
return {
'id': video_id,
'http_headers': self._API_HEADERS,
**self._extract_formats_and_subtitles(playback, video_id),
**traverse_obj(playback, ('data', {
# fallback metadata
'title': ('name', {str}),
'description': ('fullSynopsis', {str}),
'series': ('show', 'name', {str}, filter),
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
'season_number': ('episode', 'season', {int_or_none}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('totalDuration', {float_or_none}),
'thumbnail': ('images', {url_or_none}),
})),
**traverse_obj(metadata, ('result', 0, {
'title': ('fullTitle', {str}),
'description': ('fullSynopsis', {str}),
'series': ('showName', {str}, filter),
'season': ('seasonName', {str}, filter),
'season_number': ('season', {int_or_none}),
'season_id': ('seasonId', {str}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', {int_or_none}),
'timestamp': ('uploadTime', {int_or_none}),
'release_date': ('telecastDate', {str}),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('duration', {float_or_none}),
'genres': ('genres', ..., {str}),
'thumbnail': ('seo', 'ogImage', {url_or_none}),
})),
}
class JioCinemaSeriesIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema:series'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/tv-shows/(?P<slug>[\w-]+)/(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/naagin/3499917',
'info_dict': {
'id': '3499917',
'title': 'naagin',
},
'playlist_mincount': 120,
}, {
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
'info_dict': {
'id': '3499820',
'title': 'mtv-splitsvilla-x5',
},
'playlist_mincount': 310,
}]
def _entries(self, series_id):
seasons = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
'Downloading series metadata JSON', query={'responseType': 'common'}), (
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
'trayTabs', lambda _, v: v['id']))
for season_num, season in enumerate(seasons, start=1):
season_id = season['id']
label = season.get('label') or season_num
for page_num in itertools.count(1):
episodes = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',
season_id, f'Downloading season {label} page {page_num} JSON', query={
'sort': 'episode:asc',
'id': season_id,
'responseType': 'common',
'page': page_num,
}), ('result', lambda _, v: v['id'] and url_or_none(v['slug'])))
if not episodes:
break
for episode in episodes:
yield self.url_result(
episode['slug'], JioCinemaIE, **traverse_obj(episode, {
'video_id': 'id',
'video_title': ('fullTitle', {str}),
'season_number': ('season', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
}))
def _real_extract(self, url):
slug, series_id = self._match_valid_url(url).group('slug', 'id')
return self.playlist_result(self._entries(series_id), series_id, slug)

View File

@@ -22,18 +22,17 @@ class JojIE(InfoExtractor):
'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
'ext': 'mp4',
'title': 'NOVÉ BÝVANIE',
'thumbnail': r're:^https?://.*?$',
'duration': 3118,
'thumbnail': r're:https?://img\.joj\.sk/.+',
},
}, {
'url': 'https://media.joj.sk/embed/CSM0Na0l0p1',
'info_dict': {
'id': 'CSM0Na0l0p1',
'ext': 'mp4',
'height': 576,
'title': 'Extrémne rodiny 2 - POKRAČOVANIE (2012/04/09 21:30:00)',
'duration': 3937,
'thumbnail': r're:^https?://.*?$',
'thumbnail': r're:https?://img\.joj\.sk/.+',
},
}, {
'url': 'https://media.joj.sk/embed/9i1cxv',
@@ -45,6 +44,15 @@ class JojIE(InfoExtractor):
'url': 'joj:9i1cxv',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# FIXME: Embed detection
'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'info_dict': {
'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'title': 'Slovenskom sa prehnala vlna silných búrok',
},
'playlist_mincount': 5,
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -1,112 +0,0 @@
import datetime as dt
import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
datetime_from_str,
unified_timestamp,
urljoin,
)
class JoqrAgIE(InfoExtractor):
IE_DESC = '超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)'
_VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/(?:player|inc-player-hls)\.php',
r'https?://(?:www\.)?joqr\.co\.jp/ag/',
r'https?://(?:www\.)?joqr\.co\.jp/qr/ag(?:daily|regular)program/?(?:$|[#?])']
_TESTS = [{
'url': 'https://www.uniqueradio.jp/agplayer5/player.php',
'info_dict': {
'id': 'live',
'title': str,
'channel': '超!A&G+',
'description': str,
'live_status': 'is_live',
'release_timestamp': int,
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php',
'only_matching': True,
}, {
'url': 'https://www.joqr.co.jp/ag/article/103760/',
'only_matching': True,
}, {
'url': 'http://www.joqr.co.jp/qr/agdailyprogram/',
'only_matching': True,
}, {
'url': 'http://www.joqr.co.jp/qr/agregularprogram/',
'only_matching': True,
}]
def _extract_metadata(self, variable, html):
return clean_html(urllib.parse.unquote_plus(self._search_regex(
rf'var\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
html, 'metadata', group='value', default=''))) or None
def _extract_start_timestamp(self, video_id, is_live):
def extract_start_time_from(date_str):
dt_ = datetime_from_str(date_str) + dt.timedelta(hours=9)
date = dt_.strftime('%Y%m%d')
start_time = self._search_regex(
r'<h3[^>]+\bclass="dailyProgram-itemHeaderTime"[^>]*>[\s\d:]+\s*(\d{1,2}:\d{1,2})',
self._download_webpage(
f'https://www.joqr.co.jp/qr/agdailyprogram/?date={date}', video_id,
note=f'Downloading program list of {date}', fatal=False,
errnote=f'Failed to download program list of {date}') or '',
'start time', default=None)
if start_time:
return unified_timestamp(f'{dt_.strftime("%Y/%m/%d")} {start_time} +09:00')
return None
start_timestamp = extract_start_time_from('today')
if not start_timestamp:
return None
if not is_live or start_timestamp < datetime_from_str('now').timestamp():
return start_timestamp
else:
return extract_start_time_from('yesterday')
def _real_extract(self, url):
video_id = 'live'
metadata = self._download_webpage(
'https://www.uniqueradio.jp/aandg', video_id,
note='Downloading metadata', errnote='Failed to download metadata')
title = self._extract_metadata('Program_name', metadata)
if not title or title == '放送休止':
formats = []
live_status = 'is_upcoming'
release_timestamp = self._extract_start_timestamp(video_id, False)
msg = 'This stream is not currently live'
if release_timestamp:
msg += (' and will start at '
+ dt.datetime.fromtimestamp(release_timestamp).strftime('%Y-%m-%d %H:%M:%S'))
self.raise_no_formats(msg, expected=True)
else:
m3u8_path = self._search_regex(
r'<source\s[^>]*\bsrc="([^"]+)"',
self._download_webpage(
'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php', video_id,
note='Downloading player data', errnote='Failed to download player data'),
'm3u8 url')
formats = self._extract_m3u8_formats(
urljoin('https://www.uniqueradio.jp/', m3u8_path), video_id)
live_status = 'is_live'
release_timestamp = self._extract_start_timestamp(video_id, True)
return {
'id': video_id,
'title': title,
'channel': '超!A&G+',
'description': self._extract_metadata('Program_text', metadata),
'formats': formats,
'live_status': live_status,
'release_timestamp': release_timestamp,
}

View File

@@ -8,7 +8,6 @@ class JWPlatformIE(InfoExtractor):
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
_TESTS = [{
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
'md5': '3aa16e4f6860e6e78b7df5829519aed3',
'info_dict': {
'id': 'nPripu9l',
'ext': 'mp4',
@@ -17,13 +16,12 @@ class JWPlatformIE(InfoExtractor):
'upload_date': '20081127',
'timestamp': 1227796140,
'duration': 32.0,
'thumbnail': 'https://cdn.jwplayer.com/v2/media/nPripu9l/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
},
}, {
'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# JWPlatform iframe
'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
@@ -33,10 +31,11 @@ class JWPlatformIE(InfoExtractor):
'upload_date': '20160719',
'timestamp': 1468923808,
'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/AG26UQXM/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'description': '',
'duration': 294.0,
},
'skip': 'Site no longer embeds JWPlatform',
}, {
# Player url not surrounded by quotes
'url': 'https://www.deutsche-kinemathek.de/en/online/streaming/school-trip',
@@ -45,12 +44,12 @@ class JWPlatformIE(InfoExtractor):
'title': 'Klassenfahrt',
'ext': 'mp4',
'upload_date': '20230109',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/jUxh5uin/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1673270298,
'description': '',
'duration': 5193.0,
},
'params': {'allowed_extractors': ['generic', 'jwplatform']},
'skip': 'Site no longer embeds JWPlatform',
}, {
# iframe src attribute includes backslash before URL string
'url': 'https://www.elespectador.com/colombia/video-asi-se-evito-la-fuga-de-john-poulos-presunto-feminicida-de-valentina-trespalacios-explicacion',
@@ -59,11 +58,24 @@ class JWPlatformIE(InfoExtractor):
'title': 'Así se evitó la fuga de John Poulos, presunto feminicida de Valentina Trespalacios',
'ext': 'mp4',
'upload_date': '20230127',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/QD3gsexj/poster.jpg?width=720',
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1674862986,
'description': 'md5:128fd74591c4e1fc2da598c5cb6f5ce4',
'duration': 263.0,
},
}, {
'url': 'https://www.skimag.com/video/ski-people-1980',
'info_dict': {
'id': 'YTmgRiNU',
'ext': 'mp4',
'title': 'Ski People (1980)',
'channel': 'snow',
'description': 'md5:cf9c3d101452c91e141f292b19fe4843',
'duration': 5688.0,
'thumbnail': r're:https?://cdn\.jwplayer\.com/v2/media/.+',
'timestamp': 1610407738,
'upload_date': '20210111',
},
}]
@classmethod

View File

@@ -41,149 +41,188 @@ class KalturaIE(InfoExtractor):
2: 'ttml',
3: 'vtt',
}
_TESTS = [
{
'url': 'kaltura:269692:1_1jc2y3e4',
'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': {
'id': '1_1jc2y3e4',
'ext': 'mp4',
'title': 'Straight from the Heart',
'upload_date': '20131219',
'uploader_id': 'mlundberg@wolfgangsvault.com',
'description': 'The Allman Brothers Band, 12/16/1981',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'timestamp': int,
_TESTS = [{
'url': 'kaltura:269692:1_1jc2y3e4',
'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': {
'id': '1_1jc2y3e4',
'ext': 'mp4',
'title': 'Straight from the Heart',
'upload_date': '20131219',
'uploader_id': 'mlundberg@wolfgangsvault.com',
'description': 'The Allman Brothers Band, 12/16/1981',
'thumbnail': r're:https?://.+/thumbnail/.+',
'timestamp': int,
},
'skip': 'The access to this service is forbidden since the specified partner is blocked',
}, {
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
'only_matching': True,
}, {
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
'only_matching': True,
}, {
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
}, {
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
}, {
# video with ttml subtitles (no fileExt)
'url': 'kaltura:1926081:0_l5ye1133',
'info_dict': {
'id': '0_l5ye1133',
'ext': 'mp4',
'title': 'What Can You Do With Python?',
'upload_date': '20160221',
'uploader_id': 'stork',
'thumbnail': r're:https?://.+/thumbnail/.+',
'timestamp': int,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
},
'skip': 'The access to this service is forbidden since the specified partner is blocked',
},
{
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
'only_matching': True,
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
'params': {'skip_download': True},
}, {
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
# unavailable source format
'url': 'kaltura:513551:1_66x4rg7o',
'only_matching': True,
}, {
# html5lib URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
'info_dict': {
'id': '0_c076mna6',
'ext': 'mp4',
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
'duration': 3608,
'uploader_id': 'commons@swinburne.edu.au',
'timestamp': 1408086874,
'view_count': int,
'upload_date': '20140815',
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
},
{
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
'only_matching': True,
}, {
# html5lib playlist URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
'info_dict': {
'id': '1_jovey5nu',
'title': '00-00 Introduction',
},
{
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
},
{
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
},
{
# video with ttml subtitles (no fileExt)
'url': 'kaltura:1926081:0_l5ye1133',
'info_dict': {
'id': '0_l5ye1133',
'ext': 'mp4',
'title': 'What Can You Do With Python?',
'upload_date': '20160221',
'uploader_id': 'stork',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'timestamp': int,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
'playlist': [
{
'info_dict': {
'id': '1_b1y5hlvx',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Introduction',
'duration': 91,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154447,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_jfb7mdpn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Three parts to the course',
'duration': 63,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154489,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_8xflxdp7',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Textbooks',
'duration': 37,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154512,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_3hqew8kn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Prerequisites',
'duration': 49,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'view_count': int,
'timestamp': 1533154536,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
},
'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
'params': {
'skip_download': True,
},
],
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.cornell.edu/VIDEO/nima-arkani-hamed-standard-models-of-particle-physics',
'info_dict': {
'id': '1_sgtvehim',
'ext': 'mp4',
'title': 'Our "Standard Models" of particle physics and cosmology',
'duration': 5420,
'thumbnail': r're:https?://cdnsecakmi\.kaltura\.com/.+',
'timestamp': 1321158993,
'upload_date': '20111113',
'uploader_id': 'kps1',
'view_count': int,
},
{
'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
'info_dict': {
'id': '0_utuok90b',
'ext': 'mp4',
'title': '06_matthew_brender_raj_dutt',
'duration': 331,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1466638791,
'upload_date': '20160622',
'uploader_id': '',
'view_count': int,
},
{
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
}, {
'url': 'https://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
'info_dict': {
'id': '0_izeg5utt',
'ext': 'mp4',
'title': '35871',
'duration': 3403,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1355743100,
'upload_date': '20121217',
'uploader_id': 'cplapp@learn360.com',
'view_count': int,
},
{
# unavailable source format
'url': 'kaltura:513551:1_66x4rg7o',
'only_matching': True,
}, {
'url': 'https://www.cns.nyu.edu/~eero/math-tools17/Videos/lecture-05sep2017.html',
'info_dict': {
'id': '1_9gzouybz',
'ext': 'mp4',
'title': 'lecture-05sep2017',
'duration': 7219,
'thumbnail': r're:https?://cfvod\.kaltura\.com/.+',
'timestamp': 1505340777,
'upload_date': '20170913',
'uploader_id': 'eps2',
'view_count': int,
},
{
# html5lib URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.46/mwEmbedFrame.php/p/691292/uiconf_id/20499062/entry_id/0_c076mna6?wid=_691292&iframeembed=true&playerId=kaltura_player_1420508608&entry_id=0_c076mna6&flashvars%5BakamaiHD.loadingPolicy%5D=preInitialize&flashvars%5BakamaiHD.asyncInit%5D=true&flashvars%5BstreamerType%5D=hdnetwork',
'info_dict': {
'id': '0_c076mna6',
'ext': 'mp4',
'title': 'md5:4883e7acbcbf42583a2dddc97dee4855',
'duration': 3608,
'uploader_id': 'commons@swinburne.edu.au',
'timestamp': 1408086874,
'view_count': int,
'upload_date': '20140815',
'thumbnail': 'http://cfvod.kaltura.com/p/691292/sp/69129200/thumbnail/entry_id/0_c076mna6/version/100022',
},
},
{
# html5lib playlist URL using kwidget player
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.89/mwEmbedFrame.php/p/2019031/uiconf_id/40436601?wid=1_4j3m32cv&iframeembed=true&playerId=kaltura_player_&flashvars[playlistAPI.kpl0Id]=1_jovey5nu&flashvars[ks]=&&flashvars[imageDefaultDuration]=30&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[forceMobileHTML5]=true&flashvars[nextPrevBtn.plugin]=true&flashvars[hotspots.plugin]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[playlistAPI.playlistUrl]=https://canvasgatechtest.kaf.kaltura.com/playlist/details/{playlistAPI.kpl0Id}/categoryid/126428551',
'info_dict': {
'id': '1_jovey5nu',
'title': '00-00 Introduction',
},
'playlist': [
{
'info_dict': {
'id': '1_b1y5hlvx',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Introduction',
'duration': 91,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_b1y5hlvx/version/100001',
'view_count': int,
'timestamp': 1533154447,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_jfb7mdpn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Three parts to the course',
'duration': 63,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_jfb7mdpn/version/100001',
'view_count': int,
'timestamp': 1533154489,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_8xflxdp7',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Textbooks',
'duration': 37,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_8xflxdp7/version/100001',
'view_count': int,
'timestamp': 1533154512,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
}, {
'info_dict': {
'id': '1_3hqew8kn',
'ext': 'mp4',
'title': 'CS7646_00-00 Introductio_Prerequisites',
'duration': 49,
'thumbnail': 'http://cfvod.kaltura.com/p/2019031/sp/201903100/thumbnail/entry_id/1_3hqew8kn/version/100001',
'view_count': int,
'timestamp': 1533154536,
'upload_date': '20180801',
'uploader_id': 'djoyner3',
},
},
],
},
]
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):

View File

@@ -1,12 +1,12 @@
import functools
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
UserNotLive,
determine_ext,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
str_or_none,
traverse_obj,
@@ -16,21 +16,17 @@
class KickBaseIE(InfoExtractor):
def _real_initialize(self):
self._request_webpage(
HEADRequest('https://kick.com/'), None, 'Setting up session', fatal=False, impersonate=True)
xsrf_token = self._get_cookies('https://kick.com/').get('XSRF-TOKEN')
if not xsrf_token:
self.write_debug('kick.com did not set XSRF-TOKEN cookie')
KickBaseIE._API_HEADERS = {
'Authorization': f'Bearer {xsrf_token.value}',
'X-XSRF-TOKEN': xsrf_token.value,
} if xsrf_token else {}
@functools.cached_property
def _api_headers(self):
token = traverse_obj(
self._get_cookies('https://kick.com/'),
('session_token', 'value', {urllib.parse.unquote}))
return {'Authorization': f'Bearer {token}'} if token else {}
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
return self._download_json(
f'https://kick.com/api/{path}', display_id, note=note,
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
headers={**self._api_headers, **headers}, impersonate=True, **kwargs)
class KickIE(KickBaseIE):

View File

@@ -89,6 +89,15 @@ class KinjaEmbedIE(InfoExtractor):
'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
'info_dict': {
'id': '106351',
'ext': 'mp4',
'title': 'Dont Understand Bitcoin? This Man Will Mumble An Explanation At You',
},
'skip': 'Invalid URL',
}]
_JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform')
_PROVIDER_MAP = {
'fb': ('facebook.com/video.php?v=', 'Facebook'),

Some files were not shown because too many files have changed in this diff Show More