Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-02-05 08:46:37 +01:00
Code Issues Projects Releases Packages Wiki Activity

Merge remote-tracking branch 'upstream' into biliSearchPageIE

Browse source
This commit is contained in:
grqx_wsl 2024-08-17 11:20:08 +12:00
commit eac8a89b47
72 changed files with 3136 additions and 1342 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -51,7 +51,6 @@ cookies
*.srt
*.ssa
*.swf
*.swp
*.tt
*.ttml
*.url
@ -119,6 +118,7 @@ yt-dlp.zip
.vscode
*.sublime-*
*.code-workspace
*.swp
# Lazy extractors
*/extractor/lazy_extractors.py

13
CONTRIBUTORS
View file

@ -644,3 +644,16 @@ peisenwang
TheZ3ro
tippfehlr
varunchopra
DrakoCpp
PatrykMis
DinhHuy2010
exterrestris
harbhim
LeSuisse
DunnesH
iancmy
mokrueger
luvyana
szantnerb
hugepower
scribblemaniac

149
Changelog.md
View file

@ -4,10 +4,157 @@
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2024.08.06
#### Core changes
- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly)
- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac)
- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly)
- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower)
- **youtube**
- [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly)
- [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev)
### 2024.08.01
#### Core changes
- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys)
- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261)
- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly)
- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana)
- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb)
- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly)
- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly)
- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33)
- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev)
- [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly)
- [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly)
### 2024.07.25
#### Extractor changes
- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
### 2024.07.16
#### Core changes
- [Fix `noprogress` if `test=True` with `--quiet` and `--verbose`](https://github.com/yt-dlp/yt-dlp/commit/66ce3d76d87af3f81cc9dfec4be4704016cb1cdb) ([#10454](https://github.com/yt-dlp/yt-dlp/issues/10454)) by [Grub4K](https://github.com/Grub4K)
- [Support `auto-tty` and `no_color-tty` for `--color`](https://github.com/yt-dlp/yt-dlp/commit/d9cbced493cae2008508d94a2db5dd98be7c01fc) ([#10453](https://github.com/yt-dlp/yt-dlp/issues/10453)) by [Grub4K](https://github.com/Grub4K)
- **update**: [Fix network error handling](https://github.com/yt-dlp/yt-dlp/commit/ed1b9ed93dd90d2cc960c0d8eaa9d919db224203) ([#10486](https://github.com/yt-dlp/yt-dlp/issues/10486)) by [bashonly](https://github.com/bashonly)
- **utils**: `parse_codecs`: [Fix parsing of mixed case codec strings](https://github.com/yt-dlp/yt-dlp/commit/cc0070f6496e501d77352bad475fb02d6a86846a) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **adn**: [Adjust for .com domain change](https://github.com/yt-dlp/yt-dlp/commit/959b7a379b8e5da059d110a63339c964b6265736) ([#10399](https://github.com/yt-dlp/yt-dlp/issues/10399)) by [infanf](https://github.com/infanf)
- **afreecatv**: [Fix login and use `legacy_ssl`](https://github.com/yt-dlp/yt-dlp/commit/4cd41469243624d90b7a2009b95cbe0609343efe) ([#10440](https://github.com/yt-dlp/yt-dlp/issues/10440)) by [bashonly](https://github.com/bashonly)
- **box**: [Support enterprise URLs](https://github.com/yt-dlp/yt-dlp/commit/705f5b84dec75cc7af97f42fd1530e8062735970) ([#10419](https://github.com/yt-dlp/yt-dlp/issues/10419)) by [seproDev](https://github.com/seproDev)
- **digitalconcerthall**: [Extract HEVC and FLAC formats](https://github.com/yt-dlp/yt-dlp/commit/e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1) ([#10470](https://github.com/yt-dlp/yt-dlp/issues/10470)) by [bashonly](https://github.com/bashonly)
- **dplay**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f) ([#10471](https://github.com/yt-dlp/yt-dlp/issues/10471)) by [bashonly](https://github.com/bashonly)
- **epidemicsound**: [Support sound effects URLs](https://github.com/yt-dlp/yt-dlp/commit/8531d2b03bac9cc746f2ee8098aaf8f115505f5b) ([#10436](https://github.com/yt-dlp/yt-dlp/issues/10436)) by [iancmy](https://github.com/iancmy)
- **generic**: [Fix direct video link extensions](https://github.com/yt-dlp/yt-dlp/commit/b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e) ([#10468](https://github.com/yt-dlp/yt-dlp/issues/10468)) by [bashonly](https://github.com/bashonly)
- **picarto**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bacd18b7df08b4995644fd12cee1f8c8e8636bc7) ([#10414](https://github.com/yt-dlp/yt-dlp/issues/10414)) by [Frankgoji](https://github.com/Frankgoji)
- **soundcloud**: permalink, user: [Extract tracks only](https://github.com/yt-dlp/yt-dlp/commit/22870b81bad97dfa6307a7add44753b2dffc76a9) ([#10463](https://github.com/yt-dlp/yt-dlp/issues/10463)) by [DunnesH](https://github.com/DunnesH)
- **tiktok**: live: [Fix room ID extraction](https://github.com/yt-dlp/yt-dlp/commit/d2189d3d36987ebeac426fd70a60a5fe86325a2b) ([#10408](https://github.com/yt-dlp/yt-dlp/issues/10408)) by [mokrueger](https://github.com/mokrueger)
- **tv5monde**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/9b95a6765a5f6325af99c4aca961587f0c426e8c) ([#10417](https://github.com/yt-dlp/yt-dlp/issues/10417)) by [bashonly](https://github.com/bashonly) (With fixes in [cc1a309](https://github.com/yt-dlp/yt-dlp/commit/cc1a3098c00995c6aebc2a16bd1050a66bad64db))
- **youtube**
- [Avoid poToken experiment player responses](https://github.com/yt-dlp/yt-dlp/commit/8b8b442cb005a8d85315f301615f83fb736b967a) ([#10456](https://github.com/yt-dlp/yt-dlp/issues/10456)) by [seproDev](https://github.com/seproDev) (With fixes in [16da8ef](https://github.com/yt-dlp/yt-dlp/commit/16da8ef9937ff76632dfef02e5062c5ba99c8ea2))
- [Invalidate nsig cache from < 2024.07.09](https://github.com/yt-dlp/yt-dlp/commit/04e17ba20a139f1b3e30ec4bafa3fba26888f0b3) ([#10401](https://github.com/yt-dlp/yt-dlp/issues/10401)) by [bashonly](https://github.com/bashonly)
- [Reduce android client priority](https://github.com/yt-dlp/yt-dlp/commit/b85eef0a615a01304f88a3847309c667e09a20df) ([#10467](https://github.com/yt-dlp/yt-dlp/issues/10467)) by [seproDev](https://github.com/seproDev)
#### Networking changes
- [Add `legacy_ssl` request extension](https://github.com/yt-dlp/yt-dlp/commit/150ecc45d9cacc919550c13b04fd998ac5103a6b) ([#10448](https://github.com/yt-dlp/yt-dlp/issues/10448)) by [coletdjnz](https://github.com/coletdjnz)
- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.7.X](https://github.com/yt-dlp/yt-dlp/commit/42bfca00a6b460fc053514cdd7ac6f5b5daddf0c) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- **build**
- [Include `curl_cffi` in `yt-dlp_linux`](https://github.com/yt-dlp/yt-dlp/commit/4521f30d1479315cd5c3bf4abdad19391952df98) by [bashonly](https://github.com/bashonly)
- [Pin `curl-cffi` to 0.5.10 for Windows](https://github.com/yt-dlp/yt-dlp/commit/ac30941ae682f71eab010877c9a977736a61d3cf) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [89a161e](https://github.com/yt-dlp/yt-dlp/commit/89a161e8c62569a662deda1c948664152efcb6b4) by [bashonly](https://github.com/bashonly)
### 2024.07.09
#### Core changes
- [Do not alter default format selection when simulated](https://github.com/yt-dlp/yt-dlp/commit/0b570f2a90ce2363ba06089217514d644e7be2e0) ([#9862](https://github.com/yt-dlp/yt-dlp/issues/9862)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **youtube**: [Remove broken `n` function extraction fallback](https://github.com/yt-dlp/yt-dlp/commit/7ead7332af69422cee931aec3faa277288e9e212) ([#10396](https://github.com/yt-dlp/yt-dlp/issues/10396)) by [pukkandan](https://github.com/pukkandan), [seproDev](https://github.com/seproDev)
### 2024.07.08
#### Core changes
- **jsinterp**: [Implement `Function.prototype` resolving for `call` and `apply`](https://github.com/yt-dlp/yt-dlp/commit/6c056ea7aeb03660281653a9668547f2548f194f) ([#10392](https://github.com/yt-dlp/yt-dlp/issues/10392)) by [Grub4K](https://github.com/Grub4K)
#### Extractor changes
- **soundcloud**: [Fix rate-limit handling](https://github.com/yt-dlp/yt-dlp/commit/4b50b292cc98534fb8c7cdf0ae5cb85862f7ebfc) ([#10389](https://github.com/yt-dlp/yt-dlp/issues/10389)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix JS `n` function name extraction](https://github.com/yt-dlp/yt-dlp/commit/297b0a379282a15c80d82d51f3757c961db2dae1) ([#10390](https://github.com/yt-dlp/yt-dlp/issues/10390)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
### 2024.07.07
#### Important changes
- Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)
- A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors
#### Core changes
- [Address gaps in allowed extensions](https://github.com/yt-dlp/yt-dlp/commit/2469119490d7e0397ebbf5c5ae327316f955eef2) ([#10362](https://github.com/yt-dlp/yt-dlp/issues/10362)) by [bashonly](https://github.com/bashonly)
- [Fix `--ignore-no-formats-error`](https://github.com/yt-dlp/yt-dlp/commit/cc767e9490056efaaa11c186b0d032e4b4969180) ([#10345](https://github.com/yt-dlp/yt-dlp/issues/10345)) by [Grub4K](https://github.com/Grub4K)
#### Extractor changes
- **abematv**: [Extract availability](https://github.com/yt-dlp/yt-dlp/commit/2a1a1b8e67e864289ac7ba5d05ec63dbb19a639f) ([#10348](https://github.com/yt-dlp/yt-dlp/issues/10348)) by [middlingphys](https://github.com/middlingphys)
- **chzzk**: [Extract with API v3](https://github.com/yt-dlp/yt-dlp/commit/4862a29854d4044120e3f97b52199711ad04bee1) ([#10363](https://github.com/yt-dlp/yt-dlp/issues/10363)) by [hui1601](https://github.com/hui1601)
- **douyutv**: [Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/commit/6075a029dba70a89675ae1250e7cdfd91f0eba41) ([#10347](https://github.com/yt-dlp/yt-dlp/issues/10347)) by [LeSuisse](https://github.com/LeSuisse)
- **jiosaavn**: playlist: [Support featured playlists](https://github.com/yt-dlp/yt-dlp/commit/f0f867f008a1728f5f6ac1224b9e014b5d27f817) ([#10382](https://github.com/yt-dlp/yt-dlp/issues/10382)) by [harbhim](https://github.com/harbhim)
- **vidyard**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/00766ece0c5c7a80781a4ff677198c5fb69d9dc0) ([#10155](https://github.com/yt-dlp/yt-dlp/issues/10155)) by [exterrestris](https://github.com/exterrestris)
- **vimeo**: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/c1c9bb4adb42d0d93a2fb5d93a7de0a87b6ba884) ([#10341](https://github.com/yt-dlp/yt-dlp/issues/10341)) by [bashonly](https://github.com/bashonly)
- **vtv**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/987a1f94c24275f2b0cd82e719956687415dd732) ([#10173](https://github.com/yt-dlp/yt-dlp/issues/10173)) by [DinhHuy2010](https://github.com/DinhHuy2010)
- **yle_areena**
- [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/4cdc976bd861b5835601ae402bef543eacd88f3d) ([#10380](https://github.com/yt-dlp/yt-dlp/issues/10380)) by [seproDev](https://github.com/seproDev)
- [Fix subtitle extraction](https://github.com/yt-dlp/yt-dlp/commit/0d174e8bed32081eb38ef7f5d1a1282ae154f517) ([#10379](https://github.com/yt-dlp/yt-dlp/issues/10379)) by [Grub4K](https://github.com/Grub4K)
#### Misc. changes
- **cleanup**: Miscellaneous: [b337d29](https://github.com/yt-dlp/yt-dlp/commit/b337d2989ce0614651d363383f6f743d977248ef) by [bashonly](https://github.com/bashonly)
### 2024.07.02
#### Core changes
- [Fix `--compat-opt allow-unsafe-ext`](https://github.com/yt-dlp/yt-dlp/commit/773bbb181506856ffda95496ab60c1c9603f1f71) ([#10336](https://github.com/yt-dlp/yt-dlp/issues/10336)) by [bashonly](https://github.com/bashonly), [rdamas](https://github.com/rdamas)
#### Extractor changes
- **banbye**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7509791385ba88cb7ec0ab17e826681f4af4b66e) ([#10332](https://github.com/yt-dlp/yt-dlp/issues/10332)) by [PatrykMis](https://github.com/PatrykMis), [seproDev](https://github.com/seproDev)
- **murrtube**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6403530e2dfe259a87afe444708c4f3024cc45b8) ([#9249](https://github.com/yt-dlp/yt-dlp/issues/9249)) by [DrakoCpp](https://github.com/DrakoCpp)
- **zaiko**: [Support JWT video URLs](https://github.com/yt-dlp/yt-dlp/commit/7799e518956387bb3c1064c9beae26eab8d5044a) ([#10130](https://github.com/yt-dlp/yt-dlp/issues/10130)) by [pzhlkj6612](https://github.com/pzhlkj6612)
#### Postprocessor changes
- **embedthumbnail**: [Fix embedding with mutagen](https://github.com/yt-dlp/yt-dlp/commit/d502f4c6d95b74896f40070d07229997f0850f31) ([#10337](https://github.com/yt-dlp/yt-dlp/issues/10337)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **cleanup**: Miscellaneous: [93d33cb](https://github.com/yt-dlp/yt-dlp/commit/93d33cb29af9e2e84369ac43589d50ce8e0160ef) by [bashonly](https://github.com/bashonly)
### 2024.07.01
#### Important changes
- Security: [[CVE-2024-10123](https://nvd.nist.gov/vuln/detail/CVE-2024-10123)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)
- Security: [[CVE-2024-38519](https://nvd.nist.gov/vuln/detail/CVE-2024-38519)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)
- Unsafe extensions are now blocked from being downloaded
#### Core changes

2
Makefile
View file

@ -21,7 +21,7 @@ clean-test:
rm -rf test/testdata/sigs/player-*.js 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 *.swp *.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
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

22
README.md
View file

@ -202,7 +202,7 @@ The following provide support for impersonating browser requests. This may be re
* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
* Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"`
* Currently only included in `yt-dlp.exe` and `yt-dlp_macos` builds
* Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds
### Metadata
@ -368,7 +368,9 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
stderr) to apply the setting to. Can be one
of "always", "auto" (default), "never", or
"no_color" (use non color terminal
sequences). Can be used multiple times
sequences). Use "auto-tty" or "no_color-tty"
to decide based on terminal support only.
Can be used multiple times
--compat-options OPTS Options that can help keep compatibility
with youtube-dl or youtube-dlc
configurations by reverting some of the
@ -1756,7 +1758,7 @@ $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-"
# EXTRACTOR ARGUMENTS
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
@ -1765,7 +1767,7 @@ 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
* `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 main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `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). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@ -1773,7 +1775,7 @@ The following extractors use this feature:
* E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
* `innertube_key`: Innertube API key to use for all API requests
* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
#### youtubetab (YouTube playlists, channels, feeds, etc.)
@ -1859,6 +1861,9 @@ The following extractors use this feature:
#### bilibili
* `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats
#### digitalconcerthall
* `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
**Note**: These options may be changed/removed in the future without concern for backward compatibility
<!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
@ -2219,12 +2224,13 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
* yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
* 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.
For ease of use, a few more compat options are available:
* `--compat-options all`: Use all compat options (Do NOT use)
* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx`
* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx`
* `--compat-options all`: Use all compat options (**Do NOT use this!**)
* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization,no-youtube-prefer-utc-upload-date`
* `--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`: Currently does nothing. Use this to enable all future compat options

2
bundle/docker/static/entrypoint.sh
View file

@ -2,7 +2,7 @@
set -e
source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
python -m devscripts.install_deps --include secretstorage
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}"
python -m bundle.pyinstaller

7
devscripts/changelog_override.json
View file

@ -179,6 +179,11 @@
{
"action": "add",
"when": "6aaf96a3d6e7d0d426e97e11a2fcf52fda00e733",
"short": "[priority] Security: [[CVE-2024-10123](https://nvd.nist.gov/vuln/detail/CVE-2024-10123)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)\n - Unsafe extensions are now blocked from being downloaded"
"short": "[priority] Security: [[CVE-2024-38519](https://nvd.nist.gov/vuln/detail/CVE-2024-38519)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)\n - Unsafe extensions are now blocked from being downloaded"
},
{
"action": "add",
"when": "6075a029dba70a89675ae1250e7cdfd91f0eba41",
"short": "[priority] Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)\n - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors"
}
]

8
pyproject.toml
View file

@ -9,6 +9,7 @@ maintainers = [
{name = "Grub4K", email = "contact@grub4k.xyz"},
{name = "bashonly", email = "bashonly@protonmail.com"},
{name = "coletdjnz", email = "coletdjnz@protonmail.com"},
{name = "sepro", email = "sepro@sepr0.com"},
]
description = "A feature-rich command-line audio/video downloader"
readme = "README.md"
@ -53,7 +54,10 @@ dependencies = [
[project.optional-dependencies]
default = []
curl-cffi = ["curl-cffi==0.5.10; implementation_name=='cpython'"]
curl-cffi = [
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
"curl-cffi>=0.5.10,!=0.6.*,<0.8; os_name!='nt' and implementation_name=='cpython'",
]
secretstorage = [
"cffi",
"secretstorage",
@ -62,7 +66,7 @@ build = [
"build",
"hatchling",
"pip",
"setuptools",
"setuptools>=71.0.2", # 71.0.0 broke pyinstaller
"wheel",
]
dev = [

19
supportedsites.md
View file

@ -354,7 +354,6 @@
- **DigitallySpeaking**
- **Digiteka**
- **DiscogsReleasePlaylist**
- **Discovery**
- **DiscoveryLife**
- **DiscoveryNetworksDe**
- **DiscoveryPlus**
@ -363,7 +362,6 @@
- **DiscoveryPlusItaly**
- **DiscoveryPlusItalyShow**
- **Disney**
- **DIYNetwork**
- **dlf**
- **dlf:corpus**: DLF Multi-feed Archives
- **dlive:stream**
@ -516,7 +514,6 @@
- **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine")
- **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine")
- **Glide**: Glide mobile video messages (glide.me)
- **GlobalCyclingNetworkPlus**
- **GlobalPlayerAudio**
- **GlobalPlayerAudioEpisode**
- **GlobalPlayerLive**
@ -658,10 +655,11 @@
- **Ketnet**
- **khanacademy**
- **khanacademy:unit**
- **Kick**
- **kick:clips**
- **kick:live**
- **kick:vod**
- **Kicker**
- **KickStarter**
- **KickVOD**
- **kinja:embed**
- **KinoPoisk**
- **Kommunetv**
@ -693,6 +691,7 @@
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **LearningOnScreen**
- **Lecture2Go**: (**Currently broken**)
- **Lecturio**: [*lecturio*](## "netrc machine")
- **LecturioCourse**: [*lecturio*](## "netrc machine")
@ -820,8 +819,6 @@
- **MotherlessGroup**
- **MotherlessUploader**
- **Motorsport**: motorsport.com (**Currently broken**)
- **MotorTrend**
- **MotorTrendOnDemand**
- **MovieFap**
- **Moviepilot**
- **MoviewPlay**
@ -839,7 +836,7 @@
- **MTVUutisetArticle**: (**Currently broken**)
- **MuenchenTV**: münchen.tv (**Currently broken**)
- **MujRozhlas**
- **Murrtube**: (**Currently broken**)
- **Murrtube**
- **MurrtubeUser**: Murrtube user profile (**Currently broken**)
- **MuseAI**
- **MuseScore**
@ -1145,7 +1142,6 @@
- **QuantumTV**: [*quantumtv*](## "netrc machine")
- **QuantumTVLive**: [*quantumtv*](## "netrc machine")
- **QuantumTVRecordings**: [*quantumtv*](## "netrc machine")
- **Qub**
- **R7**: (**Currently broken**)
- **R7Article**: (**Currently broken**)
- **Radiko**
@ -1522,9 +1518,9 @@
- **tv5unis**
- **tv5unis:video**
- **tv8.it**
- **TVA**
- **TVANouvelles**
- **TVANouvellesArticle**
- **tvaplus**: TVA+
- **TVC**
- **TVCArticle**
- **TVer**
@ -1618,6 +1614,7 @@
- **VidLii**
- **Vidly**
- **vids.io**
- **Vidyard**
- **viewlift**
- **viewlift:embed**
- **Viidea**
@ -1665,6 +1662,8 @@
- **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
- **VrtNU**: [*vrtnu*](## "netrc machine") VRT MAX
- **VTM**: (**Currently broken**)
- **VTV**
- **VTVGo**
- **VTXTV**: [*vtxtv*](## "netrc machine")
- **VTXTVLive**: [*vtxtv*](## "netrc machine")
- **VTXTVRecordings**: [*vtxtv*](## "netrc machine")

33
test/test_YoutubeDL.py
View file

@ -4,6 +4,7 @@
import os
import sys
import unittest
from unittest.mock import patch
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@ -520,7 +521,33 @@ class TestFormatSelection(unittest.TestCase):
ydl.process_ie_result(info_dict)
self.assertEqual(ydl.downloaded_info_dicts, [])
def test_default_format_spec(self):
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
def test_default_format_spec_without_ffmpeg(self):
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'outtmpl': '-'})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', True)
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.can_merge', lambda _: True)
def test_default_format_spec_with_ffmpeg(self):
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
@ -528,13 +555,13 @@ class TestFormatSelection(unittest.TestCase):
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'outtmpl': '-'})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')

55
test/test_jsinterp.py
View file

@ -376,6 +376,61 @@ class TestJSInterpreter(unittest.TestCase):
jsi = JSInterpreter('''function f(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}''')
self.assertEqual(jsi.call_function('f', '''h 7=g("1j");7.7h({7g:[{33:"w://7f-7e-7d-7c.v.7b/7a/79/78/77/76.74?t=73&s=2s&e=72&f=2t&71=70.0.0.1&6z=6y&6x=6w"}],6v:"w://32.v.u/6u.31",16:"r%",15:"r%",6t:"6s",6r:"",6q:"l",6p:"l",6o:"6n",6m:\'6l\',6k:"6j",9:[{33:"/2u?b=6i&n=50&6h=w://32.v.u/6g.31",6f:"6e"}],1y:{6d:1,6c:\'#6b\',6a:\'#69\',68:"67",66:30,65:r,},"64":{63:"%62 2m%m%61%5z%5y%5x.u%5w%5v%5u.2y%22 2k%m%1o%22 5t%m%1o%22 5s%m%1o%22 2j%m%5r%22 16%m%5q%22 15%m%5p%22 5o%2z%5n%5m%2z",5l:"w://v.u/d/1k/5k.2y",5j:[]},\'5i\':{"5h":"5g"},5f:"5e",5d:"w://v.u",5c:{},5b:l,1x:[0.25,0.50,0.75,1,1.25,1.5,2]});h 1m,1n,5a;h 59=0,58=0;h 7=g("1j");h 2x=0,57=0,56=0;$.55({54:{\'53-52\':\'2i-51\'}});7.j(\'4z\',6(x){c(5>0&&x.1l>=5&&1n!=1){1n=1;$(\'q.4y\').4x(\'4w\')}});7.j(\'13\',6(x){2x=x.1l});7.j(\'2g\',6(x){2w(x)});7.j(\'4v\',6(){$(\'q.2v\').4u()});6 2w(x){$(\'q.2v\').4t();c(1m)19;1m=1;17=0;c(4s.4r===l){17=1}$.4q(\'/2u?b=4p&2l=1k&4o=2t-4n-4m-2s-4l&4k=&4j=&4i=&17=\'+17,6(2r){$(\'#4h\').4g(2r)});$(\'.3-8-4f-4e:4d("4c")\').2h(6(e){2q();g().4b(0);g().4a(l)});6 2q(){h $14=$("<q />").2p({1l:"49",16:"r%",15:"r%",48:0,2n:0,2o:47,46:"45(10%, 10%, 10%, 0.4)","44-43":"42"});$("<41 />").2p({16:"60%",15:"60%",2o:40,"3z-2n":"3y"}).3x({\'2m\':\'/?b=3w&2l=1k\',\'2k\':\'0\',\'2j\':\'2i\'}).2f($14);$14.2h(6(){$(3v).3u();g().2g()});$14.2f($(\'#1j\'))}g().13(0);}6 3t(){h 9=7.1b(2e);2d.2c(9);c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==2e){2d.2c(\'!!=\'+i);7.1p(i)}}}}7.j(\'3s\',6(){g().1h("/2a/3r.29","3q 10 28",6(){g().13(g().27()+10)},"2b");$("q[26=2b]").23().21(\'.3-20-1z\');g().1h("/2a/3p.29","3o 10 28",6(){h 12=g().27()-10;c(12<0)12=0;g().13(12)},"24");$("q[26=24]").23().21(\'.3-20-1z\');});6 1i(){}7.j(\'3n\',6(){1i()});7.j(\'3m\',6(){1i()});7.j("k",6(y){h 9=7.1b();c(9.n<2)19;$(\'.3-8-3l-3k\').3j(6(){$(\'#3-8-a-k\').1e(\'3-8-a-z\');$(\'.3-a-k\').p(\'o-1f\',\'11\')});7.1h("/3i/3h.3g","3f 3e",6(){$(\'.3-1w\').3d(\'3-8-1v\');$(\'.3-8-1y, .3-8-1x\').p(\'o-1g\',\'11\');c($(\'.3-1w\').3c(\'3-8-1v\')){$(\'.3-a-k\').p(\'o-1g\',\'l\');$(\'.3-a-k\').p(\'o-1f\',\'l\');$(\'.3-8-a\').1e(\'3-8-a-z\');$(\'.3-8-a:1u\').3b(\'3-8-a-z\')}3a{$(\'.3-a-k\').p(\'o-1g\',\'11\');$(\'.3-a-k\').p(\'o-1f\',\'11\');$(\'.3-8-a:1u\').1e(\'3-8-a-z\')}},"39");7.j("38",6(y){1d.37(\'1c\',y.9[y.36].1a)});c(1d.1t(\'1c\')){35("1s(1d.1t(\'1c\'));",34)}});h 18;6 1s(1q){h 9=7.1b();c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==1q){c(i==18){19}18=i;7.1p(i)}}}}',36,270,'|||jw|||function|player|settings|tracks|submenu||if||||jwplayer|var||on|audioTracks|true|3D|length|aria|attr|div|100|||sx|filemoon|https||event|active||false|tt|seek|dd|height|width|adb|current_audio|return|name|getAudioTracks|default_audio|localStorage|removeClass|expanded|checked|addButton|callMeMaybe|vplayer|0fxcyc2ajhp1|position|vvplay|vvad|220|setCurrentAudioTrack|audio_name|for|audio_set|getItem|last|open|controls|playbackRates|captions|rewind|icon|insertAfter||detach|ff00||button|getPosition|sec|png|player8|ff11|log|console|track_name|appendTo|play|click|no|scrolling|frameborder|file_code|src|top|zIndex|css|showCCform|data|1662367683|383371|dl|video_ad|doPlay|prevt|mp4|3E||jpg|thumbs|file|300|setTimeout|currentTrack|setItem|audioTrackChanged|dualSound|else|addClass|hasClass|toggleClass|Track|Audio|svg|dualy|images|mousedown|buttons|topbar|playAttemptFailed|beforePlay|Rewind|fr|Forward|ff|ready|set_audio_track|remove|this|upload_srt|prop|50px|margin|1000001|iframe|center|align|text|rgba|background|1000000|left|absolute|pause|setCurrentCaptions|Upload|contains|item|content|html|fviews|referer|prem|embed|3e57249ef633e0d03bf76ceb8d8a4b65|216|83|hash|view|get|TokenZir|window|hide|show|complete|slow|fadeIn|video_ad_fadein|time||cache|Cache|Content|headers|ajaxSetup|v2done|tott|vastdone2|vastdone1|vvbefore|playbackRateControls|cast|aboutlink|FileMoon|abouttext|UHD|1870|qualityLabels|sites|GNOME_POWER|link|2Fiframe|3C|allowfullscreen|22360|22640|22no|marginheight|marginwidth|2FGNOME_POWER|2F0fxcyc2ajhp1|2Fe|2Ffilemoon|2F|3A||22https|3Ciframe|code|sharing|fontOpacity|backgroundOpacity|Tahoma|fontFamily|303030|backgroundColor|FFFFFF|color|userFontScale|thumbnails|kind|0fxcyc2ajhp10000|url|get_slides|start|startparam|none|preload|html5|primary|hlshtml|androidhls|duration|uniform|stretching|0fxcyc2ajhp1_xt|image|2048|sp|6871|asn|127|srv|43200|_g3XlBcu2lmD9oDexD2NLWSmah2Nu3XcDrl93m9PwXY|m3u8||master|0fxcyc2ajhp1_x|00076|01|hls2|to|s01|delivery|storage|moon|sources|setup'''.split('|')))
def test_join(self):
test_input = list('test')
tests = [
'function f(a, b){return a.join(b)}',
'function f(a, b){return Array.prototype.join.call(a, b)}',
'function f(a, b){return Array.prototype.join.apply(a, [b])}',
]
for test in tests:
jsi = JSInterpreter(test)
self._test(jsi, 'test', args=[test_input, ''])
self._test(jsi, 't-e-s-t', args=[test_input, '-'])
self._test(jsi, '', args=[[], '-'])
def test_split(self):
test_result = list('test')
tests = [
'function f(a, b){return a.split(b)}',
'function f(a, b){return String.prototype.split.call(a, b)}',
'function f(a, b){return String.prototype.split.apply(a, [b])}',
]
for test in tests:
jsi = JSInterpreter(test)
self._test(jsi, test_result, args=['test', ''])
self._test(jsi, test_result, args=['t-e-s-t', '-'])
self._test(jsi, [''], args=['', '-'])
self._test(jsi, [], args=['', ''])
def test_slice(self):
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
self._test('function f(){return "012345678".slice()}', '012345678')
self._test('function f(){return "012345678".slice(0)}', '012345678')
self._test('function f(){return "012345678".slice(5)}', '5678')
self._test('function f(){return "012345678".slice(99)}', '')
self._test('function f(){return "012345678".slice(-2)}', '78')
self._test('function f(){return "012345678".slice(-99)}', '012345678')
self._test('function f(){return "012345678".slice(0, 0)}', '')
self._test('function f(){return "012345678".slice(1, 0)}', '')
self._test('function f(){return "012345678".slice(0, 1)}', '0')
self._test('function f(){return "012345678".slice(3, 6)}', '345')
self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
self._test('function f(){return "012345678".slice(-1, 1)}', '')
self._test('function f(){return "012345678".slice(-3, -1)}', '67')
if __name__ == '__main__':
unittest.main()

82
test/test_networking.py
View file

@ -265,6 +265,11 @@ class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
self.end_headers()
self.wfile.write(payload)
self.finish()
elif self.path == '/get_cookie':
self.send_response(200)
self.send_header('Set-Cookie', 'test=ytdlp; path=/')
self.end_headers()
self.finish()
else:
self._status(404)
@ -338,6 +343,52 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
assert not issubclass(exc_info.type, CertificateVerifyError)
@pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
def test_legacy_ssl_extension(self, handler):
# HTTPS server with old ciphers
# XXX: is there a better way to test this than to create a new server?
https_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
https_port = http_server_port(https_httpd)
https_server_thread = threading.Thread(target=https_httpd.serve_forever)
https_server_thread.daemon = True
https_server_thread.start()
with handler(verify=False) as rh:
res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers', extensions={'legacy_ssl': True}))
assert res.status == 200
res.close()
# Ensure only applies to request extension
with pytest.raises(SSLError):
validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
@pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
def test_legacy_ssl_support(self, handler):
# HTTPS server with old ciphers
# XXX: is there a better way to test this than to create a new server?
https_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
https_port = http_server_port(https_httpd)
https_server_thread = threading.Thread(target=https_httpd.serve_forever)
https_server_thread.daemon = True
https_server_thread.start()
with handler(verify=False, legacy_ssl_support=True) as rh:
res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
assert res.status == 200
res.close()
def test_percent_encode(self, handler):
with handler() as rh:
# Unicode characters should be encoded with uppercase percent-encoding
@ -490,6 +541,24 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': cookiejar})).read()
assert b'cookie: test=ytdlp' in data.lower()
def test_cookie_sync_only_cookiejar(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
with handler() as rh:
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': YoutubeDLCookieJar()})).read()
assert b'cookie: test=ytdlp' not in data.lower()
def test_cookie_sync_delete_cookie(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
cookiejar = YoutubeDLCookieJar()
with handler(cookiejar=cookiejar) as rh:
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie'))
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
assert b'cookie: test=ytdlp' in data.lower()
cookiejar.clear_session_cookies()
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
assert b'cookie: test=ytdlp' not in data.lower()
def test_headers(self, handler):
with handler(headers=HTTPHeaderDict({'test1': 'test', 'test2': 'test2'})) as rh:
@ -914,7 +983,6 @@ class TestRequestsRequestHandler(TestRequestHandlerBase):
class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
@pytest.mark.parametrize('params,extensions', [
({}, {'impersonate': ImpersonateTarget('chrome')}),
({'impersonate': ImpersonateTarget('chrome', '110')}, {}),
({'impersonate': ImpersonateTarget('chrome', '99')}, {'impersonate': ImpersonateTarget('chrome', '110')}),
])
@ -1200,6 +1268,9 @@ class TestRequestHandlerValidation:
({'timeout': 1}, False),
({'timeout': 'notatimeout'}, AssertionError),
({'unsupported': 'value'}, UnsupportedRequest),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
('Requests', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),
@ -1207,6 +1278,9 @@ class TestRequestHandlerValidation:
({'timeout': 1}, False),
({'timeout': 'notatimeout'}, AssertionError),
({'unsupported': 'value'}, UnsupportedRequest),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
('CurlCFFI', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),
@ -1220,6 +1294,9 @@ class TestRequestHandlerValidation:
({'impersonate': ImpersonateTarget(None, None, None, None)}, False),
({'impersonate': ImpersonateTarget()}, False),
({'impersonate': 'chrome'}, AssertionError),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
(NoCheckRH, 'http', [
({'cookiejar': 'notacookiejar'}, False),
@ -1228,6 +1305,9 @@ class TestRequestHandlerValidation:
('Websockets', 'ws', [
({'cookiejar': YoutubeDLCookieJar()}, False),
({'timeout': 2}, False),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
]

7
test/test_utils.py
View file

@ -444,6 +444,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600)
self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200)
self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
@ -929,6 +931,11 @@ class TestUtil(unittest.TestCase):
'acodec': 'none',
'dynamic_range': 'DV',
})
self.assertEqual(parse_codecs('fLaC'), {
'vcodec': 'none',
'acodec': 'flac',
'dynamic_range': None,
})
self.assertEqual(parse_codecs('theora, vorbis'), {
'vcodec': 'theora',
'acodec': 'vorbis',

58
test/test_websockets.py
View file

@ -61,6 +61,10 @@ def process_request(self, request):
return websockets.http11.Response(
status.value, status.phrase, websockets.datastructures.Headers([('Location', '/')]), b'')
return self.protocol.reject(status.value, status.phrase)
elif request.path.startswith('/get_cookie'):
response = self.protocol.accept(request)
response.headers['Set-Cookie'] = 'test=ytdlp'
return response
return self.protocol.accept(request)
@ -102,6 +106,15 @@ def create_mtls_wss_websocket_server():
return create_websocket_server(ssl_context=sslctx)
def create_legacy_wss_websocket_server():
certfn = os.path.join(TEST_DIR, 'testcert.pem')
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(certfn, None)
return create_websocket_server(ssl_context=sslctx)
def ws_validate_and_send(rh, req):
rh.validate(req)
max_tries = 3
@ -132,6 +145,9 @@ class TestWebsSocketRequestHandlerConformance:
cls.mtls_wss_thread, cls.mtls_wss_port = create_mtls_wss_websocket_server()
cls.mtls_wss_base_url = f'wss://127.0.0.1:{cls.mtls_wss_port}'
cls.legacy_wss_thread, cls.legacy_wss_port = create_legacy_wss_websocket_server()
cls.legacy_wss_host = f'wss://127.0.0.1:{cls.legacy_wss_port}'
def test_basic_websockets(self, handler):
with handler() as rh:
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
@ -166,6 +182,22 @@ class TestWebsSocketRequestHandlerConformance:
ws_validate_and_send(rh, Request(self.bad_wss_host))
assert not issubclass(exc_info.type, CertificateVerifyError)
def test_legacy_ssl_extension(self, handler):
with handler(verify=False) as rh:
ws = ws_validate_and_send(rh, Request(self.legacy_wss_host, extensions={'legacy_ssl': True}))
assert ws.status == 101
ws.close()
# Ensure only applies to request extension
with pytest.raises(SSLError):
ws_validate_and_send(rh, Request(self.legacy_wss_host))
def test_legacy_ssl_support(self, handler):
with handler(verify=False, legacy_ssl_support=True) as rh:
ws = ws_validate_and_send(rh, Request(self.legacy_wss_host))
assert ws.status == 101
ws.close()
@pytest.mark.parametrize('path,expected', [
# Unicode characters should be encoded with uppercase percent-encoding
('/中文', '/%E4%B8%AD%E6%96%87'),
@ -248,6 +280,32 @@ class TestWebsSocketRequestHandlerConformance:
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
def test_cookie_sync_only_cookiejar(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
with handler() as rh:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
ws = ws_validate_and_send(rh, Request(self.ws_base_url, extensions={'cookiejar': YoutubeDLCookieJar()}))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
def test_cookie_sync_delete_cookie(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
cookiejar = YoutubeDLCookieJar()
with handler(verbose=True, cookiejar=cookiejar) as rh:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie'))
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
ws.close()
cookiejar.clear_session_cookies()
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
ws.close()
def test_source_address(self, handler):
source_address = f'127.0.0.{random.randint(5, 255)}'
verify_address_availability(source_address)

16
test/test_youtube_signature.py
View file

@ -167,6 +167,22 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
'1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
),
(
'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
),
(
'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
),
(
'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
'-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
),
(
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
),
]

26
yt_dlp/YoutubeDL.py
View file

@ -452,7 +452,8 @@ class YoutubeDL:
Can also just be a single color policy,
in which case it applies to all outputs.
Valid stream names are 'stdout' and 'stderr'.
Valid color policies are one of 'always', 'auto', 'no_color' or 'never'.
Valid color policies are one of 'always', 'auto',
'no_color', 'never', 'auto-tty' or 'no_color-tty'.
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
HTTP header
geo_bypass_country:
@ -659,12 +660,15 @@ class YoutubeDL:
self.params['color'] = 'no_color'
term_allow_color = os.getenv('TERM', '').lower() != 'dumb'
no_color = bool(os.getenv('NO_COLOR'))
base_no_color = bool(os.getenv('NO_COLOR'))
def process_color_policy(stream):
stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream]
policy = traverse_obj(self.params, ('color', (stream_name, None), {str}), get_all=False)
if policy in ('auto', None):
policy = traverse_obj(self.params, ('color', (stream_name, None), {str}, any)) or 'auto'
if policy in ('auto', 'auto-tty', 'no_color-tty'):
no_color = base_no_color
if policy.endswith('tty'):
no_color = policy.startswith('no_color')
if term_allow_color and supports_terminal_sequences(stream):
return 'no_color' if no_color else True
return False
@ -2190,9 +2194,8 @@ class YoutubeDL:
or all(f.get('acodec') == 'none' for f in formats)), # OR, No formats with audio
}))
def _default_format_spec(self, info_dict, download=True):
download = download and not self.params.get('simulate')
prefer_best = download and (
def _default_format_spec(self, info_dict):
prefer_best = (
self.params['outtmpl']['default'] == '-'
or info_dict.get('is_live') and not self.params.get('live_from_start'))
@ -2200,7 +2203,7 @@ class YoutubeDL:
merger = FFmpegMergerPP(self)
return merger.available and merger.can_merge()
if not prefer_best and download and not can_merge():
if not prefer_best and not can_merge():
prefer_best = True
formats = self._get_formats(info_dict)
evaluate_formats = lambda spec: self._select_formats(formats, self.build_format_selector(spec))
@ -2959,7 +2962,7 @@ class YoutubeDL:
continue
if format_selector is None:
req_format = self._default_format_spec(info_dict, download=download)
req_format = self._default_format_spec(info_dict)
self.write_debug(f'Default format spec: {req_format}')
format_selector = self.build_format_selector(req_format)
@ -3169,11 +3172,12 @@ class YoutubeDL:
if test:
verbose = self.params.get('verbose')
quiet = self.params.get('quiet') or not verbose
params = {
'test': True,
'quiet': self.params.get('quiet') or not verbose,
'quiet': quiet,
'verbose': verbose,
'noprogress': not verbose,
'noprogress': quiet,
'nopart': True,
'skip_unavailable_fragments': False,
'keep_fragments': False,

4
yt_dlp/__init__.py
View file

@ -468,7 +468,7 @@ def validate_options(opts):
default_downloader = ed.get_basename()
for policy in opts.color.values():
if policy not in ('always', 'auto', 'no_color', 'never'):
if policy not in ('always', 'auto', 'auto-tty', 'no_color', 'no_color-tty', 'never'):
raise ValueError(f'"{policy}" is not a valid color policy')
warnings, deprecation_warnings = [], []
@ -599,7 +599,7 @@ def validate_options(opts):
warnings.append(
'Using allow-unsafe-ext opens you up to potential attacks. '
'Use with great care!')
_UnsafeExtensionError.sanitize_extension = lambda x: x
_UnsafeExtensionError.sanitize_extension = lambda x, prepend=False: x
return warnings, deprecation_warnings

17
yt_dlp/extractor/_extractors.py
View file

@ -506,7 +506,6 @@ from .dhm import DHMIE
from .digitalconcerthall import DigitalConcertHallIE
from .digiteka import DigitekaIE
from .discogs import DiscogsReleasePlaylistIE
from .discovery import DiscoveryIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .dlf import (
@ -534,16 +533,12 @@ from .dplay import (
DiscoveryPlusIndiaShowIE,
DiscoveryPlusItalyIE,
DiscoveryPlusItalyShowIE,
DIYNetworkIE,
DPlayIE,
FoodNetworkIE,
GlobalCyclingNetworkPlusIE,
GoDiscoveryIE,
HGTVDeIE,
HGTVUsaIE,
InvestigationDiscoveryIE,
MotorTrendIE,
MotorTrendOnDemandIE,
ScienceChannelIE,
TravelChannelIE,
)
@ -946,6 +941,7 @@ from .khanacademy import (
KhanAcademyUnitIE,
)
from .kick import (
KickClipIE,
KickIE,
KickVODIE,
)
@ -993,6 +989,7 @@ from .lcp import (
LcpIE,
LcpPlayIE,
)
from .learningonscreen import LearningOnScreenIE
from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioCourseIE,
@ -2176,10 +2173,7 @@ from .tv5unis import (
TV5UnisVideoIE,
)
from .tv24ua import TV24UAVideoIE
from .tva import (
TVAIE,
QubIE,
)
from .tva import TVAIE
from .tvanouvelles import (
TVANouvellesArticleIE,
TVANouvellesIE,
@ -2326,6 +2320,7 @@ from .vidio import (
)
from .vidlii import VidLiiIE
from .vidly import VidlyIE
from .vidyard import VidyardIE
from .viewlift import (
ViewLiftEmbedIE,
ViewLiftIE,
@ -2391,6 +2386,10 @@ from .vrt import (
VrtNUIE,
)
from .vtm import VTMIE
from .vtv import (
VTVIE,
VTVGoIE,
)
from .vuclip import VuClipIE
from .vvvvid import (
VVVVIDIE,

74
yt_dlp/extractor/abematv.py
View file

@ -9,12 +9,12 @@ import re
import struct
import time
import urllib.parse
import urllib.request
import urllib.response
import uuid
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..networking import RequestHandler, Response
from ..networking.exceptions import TransportError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -26,37 +26,36 @@ from ..utils import (
traverse_obj,
update_url_query,
)
from ..utils.networking import clean_proxies
def add_opener(ydl, handler): # FIXME: Create proper API in .networking
"""Add a handler for opening URLs, like _download_webpage"""
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
rh = ydl._request_director.handlers['Urllib']
if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
return
headers = ydl.params['http_headers'].copy()
proxies = ydl.proxies.copy()
clean_proxies(proxies, headers)
opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
assert isinstance(opener, urllib.request.OpenerDirector)
opener.add_handler(handler)
rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
class AbemaLicenseRH(RequestHandler):
_SUPPORTED_URL_SCHEMES = ('abematv-license',)
_SUPPORTED_PROXY_SCHEMES = None
_SUPPORTED_FEATURES = None
RH_NAME = 'abematv_license'
_STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
_HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
class AbemaLicenseHandler(urllib.request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protocol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
super().__init__(**kwargs)
self.ie = ie
def _send(self, request):
url = request.url
ticket = urllib.parse.urlparse(url).netloc
try:
response_data = self._get_videokey_from_ticket(ticket)
except ExtractorError as e:
raise TransportError(cause=e.cause) from e
except (IndexError, KeyError, TypeError) as e:
raise TransportError(cause=repr(e)) from e
return Response(
io.BytesIO(response_data), url,
headers={'Content-Length': str(len(response_data))})
def _get_videokey_from_ticket(self, ticket):
to_show = self.ie.get_param('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show)
@ -72,25 +71,17 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
'Content-Type': 'application/json',
})
res = decode_base_n(license_response['k'], table=self.STRTABLE)
res = decode_base_n(license_response['k'], table=self._STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new(
binascii.unhexlify(self.HKEY),
binascii.unhexlify(self._HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode(),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': str(len(response_data)),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'abematv'
@ -139,7 +130,7 @@ class AbemaTVBaseIE(InfoExtractor):
if self._USERTOKEN:
return self._USERTOKEN
add_opener(self._downloader, AbemaLicenseHandler(self))
self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
username, _ = self._get_login_info()
auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
@ -368,6 +359,7 @@ class AbemaTVIE(AbemaTVBaseIE):
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
availability = 'public'
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
@ -385,10 +377,10 @@ class AbemaTVIE(AbemaTVBaseIE):
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
if 3 not in ondemand_types:
if not traverse_obj(api_response, ('label', 'free', {bool})):
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
info.update(traverse_obj(api_response, {
'series': ('series', 'title'),
'season': ('season', 'name'),
@ -408,6 +400,7 @@ class AbemaTVIE(AbemaTVBaseIE):
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
@ -425,6 +418,7 @@ class AbemaTVIE(AbemaTVBaseIE):
'description': description,
'formats': formats,
'is_live': is_live,
'availability': availability,
})
return info

33
yt_dlp/extractor/adn.py
View file

@ -16,6 +16,7 @@ from ..utils import (
float_or_none,
int_or_none,
intlist_to_bytes,
join_nonempty,
long_to_bytes,
parse_iso8601,
pkcs1pad,
@ -48,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
class ADNIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'url': 'https://animationdigitalnetwork.com/video/558-fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '9841',
@ -70,10 +71,7 @@ class ADNIE(ADNBaseIE):
},
'skip': 'Only available in French and German speaking Europe',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}, {
'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1',
'url': 'https://animationdigitalnetwork.com/de/video/973-the-eminence-in-shadow/23550-folge-1',
'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
'info_dict': {
'id': '23550',
@ -166,7 +164,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
'username': username,
})) or {}).get('accessToken')
if access_token:
self._HEADERS = {'authorization': 'Bearer ' + access_token}
self._HEADERS['Authorization'] = f'Bearer {access_token}'
except ExtractorError as e:
message = None
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
@ -177,6 +175,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
def _real_extract(self, url):
lang, video_id = self._match_valid_url(url).group('lang', 'id')
self._HEADERS['X-Target-Distribution'] = lang or 'fr'
video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
player = self._download_json(
video_base_url + 'configuration', video_id,
@ -217,7 +216,6 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization,
'X-Target-Distribution': lang,
**self._HEADERS,
}, query={
'freeWithAds': 'true',
@ -256,6 +254,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
load_balancer_data = self._download_json(
load_balancer_url, video_id,
f'Downloading {format_id} {quality} JSON metadata',
headers=self._HEADERS,
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
@ -276,7 +275,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
video = (self._download_json(
self._API_BASE_URL + f'video/{video_id}', video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
'Downloading additional video metadata', fatal=False, headers=self._HEADERS) or {}).get('video') or {}
show = video.get('show') or {}
return {
@ -298,9 +297,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
class ADNSeasonIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>\d+)[^/?#]*/?(?:$|[#?])'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new',
'url': 'https://animationdigitalnetwork.com/video/911-tokyo-mew-mew-new',
'playlist_count': 12,
'info_dict': {
'id': '911',
@ -311,24 +310,22 @@ class ADNSeasonIE(ADNBaseIE):
def _real_extract(self, url):
lang, video_show_slug = self._match_valid_url(url).group('lang', 'id')
self._HEADERS['X-Target-Distribution'] = lang or 'fr'
show = self._download_json(
f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug,
'Downloading show JSON metadata', headers=self._HEADERS)['show']
show_id = str(show['id'])
episodes = self._download_json(
f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
'Downloading episode list', headers={
'X-Target-Distribution': lang,
**self._HEADERS,
}, query={
'Downloading episode list', headers=self._HEADERS, query={
'order': 'asc',
'limit': '-1',
})
def entries():
for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
yield self.url_result(
f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
ADNIE, episode_id)
yield self.url_result(join_nonempty(
'https://animationdigitalnetwork.com', lang, 'video',
video_show_slug, episode_id, delim='/'), ADNIE, episode_id)
return self.playlist_result(entries(), show_id, show.get('title'))

22
yt_dlp/extractor/afreecatv.py
View file

@ -1,6 +1,7 @@
import functools
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -58,6 +59,13 @@ class AfreecaTVBaseIE(InfoExtractor):
f'Unable to login: {self.IE_NAME} said: {error}',
expected=True)
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
return self._download_json(Request(
f'https://api.m.afreecatv.com/{endpoint}',
data=data, headers=headers, query=query,
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
@ -184,12 +192,12 @@ class AfreecaTVIE(AfreecaTVBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api.m.afreecatv.com/station/video/a/view', video_id,
headers={'Referer': url}, data=urlencode_postdata({
data = self._call_api(
'station/video/a/view', video_id, headers={'Referer': url},
data=urlencode_postdata({
'nTitleNo': video_id,
'nApiLevel': 10,
}), impersonate=True)['data']
}))['data']
error_code = traverse_obj(data, ('code', {int}))
if error_code == -6221:
@ -267,9 +275,9 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api.m.afreecatv.com/catchstory/a/view', video_id, headers={'Referer': url},
query={'aStoryListIdx': '', 'nStoryIdx': video_id}, impersonate=True)
data = self._call_api(
'catchstory/a/view', video_id, headers={'Referer': url},
query={'aStoryListIdx': '', 'nStoryIdx': video_id})
return self.playlist_result(self._entries(data), video_id)

71
yt_dlp/extractor/banbye.py
View file

@ -4,9 +4,13 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
determine_ext,
format_field,
int_or_none,
join_nonempty,
traverse_obj,
unified_timestamp,
url_or_none,
)
@ -30,6 +34,7 @@ class BanByeBaseIE(InfoExtractor):
class BanByeIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
_TESTS = [{
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
'info_dict': {
@ -58,6 +63,7 @@ class BanByeIE(BanByeBaseIE):
},
'playlist_mincount': 9,
}, {
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_kb6_o1Kyq-CD',
'info_dict': {
'id': 'v_kb6_o1Kyq-CD',
@ -77,6 +83,48 @@ class BanByeIE(BanByeBaseIE):
'view_count': int,
'comment_count': int,
},
}, {
# ['src']['hls']['levels'] variant m3u8 urls only; master m3u8 is 404
'url': 'https://banbye.com/watch/v_a_gPFuC9LoW5',
'info_dict': {
'id': 'v_a_gPFuC9LoW5',
'ext': 'mp4',
'title': 'md5:183524056bebdfa245fd6d214f63c0fe',
'description': 'md5:943ac87287ca98d28d8b8797719827c6',
'uploader': 'wRealu24',
'channel_id': 'ch_wrealu24',
'channel_url': 'https://banbye.com/channel/ch_wrealu24',
'upload_date': '20231113',
'timestamp': 1699874062,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_a_gPFuC9LoW5/96.webp',
'tags': ['jaszczur', 'sejm', 'lewica', 'polska', 'ukrainizacja', 'pierwszeposiedzeniesejmu'],
},
'expected_warnings': ['Failed to download m3u8'],
}, {
# ['src']['hls']['masterPlaylist'] m3u8 only
'url': 'https://banbye.com/watch/v_B0rsKWsr-aaa',
'info_dict': {
'id': 'v_B0rsKWsr-aaa',
'ext': 'mp4',
'title': 'md5:00b254164b82101b3f9e5326037447ed',
'description': 'md5:3fd8b48aa81954ba024bc60f5de6e167',
'uploader': 'PSTV Piotr Szlachtowicz ',
'channel_id': 'ch_KV9EVObkB9wB',
'channel_url': 'https://banbye.com/channel/ch_KV9EVObkB9wB',
'upload_date': '20240629',
'timestamp': 1719646816,
'duration': 2377,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_B0rsKWsr-aaa/96.webp',
'tags': ['Biden', 'Trump', 'Wybory', 'USA'],
},
}]
def _real_extract(self, url):
@ -91,11 +139,24 @@ class BanByeIE(BanByeBaseIE):
'id': f'{quality}p',
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.webp',
} for quality in [48, 96, 144, 240, 512, 1080]]
formats = [{
'format_id': f'http-{quality}p',
'quality': quality,
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.mp4',
} for quality in data['quality']]
formats = []
url_data = self._download_json(f'{self._API_BASE}/videos/{video_id}/url', video_id, data=b'')
if master_url := traverse_obj(url_data, ('src', 'hls', 'masterPlaylist', {url_or_none})):
formats = self._extract_m3u8_formats(master_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
for format_id, format_url in traverse_obj(url_data, (
'src', ('mp4', 'hls'), 'levels', {dict.items}, lambda _, v: url_or_none(v[1]))):
ext = determine_ext(format_url)
is_hls = ext == 'm3u8'
formats.append({
'url': format_url,
'ext': 'mp4' if is_hls else ext,
'format_id': join_nonempty(is_hls and 'hls', format_id),
'protocol': 'm3u8_native' if is_hls else 'https',
'height': int_or_none(format_id),
})
self._remove_duplicate_formats(formats)
return {
'id': video_id,

6
yt_dlp/extractor/bilibili.py
View file

@ -298,7 +298,7 @@ class BilibiliBaseIE(InfoExtractor):
class BiliBiliIE(BilibiliBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bilibili.com/video/BV13x41117TL',
@ -622,6 +622,10 @@ class BiliBiliIE(BilibiliBaseIE):
'ext': 'mp4',
},
'skip': 'geo-restricted',
}, {
'note': 'has - in the last path segment of the url',
'url': 'https://www.bilibili.com/festival/bh3-7th?bvid=BV1tr4y1f7p2&',
'only_matching': True,
}]
def _real_extract(self, url):

20
yt_dlp/extractor/box.py
View file

@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
class BoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<service>app|ent)\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_TESTS = [{
'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@ -38,10 +38,22 @@ class BoxIE(InfoExtractor):
'uploader_id': '239068974',
},
'params': {'skip_download': 'dash fragment too small'},
}, {
'url': 'https://thejacksonlaboratory.ent.box.com/s/2x09dm6vcg6y28o0oox1so4l0t8wzt6l/file/1536173056065',
'info_dict': {
'id': '1536173056065',
'ext': 'mp4',
'uploader_id': '18523128264',
'uploader': 'Lexi Hennigan',
'title': 'iPSC Symposium recording part 1.mp4',
'timestamp': 1716228343,
'upload_date': '20240520',
},
'params': {'skip_download': 'dash fragment too small'},
}]
def _real_extract(self, url):
shared_name, file_id = self._match_valid_url(url).groups()
shared_name, file_id, service = self._match_valid_url(url).group('shared_name', 'id', 'service')
webpage = self._download_webpage(url, file_id or shared_name)
if not file_id:
@ -57,14 +69,14 @@ class BoxIE(InfoExtractor):
request_token = self._search_json(
r'Box\.config\s*=', webpage, 'Box config', file_id)['requestToken']
access_token = self._download_json(
'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
f'https://{service}.box.com/app-api/enduserapp/elements/tokens', file_id,
'Downloading token JSON metadata',
data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
'Content-Type': 'application/json',
'X-Request-Token': request_token,
'X-Box-EndUser-API': 'sharedName=' + shared_name,
})[file_id]['read']
shared_link = 'https://app.box.com/s/' + shared_name
shared_link = f'https://{service}.box.com/s/{shared_name}'
f = self._download_json(
'https://api.box.com/2.0/files/' + file_id, file_id,
'Downloading file JSON metadata', headers={

356
yt_dlp/extractor/cbc.py
View file

@ -1,4 +1,5 @@
import base64
import functools
import json
import re
import time
@ -6,17 +7,24 @@ import urllib.parse
import xml.etree.ElementTree
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
join_nonempty,
js_to_json,
mimetype2ext,
orderedSet,
parse_iso8601,
replace_extension,
smuggle_url,
strip_or_none,
traverse_obj,
try_get,
update_url,
url_basename,
url_or_none,
)
@ -149,6 +157,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
_GEO_COUNTRIES = ['CA']
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
'md5': '64d25f841ddf4ddb28a235338af32e2c',
@ -172,21 +181,20 @@ class CBCPlayerIE(InfoExtractor):
'description': 'md5:dd3b692f0a139b0369943150bd1c46a9',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'categories': ['All in a Weekend Montreal'],
'tags': 'count:11',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
'genres': ['Other'],
},
}, {
'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'ext': 'mp4',
@ -194,107 +202,168 @@ class CBCPlayerIE(InfoExtractor):
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'categories': ['Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
'media_type': 'Excerpt',
'genres': ['News'],
},
'params': {'skip_download': 'm3u8'},
}, {
# Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
'url': 'https://www.cbc.ca/player/play/1.2985700',
'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
'info_dict': {
'id': '2657631896',
'id': '1.2985700',
'ext': 'mp3',
'title': 'CBC Montreal is organizing its first ever community hackathon!',
'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'categories': ['All in a Weekend Montreal'],
'tags': 'count:11',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
'genres': ['Other'],
},
}, {
'url': 'https://www.cbc.ca/player/play/1.1711287',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'id': '1.1711287',
'ext': 'mp4',
'title': 'Cancer survivor four times over',
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'categories': ['Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
'media_type': 'Excerpt',
'genres': ['News'],
},
'params': {'skip_download': 'm3u8'},
}, {
# Has subtitles
# These broadcasts expire after ~1 month, can find new test URL here:
# https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
'url': 'https://www.cbc.ca/player/play/1.7159484',
'md5': '6ed6cd0fc2ef568d2297ba68a763d455',
'url': 'https://www.cbc.ca/player/play/video/9.6424403',
'md5': '8025909eaffcf0adf59922904def9a5e',
'info_dict': {
'id': '2324213316001',
'id': '9.6424403',
'ext': 'mp4',
'title': 'The National | School boards sue social media giants',
'description': 'md5:4b4db69322fa32186c3ce426da07402c',
'timestamp': 1711681200,
'duration': 2743.400,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg',
'uploader': 'CBCC-NEW',
'title': 'The National | N.W.T. wildfire emergency',
'description': 'md5:ada33d36d1df69347ed575905bfd496c',
'timestamp': 1718589600,
'duration': 2692.833,
'subtitles': {
'en-US': [{
'name': 'English Captions',
'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
}],
},
'thumbnail': 'https://i.cbc.ca/ais/6272b5c6-5e78-4c05-915d-0e36672e33d1,1714756287822/full/max/0/default.jpg',
'chapters': 'count:5',
'upload_date': '20240329',
'categories': 'count:4',
'upload_date': '20240617',
'categories': ['News', 'The National', 'The National Latest Broadcasts'],
'series': 'The National - Full Show',
'tags': 'count:1',
'creators': ['News'],
'tags': ['The National'],
'location': 'Canada',
'media_type': 'Full Program',
'genres': ['News'],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/1.7194274',
'md5': '188b96cf6bdcb2540e178a6caa957128',
'info_dict': {
'id': '2334524995812',
'id': '1.7194274',
'ext': 'mp4',
'title': '#TheMoment a rare white spirit moose was spotted in Alberta',
'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3',
'timestamp': 1714788791,
'duration': 77.678,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg',
'uploader': 'CBCC-NEW',
'chapters': 'count:0',
'upload_date': '20240504',
'thumbnail': 'https://i.cbc.ca/ais/1.7194274,1717224990425/full/max/0/default.jpg',
'chapters': [],
'categories': 'count:3',
'series': 'The National',
'tags': 'count:15',
'creators': ['encoder'],
'tags': 'count:17',
'location': 'Canada',
'media_type': 'Excerpt',
'upload_date': '20240504',
'genres': ['News'],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6427282',
'info_dict': {
'id': '9.6427282',
'ext': 'mp4',
'title': 'Men\'s Soccer - Argentina vs Morocco',
'description': 'Argentina faces Morocco on the football pitch at Saint Etienne Stadium.',
'series': 'CBC Sports',
'media_type': 'Event Coverage',
'thumbnail': 'https://i.cbc.ca/ais/a4c5c0c2-99fa-4bd3-8061-5a63879c1b33,1718828053500/full/max/0/default.jpg',
'timestamp': 1721825400.0,
'upload_date': '20240724',
'duration': 10568.0,
'chapters': [],
'genres': [],
'tags': ['2024 Paris Olympic Games'],
'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
'location': 'Canada',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6459530',
'md5': '6c1bb76693ab321a2e99c347a1d5ecbc',
'info_dict': {
'id': '9.6459530',
'ext': 'mp4',
'title': 'Parts of Jasper incinerated as wildfire rages',
'description': 'md5:6f1caa8d128ad3f629257ef5fecf0962',
'series': 'The National',
'media_type': 'Excerpt',
'thumbnail': 'https://i.cbc.ca/ais/507c0086-31a2-494d-96e4-bffb1048d045,1721953984375/full/max/0/default.jpg',
'timestamp': 1721964091.012,
'upload_date': '20240726',
'duration': 952.285,
'chapters': [],
'genres': [],
'tags': 'count:23',
'categories': ['News (FAST)', 'News', 'The National', 'TV News Shows', 'The National '],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6420651',
'md5': '71a850c2c6ee5e912de169f5311bb533',
'info_dict': {
'id': '9.6420651',
'ext': 'mp4',
'title': 'Is it a breath of fresh air? Measuring air quality in Edmonton',
'description': 'md5:3922b92cc8b69212d739bd9dd095b1c3',
'series': 'CBC News Edmonton',
'media_type': 'Excerpt',
'thumbnail': 'https://i.cbc.ca/ais/73c4ab9c-7ad4-46ee-bb9b-020fdc01c745,1718214547576/full/max/0/default.jpg',
'timestamp': 1718220065.768,
'upload_date': '20240612',
'duration': 286.086,
'chapters': [],
'genres': ['News'],
'categories': ['News', 'Edmonton'],
'tags': 'count:7',
'location': 'Edmonton',
},
}, {
'url': 'cbcplayer:1.7159484',
@ -307,23 +376,113 @@ class CBCPlayerIE(InfoExtractor):
'only_matching': True,
}]
def _parse_param(self, asset_data, name):
return traverse_obj(asset_data, ('params', lambda _, v: v['name'] == name, 'value', {str}, any))
def _real_extract(self, url):
video_id = self._match_id(url)
if '.' in video_id:
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
video_id = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage,
'initial state', video_id)['video']['currentClip']['mediaId']
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
data = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip']
assets = traverse_obj(
data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
if not assets and (media_id := traverse_obj(data, ('mediaId', {str}))):
# XXX: Deprecated; CBC is migrating off of ThePlatform
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(
f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{media_id}?mbr=true&formats=MPEG4,FLV,MP3', {
'force_smil_url': True,
}),
'id': media_id,
'_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS
}
is_live = traverse_obj(data, ('media', 'streamType', {str})) == 'Live'
formats, subtitles = [], {}
for sub in traverse_obj(data, ('media', 'textTracks', lambda _, v: url_or_none(v['src']))):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['src'],
'name': sub.get('label'),
})
for asset in assets:
asset_key = asset['key']
asset_type = asset['type']
if asset_type != 'medianet':
self.report_warning(f'Skipping unsupported asset type "{asset_type}": {asset_key}')
continue
asset_data = self._download_json(asset_key, video_id, f'Downloading {asset_type} JSON')
ext = mimetype2ext(self._parse_param(asset_data, 'contentType'))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_data['url'], video_id, 'mp4', m3u8_id='hls', live=is_live)
formats.extend(fmts)
# Avoid slow/error-prone webvtt-over-m3u8 if direct https vtt is available
if not subtitles:
self._merge_subtitles(subs, target=subtitles)
if is_live or not fmts:
continue
# Check for direct https mp4 format
best_video_fmt = traverse_obj(fmts, (
lambda _, v: v.get('vcodec') != 'none' and v['tbr'], all,
{functools.partial(sorted, key=lambda x: x['tbr'])}, -1, {dict})) or {}
base_url = self._search_regex(
r'(https?://[^?#]+?/)hdntl=', best_video_fmt.get('url'), 'base url', default=None)
if not base_url or '/live/' in base_url:
continue
mp4_url = base_url + replace_extension(url_basename(best_video_fmt['url']), 'mp4')
if self._request_webpage(
HEADRequest(mp4_url), video_id, 'Checking for https format',
errnote=False, fatal=False):
formats.append({
**best_video_fmt,
'url': mp4_url,
'format_id': 'https-mp4',
'protocol': 'https',
'manifest_url': None,
'acodec': None,
})
else:
formats.append({
'url': asset_data['url'],
'ext': ext,
'vcodec': 'none' if self._parse_param(asset_data, 'mediaType') == 'audio' else None,
})
chapters = traverse_obj(data, (
'media', 'chapters', lambda _, v: float(v['startTime']) is not None, {
'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}),
'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}),
'title': ('name', {str}),
}))
# Filter out pointless single chapters with start_time==0 and no end_time
if len(chapters) == 1 and not (chapters[0].get('start_time') or chapters[0].get('end_time')):
chapters = []
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(
f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{video_id}?mbr=true&formats=MPEG4,FLV,MP3', {
'force_smil_url': True,
}),
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('description', {str.strip}),
'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}),
'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}),
'media_type': ('media', 'clipType', {str}),
'series': ('showName', {str}),
'season_number': ('media', 'season', {int_or_none}),
'duration': ('media', 'duration', {float_or_none}, {lambda x: None if is_live else x}),
'location': ('media', 'region', {str}),
'tags': ('tags', ..., 'name', {str}),
'genres': ('media', 'genre', all),
'categories': ('categories', ..., 'name', {str}),
}),
'id': video_id,
'_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
'is_live': is_live,
}
@ -647,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor):
'title': 'Ottawa',
'description': 'The live TV channel and local programming from Ottawa',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
'is_live': True,
'live_status': 'is_live',
'id': 'AyqZwxRqh8EH',
'ext': 'mp4',
'timestamp': 1492106160,
'upload_date': '20170413',
'release_timestamp': 1492106160,
'release_date': '20170413',
'uploader': 'CBCC-NEW',
},
'skip': 'Live might have ended',
@ -680,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor):
'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
'live_status': 'is_live',
'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
'timestamp': 1679706000,
'upload_date': '20230325',
'release_timestamp': 1679706000,
'release_date': '20230325',
},
'params': {'skip_download': True},
'skip': 'Live might have ended',
},
{ # event replay (medianetlive)
'url': 'https://gem.cbc.ca/live-event/42314',
'md5': '297a9600f554f2258aed01514226a697',
'info_dict': {
'id': '42314',
'ext': 'mp4',
'live_status': 'was_live',
'title': 'Women\'s Soccer - Canada vs New Zealand',
'description': 'md5:36200e5f1a70982277b5a6ecea86155d',
'thumbnail': r're:https://.+default\.jpg',
'release_timestamp': 1721917200,
'release_date': '20240725',
},
'params': {'skip_download': True},
'skip': 'Replay might no longer be available',
},
{ # event replay (medianetlive)
'url': 'https://gem.cbc.ca/live-event/43273',
'only_matching': True,
},
]
_GEO_COUNTRIES = ['CA']
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
# Two types of metadata JSON
# Three types of video_info JSON: info in root, freeTv stream/item, event replay
if not video_info.get('formattedIdMedia'):
video_info = traverse_obj(
video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
get_all=False, default={})
if traverse_obj(video_info, ('event', 'key')) == video_id:
video_info = video_info['event']
else:
video_info = traverse_obj(video_info, (
('freeTv', ('streams', ...)), 'items',
lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {}
video_stream_id = video_info.get('formattedIdMedia')
if not video_stream_id:
raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
raise ExtractorError(
'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
stream_data = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
'appCode': 'mpx',
'connectionType': 'hd',
'deviceType': 'ipad',
'idMedia': video_stream_id,
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestType': 'desktop',
})
live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live'
release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601}))
if live_status == 'is_live' and release_timestamp and release_timestamp > time.time():
formats = []
live_status = 'is_upcoming'
self.raise_no_formats('This livestream has not yet started', expected=True)
else:
stream_data = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
'appCode': 'medianetlive',
'connectionType': 'hd',
'deviceType': 'ipad',
'idMedia': video_stream_id,
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestType': 'desktop',
})
formats = self._extract_m3u8_formats(
stream_data['url'], video_id, 'mp4', live=live_status == 'is_live')
return {
'id': video_id,
'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
'is_live': True,
'formats': formats,
'live_status': live_status,
'release_timestamp': release_timestamp,
**traverse_obj(video_info, {
'title': 'title',
'description': 'description',
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('images', 'card', 'url'),
'timestamp': ('airDate', {parse_iso8601}),
}),
}

69
yt_dlp/extractor/cellebrite.py
View file

@ -1,63 +1,50 @@
from .common import InfoExtractor
from ..utils import traverse_obj
from .vidyard import VidyardBaseIE, VidyardIE
from ..utils import ExtractorError, make_archive_id, url_basename
class CellebriteIE(InfoExtractor):
class CellebriteIE(VidyardBaseIE):
_VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
'info_dict': {
'id': '16025876',
'id': 'ZqmUss3dQfEMGpauambPuH',
'display_id': '16025876',
'ext': 'mp4',
'description': 'md5:174571cb97083fd1d457d75c684f4e2b',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
'duration': 455,
'tags': [],
'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
'duration': 455.979,
'_old_archive_ids': ['cellebrite 16025876'],
},
}, {
'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
'info_dict': {
'id': '29018255',
'id': 'QV1U8a2yzcxigw7VFnqKyg',
'display_id': '29018255',
'ext': 'mp4',
'duration': 134,
'tags': [],
'description': 'md5:e9a3d124c7287b0b07bad2547061cacf',
'title': 'How to Lawfully Collect the Maximum Amount of Data From Android Devices',
'description': 'md5:0e943a9ac14c374d5d74faed634d773c',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
'title': 'Android Extractions Explained',
'duration': 134.315,
'_old_archive_ids': ['cellebrite 29018255'],
},
}]
def _get_formats_and_subtitles(self, json_data, display_id):
formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []]
subtitles = {}
for url in traverse_obj(json_data, ('hls', ..., 'url')) or []:
fmt, sub = self._extract_m3u8_formats_and_subtitles(
url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'})
formats.extend(fmt)
self._merge_subtitles(sub, target=subtitles)
return formats, subtitles
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
slug = self._match_id(url)
webpage = self._download_webpage(url, slug)
vidyard_url = next(VidyardIE._extract_embed_urls(url, webpage), None)
if not vidyard_url:
raise ExtractorError('No Vidyard video embeds found on page')
player_uuid = self._search_regex(
r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID')
json_data = self._download_json(
f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0]
video_id = url_basename(vidyard_url)
info = self._process_video_json(self._fetch_video_json(video_id)['chapters'][0], video_id)
if info.get('display_id'):
info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
if thumbnail := self._og_search_thumbnail(webpage, default=None):
info.setdefault('thumbnails', []).append({'url': thumbnail})
formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id)
return {
'id': str(json_data['videoId']),
'title': json_data.get('name') or self._og_search_title(webpage),
'formats': formats,
'subtitles': subtitles,
'description': json_data.get('description') or self._og_search_description(webpage),
'duration': json_data.get('seconds'),
'tags': json_data.get('tags'),
'thumbnail': self._og_search_thumbnail(webpage),
'http_headers': {'Referer': 'https://play.vidyard.com/'},
'description': self._og_search_description(webpage, default=None),
**info,
}

37
yt_dlp/extractor/chzzk.py
View file

@ -36,7 +36,7 @@ class CHZZKLiveIE(InfoExtractor):
def _real_extract(self, url):
channel_id = self._match_id(url)
live_detail = self._download_json(
f'https://api.chzzk.naver.com/service/v2/channels/{channel_id}/live-detail', channel_id,
f'https://api.chzzk.naver.com/service/v3/channels/{channel_id}/live-detail', channel_id,
note='Downloading channel info', errnote='Unable to download channel info')['content']
if live_detail.get('status') == 'CLOSE':
@ -106,12 +106,45 @@ class CHZZKVideoIE(InfoExtractor):
'upload_date': '20231219',
'view_count': int,
},
'skip': 'Replay video is expired',
}, {
# Manually uploaded video
'url': 'https://chzzk.naver.com/video/1980',
'info_dict': {
'id': '1980',
'ext': 'mp4',
'title': '※시청주의※한번보면 잊기 힘든 영상',
'channel': '라디유radiyu',
'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 95,
'timestamp': 1703102631.722,
'upload_date': '20231220',
'view_count': int,
},
}, {
# Partner channel replay video
'url': 'https://chzzk.naver.com/video/2458',
'info_dict': {
'id': '2458',
'ext': 'mp4',
'title': '첫 방송',
'channel': '강지',
'channel_id': 'b5ed5db484d04faf4d150aedd362f34b',
'channel_is_verified': True,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 4433,
'timestamp': 1703307460.214,
'upload_date': '20231223',
'view_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_meta = self._download_json(
f'https://api.chzzk.naver.com/service/v2/videos/{video_id}', video_id,
f'https://api.chzzk.naver.com/service/v3/videos/{video_id}', video_id,
note='Downloading video info', errnote='Unable to download video info')['content']
formats, subtitles = self._extract_mpd_formats_and_subtitles(
f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}', video_id,

8
yt_dlp/extractor/common.py
View file

@ -3150,7 +3150,7 @@ class InfoExtractor:
})
return formats, subtitles
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None, _headers=None):
def absolute_url(item_url):
return urljoin(base_url, item_url)
@ -3174,11 +3174,11 @@ class InfoExtractor:
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
preference=preference, quality=quality, fatal=False)
preference=preference, quality=quality, fatal=False, headers=_headers)
elif ext == 'mpd':
is_plain_url = False
formats = self._extract_mpd_formats(
full_url, video_id, mpd_id=mpd_id, fatal=False)
full_url, video_id, mpd_id=mpd_id, fatal=False, headers=_headers)
else:
is_plain_url = True
formats = [{
@ -3272,6 +3272,8 @@ class InfoExtractor:
})
for f in media_info['formats']:
f.setdefault('http_headers', {})['Referer'] = base_url
if _headers:
f['http_headers'].update(_headers)
if media_info['formats'] or media_info['subtitles']:
entries.append(media_info)
return entries

42
yt_dlp/extractor/digitalconcerthall.py
View file

@ -1,6 +1,8 @@
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
parse_codecs,
try_get,
url_or_none,
urlencode_postdata,
@ -12,6 +14,7 @@ class DigitalConcertHallIE(InfoExtractor):
IE_DESC = 'DigitalConcertHall extractor'
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
_OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
_USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Safari/605.1.15'
_ACCESS_TOKEN = None
_NETRC_MACHINE = 'digitalconcerthall'
_TESTS = [{
@ -68,33 +71,42 @@ class DigitalConcertHallIE(InfoExtractor):
}]
def _perform_login(self, username, password):
token_response = self._download_json(
login_token = self._download_json(
self._OAUTH_URL,
None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({
'affiliate': 'none',
'grant_type': 'device',
'device_vendor': 'unknown',
# device_model 'Safari' gets split streams of 4K/HEVC video and lossless/FLAC audio
'device_model': 'unknown' if self._configuration_arg('prefer_combined_hls') else 'Safari',
'app_id': 'dch.webapp',
'app_version': '1.0.0',
'app_distributor': 'berlinphil',
'app_version': '1.84.0',
'client_secret': '2ySLN+2Fwb',
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
self._ACCESS_TOKEN = token_response['access_token']
'Accept': 'application/json',
'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
'User-Agent': self._USER_AGENT,
})['access_token']
try:
self._download_json(
login_response = self._download_json(
self._OAUTH_URL,
None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({
'grant_type': 'password',
'username': username,
'password': password,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Accept': 'application/json',
'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
'Referer': 'https://www.digitalconcerthall.com',
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
'Authorization': f'Bearer {login_token}',
'User-Agent': self._USER_AGENT,
})
except ExtractorError:
self.raise_login_required(msg='Login info incorrect')
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 401:
raise ExtractorError('Invalid username or password', expected=True)
raise
self._ACCESS_TOKEN = login_response['access_token']
def _real_initialize(self):
if not self._ACCESS_TOKEN:
@ -108,11 +120,15 @@ class DigitalConcertHallIE(InfoExtractor):
'Accept': 'application/json',
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
'Accept-Language': language,
'User-Agent': self._USER_AGENT,
})
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', fatal=False))
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']))
yield {
'id': video_id,
@ -140,13 +156,15 @@ class DigitalConcertHallIE(InfoExtractor):
f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
'Accept': 'application/json',
'Accept-Language': language,
'User-Agent': self._USER_AGENT,
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
})
album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
if type_ == 'work':
videos = [videos[int(part) - 1]]
album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name', {str}))
thumbnail = traverse_obj(vid_info, (
'image', ..., {self._proto_relative_url}, {url_or_none},
{lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size

115
yt_dlp/extractor/discovery.py
View file

@ -1,115 +0,0 @@
import random
import string
import urllib.parse
from .discoverygo import DiscoveryGoBaseIE
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError
class DiscoveryIE(DiscoveryGoBaseIE):
_VALID_URL = r'''(?x)https?://
(?P<site>
go\.discovery|
www\.
(?:
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc
)|
watch\.
(?:
hgtv|
foodnetwork|
travelchannel|
diynetwork|
cookingchanneltv|
motortrend
)
)\.com/tv-shows/(?P<show_slug>[^/]+)/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
_TESTS = [{
'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
'info_dict': {
'id': '5a2f35ce6b66d17a5026e29e',
'ext': 'mp4',
'title': 'Riding with Matthew Perry',
'description': 'md5:a34333153e79bc4526019a5129e7f878',
'duration': 84,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, {
'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision',
'only_matching': True,
}, {
'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road',
'only_matching': True,
}, {
# using `show_slug` is important to get the correct video data
'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special',
'only_matching': True,
}]
_GEO_COUNTRIES = ['US']
_GEO_BYPASS = False
_API_BASE_URL = 'https://api.discovery.com/v1/'
def _real_extract(self, url):
site, show_slug, display_id = self._match_valid_url(url).groups()
access_token = None
cookies = self._get_cookies(url)
# prefer Affiliate Auth Token over Anonymous Auth Token
auth_storage_cookie = cookies.get('eosAf') or cookies.get('eosAn')
if auth_storage_cookie and auth_storage_cookie.value:
auth_storage = self._parse_json(urllib.parse.unquote(
urllib.parse.unquote(auth_storage_cookie.value)),
display_id, fatal=False) or {}
access_token = auth_storage.get('a') or auth_storage.get('access_token')
if not access_token:
access_token = self._download_json(
f'https://{site}.com/anonymous', display_id,
'Downloading token JSON metadata', query={
'authRel': 'authorization',
'client_id': '3020a40c2356a645b4b4',
'nonce': ''.join(random.choices(string.ascii_letters, k=32)),
'redirectUri': 'https://www.discovery.com/',
})['access_token']
headers = self.geo_verification_headers()
headers['Authorization'] = 'Bearer ' + access_token
try:
video = self._download_json(
self._API_BASE_URL + 'content/videos',
display_id, 'Downloading content JSON metadata',
headers=headers, query={
'embed': 'show.name',
'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags',
'slug': display_id,
'show_slug': show_slug,
})[0]
video_id = video['id']
stream = self._download_json(
self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
e_description = self._parse_json(
e.cause.response.read().decode(), display_id)['description']
if 'resource not available for country' in e_description:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
if 'Authorized Networks' in e_description:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
raise ExtractorError(e_description)
raise
return self._extract_video_info(video, stream, display_id)

171
yt_dlp/extractor/discoverygo.py
View file

@ -1,171 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
extract_attributes,
int_or_none,
parse_age_limit,
remove_end,
unescapeHTML,
url_or_none,
)
class DiscoveryGoBaseIE(InfoExtractor):
_VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc|
velocitychannel
)go\.com/%s(?P<id>[^/?#&]+)'''
def _extract_video_info(self, video, stream, display_id):
title = video['name']
if not stream:
if video.get('authenticated') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream')
STREAM_URL_SUFFIX = 'streamUrl'
formats = []
for stream_kind in ('', 'hds'):
suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
stream_url = stream.get(f'{stream_kind}{suffix}')
if not stream_url:
continue
if stream_kind == '':
formats.extend(self._extract_m3u8_formats(
stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif stream_kind == 'hds':
formats.extend(self._extract_f4m_formats(
stream_url, display_id, f4m_id=stream_kind, fatal=False))
video_id = video.get('id') or display_id
description = video.get('description', {}).get('detailed')
duration = int_or_none(video.get('duration'))
series = video.get('show', {}).get('name')
season_number = int_or_none(video.get('season', {}).get('number'))
episode_number = int_or_none(video.get('episodeNumber'))
tags = video.get('tags')
age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
subtitles = {}
captions = stream.get('captions')
if isinstance(captions, list):
for caption in captions:
subtitle_url = url_or_none(caption.get('fileUrl'))
if not subtitle_url or not subtitle_url.startswith('http'):
continue
lang = caption.get('fileLang', 'en')
ext = determine_ext(subtitle_url)
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
'ext': 'ttml' if ext == 'xml' else ext,
})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'duration': duration,
'series': series,
'season_number': season_number,
'episode_number': episode_number,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
'subtitles': subtitles,
}
class DiscoveryGoIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
_GEO_COUNTRIES = ['US']
_TEST = {
'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
'info_dict': {
'id': '58c167d86b66d12f2addeb01',
'ext': 'mp4',
'title': 'Reaper Madness',
'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
'duration': 2519,
'series': 'Bering Sea Gold',
'season_number': 8,
'episode_number': 6,
'age_limit': 14,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
container = extract_attributes(
self._search_regex(
r'(<div[^>]+class=["\']video-player-container[^>]+>)',
webpage, 'video container'))
video = self._parse_json(
container.get('data-video') or container.get('data-json'),
display_id)
stream = video.get('stream')
return self._extract_video_info(video, stream, display_id)
class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
_TEST = {
'url': 'https://www.discoverygo.com/bering-sea-gold/',
'info_dict': {
'id': 'bering-sea-gold',
'title': 'Bering Sea Gold',
'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
},
'playlist_mincount': 6,
}
@classmethod
def suitable(cls, url):
return False if DiscoveryGoIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
data = self._parse_json(
mobj.group('json'), display_id,
transform_source=unescapeHTML, fatal=False)
if not isinstance(data, dict) or data.get('type') != 'episode':
continue
episode_url = data.get('socialUrl')
if not episode_url:
continue
entries.append(self.url_result(
episode_url, ie=DiscoveryGoIE.ie_key(),
video_id=data.get('id')))
return self.playlist_result(
entries, display_id,
remove_end(self._og_search_title(
webpage, fatal=False), ' | Discovery GO'),
self._og_search_description(webpage))

6
yt_dlp/extractor/douyutv.py
View file

@ -24,8 +24,9 @@ from ..utils import (
class DouyuBaseIE(InfoExtractor):
def _download_cryptojs_md5(self, video_id):
for url in [
# XXX: Do NOT use cdn.bootcdn.net; ref: https://sansec.io/research/polyfill-supply-chain-attack
'https://cdnjs.cloudflare.com/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
'https://cdn.bootcdn.net/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
'https://unpkg.com/cryptojslib@3.1.2/rollups/md5.js',
]:
js_code = self._download_webpage(
url, video_id, note='Downloading signing dependency', fatal=False)
@ -35,7 +36,8 @@ class DouyuBaseIE(InfoExtractor):
raise ExtractorError('Unable to download JS dependency (crypto-js/md5)')
def _get_cryptojs_md5(self, video_id):
return self.cache.load('douyu', 'crypto-js-md5') or self._download_cryptojs_md5(video_id)
return self.cache.load(
'douyu', 'crypto-js-md5', min_ver='2024.07.04') or self._download_cryptojs_md5(video_id)
def _calc_sign(self, sign_func, video_id, a):
b = uuid.uuid4().hex

453
yt_dlp/extractor/dplay.py
View file

@ -346,8 +346,16 @@ class HGTVDeIE(DPlayBaseIE):
class DiscoveryPlusBaseIE(DPlayBaseIE):
"""Subclasses must set _PRODUCT, _DISCO_API_PARAMS"""
_DISCO_CLIENT_VER = '27.43.0'
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6'
headers.update({
'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
def _download_video_playback_info(self, disco_base, video_id, headers):
return self._download_json(
@ -368,6 +376,26 @@ class DiscoveryPlusBaseIE(DPlayBaseIE):
class GoDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://go.discovery.com/video/in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
'info_dict': {
'id': '5352642',
'display_id': 'in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
'ext': 'mp4',
'title': 'Trapped in a Twister',
'description': 'Twisters destroy Midwest towns, trapping spotters in the eye of the storm.',
'episode_number': 1,
'episode': 'Episode 1',
'season_number': 1,
'season': 'Season 1',
'series': 'In The Eye Of The Storm',
'duration': 2490.237,
'upload_date': '20240715',
'timestamp': 1721008800,
'tags': [],
'creators': ['Discovery'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/10/5e39637d-cabf-3ab3-8e9a-f4e9d37bc036.jpeg',
},
}, {
'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
'info_dict': {
'id': '4164906',
@ -395,6 +423,26 @@ class GoDiscoveryIE(DiscoveryPlusBaseIE):
class TravelChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.travelchannel.com/video/the-dead-files-travel-channel/protect-the-children',
'info_dict': {
'id': '4710177',
'display_id': 'the-dead-files-travel-channel/protect-the-children',
'ext': 'mp4',
'title': 'Protect the Children',
'description': 'An evil presence threatens an Ohio woman\'s children and marriage.',
'season_number': 14,
'season': 'Season 14',
'episode_number': 10,
'episode': 'Episode 10',
'series': 'The Dead Files',
'duration': 2550.481,
'timestamp': 1664510400,
'upload_date': '20220930',
'tags': [],
'creators': ['Travel Channel'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/17/5e45eace-de5d-343a-9293-f400a2aa77d5.jpeg',
},
}, {
'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely',
'info_dict': {
'id': '2220256',
@ -422,6 +470,26 @@ class TravelChannelIE(DiscoveryPlusBaseIE):
class CookingChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.cookingchanneltv.com/video/bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
'info_dict': {
'id': '5350005',
'ext': 'mp4',
'display_id': 'bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
'title': 'Titans vs Marcus Samuelsson',
'description': 'Marcus Samuelsson throws his legendary global tricks at the Titans.',
'episode_number': 1,
'episode': 'Episode 1',
'season_number': 3,
'season': 'Season 3',
'series': 'Bobby\'s Triple Threat',
'duration': 2520.851,
'upload_date': '20240710',
'timestamp': 1720573200,
'tags': [],
'creators': ['Food Network'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/04/529cd095-27ec-35c5-84e9-90ebd3e5d2da.jpeg',
},
}, {
'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
'info_dict': {
'id': '2348634',
@ -449,6 +517,22 @@ class CookingChannelIE(DiscoveryPlusBaseIE):
class HGTVUsaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.hgtv.com/video/flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
'info_dict': {
'id': '5025585',
'display_id': 'flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
'ext': 'mp4',
'title': 'Flip or Flop: The Final Flip',
'description': 'Tarek and Christina are going their separate ways after one last flip!',
'series': 'Flip or Flop: The Final Flip',
'duration': 2580.644,
'upload_date': '20231101',
'timestamp': 1698811200,
'tags': [],
'creators': ['HGTV'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/11/27/455caa6c-1462-3f14-b63d-a026d7a5e6d3.jpeg',
},
}, {
'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house',
'info_dict': {
'id': '4289736',
@ -476,6 +560,26 @@ class HGTVUsaIE(DiscoveryPlusBaseIE):
class FoodNetworkIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.foodnetwork.com/video/guys-grocery-games-food-network/wild-in-the-aisles',
'info_dict': {
'id': '2152549',
'display_id': 'guys-grocery-games-food-network/wild-in-the-aisles',
'ext': 'mp4',
'title': 'Wild in the Aisles',
'description': 'The chefs make spaghetti and meatballs with "Out of Stock" ingredients.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Guy\'s Grocery Games',
'tags': [],
'creators': ['Food Network'],
'duration': 2520.651,
'upload_date': '20230623',
'timestamp': 1687492800,
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/06/15/37fb5333-cad2-3dbb-af7c-c20ec77c89c6.jpeg',
},
}, {
'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly',
'info_dict': {
'id': '4116449',
@ -503,6 +607,26 @@ class FoodNetworkIE(DiscoveryPlusBaseIE):
class DestinationAmericaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.destinationamerica.com/video/bbq-pit-wars-destination-america/smoke-on-the-water',
'info_dict': {
'id': '2218409',
'display_id': 'bbq-pit-wars-destination-america/smoke-on-the-water',
'ext': 'mp4',
'title': 'Smoke on the Water',
'description': 'The pitmasters head to Georgia for the Smoke on the Water BBQ Festival.',
'season_number': 2,
'season': 'Season 2',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'BBQ Pit Wars',
'tags': [],
'creators': ['Destination America'],
'duration': 2614.878,
'upload_date': '20230623',
'timestamp': 1687492800,
'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/c0f8e85d-9a10-3e6f-8e43-f6faafa81ba2.jpeg',
},
}, {
'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
'info_dict': {
'id': '4210904',
@ -530,6 +654,26 @@ class DestinationAmericaIE(DiscoveryPlusBaseIE):
class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.investigationdiscovery.com/video/deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
'info_dict': {
'id': '5341132',
'display_id': 'deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
'ext': 'mp4',
'title': 'RIP Bianca',
'description': 'A teenage influencer discovers an online world of threat, harm and danger.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 3,
'episode': 'Episode 3',
'series': 'Deadly Influence: The Social Media Murders',
'creators': ['Investigation Discovery'],
'tags': [],
'duration': 2490.888,
'upload_date': '20240618',
'timestamp': 1718672400,
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/06/15/b567c774-9e44-3c6c-b0ba-db860a73e812.jpeg',
},
}, {
'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown',
'info_dict': {
'id': '2139409',
@ -557,6 +701,26 @@ class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
class AmHistoryChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.ahctv.com/video/blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
'info_dict': {
'id': '2139199',
'display_id': 'blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
'ext': 'mp4',
'title': 'Battle of Bull Run',
'description': 'Two untested armies clash in the first real battle of the Civil War.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Blood and Fury: America\'s Civil War',
'duration': 2612.509,
'upload_date': '20220923',
'timestamp': 1663905600,
'creators': ['AHC'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/4af61bd7-d705-3108-82c4-1a6e541e20fa.jpeg',
},
}, {
'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army',
'info_dict': {
'id': '2309730',
@ -584,6 +748,26 @@ class AmHistoryChannelIE(DiscoveryPlusBaseIE):
class ScienceChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.sciencechannel.com/video/spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
'info_dict': {
'id': '2347335',
'display_id': 'spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
'ext': 'mp4',
'title': 'Mystery of the Dead Planets',
'description': 'Astronomers unmask the truly destructive nature of the cosmos.',
'season_number': 7,
'season': 'Season 7',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Space\'s Deepest Secrets',
'duration': 2524.989,
'upload_date': '20230128',
'timestamp': 1674882000,
'creators': ['Science'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/30/3796829d-aead-3f9a-bd8d-e49048b3cdca.jpeg',
},
}, {
'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
'info_dict': {
'id': '2842849',
@ -608,36 +792,29 @@ class ScienceChannelIE(DiscoveryPlusBaseIE):
}
class DIYNetworkIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
'info_dict': {
'id': '2309730',
'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas',
'ext': 'mp4',
'title': 'Bringing Beach Life to Texas',
'description': 'The Pool Kings give a family a day at the beach in their own backyard.',
'season_number': 10,
'episode_number': 2,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
'only_matching': True,
}]
_PRODUCT = 'diy'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.diynetwork.com',
'realm': 'go',
'country': 'us',
}
class DiscoveryLifeIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoverylife.com/video/er-files-discovery-life-atve-us/sweet-charity',
'info_dict': {
'id': '2347614',
'display_id': 'er-files-discovery-life-atve-us/sweet-charity',
'ext': 'mp4',
'title': 'Sweet Charity',
'description': 'The staff at Charity Hospital treat a serious foot infection.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'ER Files',
'duration': 2364.261,
'upload_date': '20230721',
'timestamp': 1689912000,
'creators': ['Discovery Life'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/16/4b6f0124-360b-3546-b6a4-5552db886b86.jpeg',
},
}, {
'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma',
'info_dict': {
'id': '2218238',
@ -665,6 +842,26 @@ class DiscoveryLifeIE(DiscoveryPlusBaseIE):
class AnimalPlanetIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.animalplanet.com/video/mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
'info_dict': {
'id': '4650835',
'display_id': 'mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
'ext': 'mp4',
'title': 'The Demon of Peru',
'description': 'In Peru, a farming village is being terrorized by a “man-like beast.”',
'season_number': 1,
'season': 'Season 1',
'episode_number': 4,
'episode': 'Episode 4',
'series': 'Mysterious Creatures with Forrest Galante',
'duration': 2490.488,
'upload_date': '20230111',
'timestamp': 1673413200,
'creators': ['Animal Planet'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/01/6dbaa833-9a2e-3fee-9381-c19eddf67c0c.jpeg',
},
}, {
'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
'info_dict': {
'id': '3338923',
@ -692,6 +889,26 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE):
class TLCIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://go.tlc.com/video/90-day-the-last-resort-tlc-atve-us/the-last-chance',
'info_dict': {
'id': '5186422',
'display_id': '90-day-the-last-resort-tlc-atve-us/the-last-chance',
'ext': 'mp4',
'title': 'The Last Chance',
'description': 'Infidelity shakes Kalani and Asuelu\'s world, and Angela threatens divorce.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': '90 Day: The Last Resort',
'duration': 5123.91,
'upload_date': '20230815',
'timestamp': 1692061200,
'creators': ['TLC'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2023/08/08/0ee367e2-ac76-334d-bf23-dbf796696a24.jpeg',
},
}, {
'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1',
'info_dict': {
'id': '2206540',
@ -716,93 +933,8 @@ class TLCIE(DiscoveryPlusBaseIE):
}
class MotorTrendIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?motortrend\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
'info_dict': {
'id': '"4859182"',
'display_id': 'double-dakotas',
'ext': 'mp4',
'title': 'Double Dakotas',
'description': 'Tylers buy-one-get-one Dakota deal has the Wizard pulling double duty.',
'season_number': 2,
'episode_number': 3,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
'only_matching': True,
}]
_PRODUCT = 'vel'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.motortrend.com',
'realm': 'go',
'country': 'us',
}
class MotorTrendOnDemandIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?motortrend(?:ondemand\.com|\.com/plus)/detail' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.motortrendondemand.com/detail/wheelstanding-dump-truck-stubby-bobs-comeback/37699/784',
'info_dict': {
'id': '37699',
'display_id': 'wheelstanding-dump-truck-stubby-bobs-comeback/37699',
'ext': 'mp4',
'title': 'Wheelstanding Dump Truck! Stubby Bob’s Comeback',
'description': 'md5:996915abe52a1c3dfc83aecea3cce8e7',
'season_number': 5,
'episode_number': 52,
'episode': 'Episode 52',
'season': 'Season 5',
'thumbnail': r're:^https?://.+\.jpe?g$',
'timestamp': 1388534401,
'duration': 1887.345,
'creator': 'Originals',
'series': 'Roadkill',
'upload_date': '20140101',
'tags': [],
},
}, {
'url': 'https://www.motortrend.com/plus/detail/roadworthy-rescues-teaser-trailer/4922860/',
'info_dict': {
'id': '4922860',
'ext': 'mp4',
'title': 'Roadworthy Rescues | Teaser Trailer',
'description': 'Derek Bieri helps Freiburger and Finnegan with their \'68 big-block Dart.',
'display_id': 'roadworthy-rescues-teaser-trailer/4922860',
'creator': 'Originals',
'series': 'Roadworthy Rescues',
'thumbnail': r're:^https?://.+\.jpe?g$',
'upload_date': '20220907',
'timestamp': 1662523200,
'duration': 1066.356,
'tags': [],
},
}, {
'url': 'https://www.motortrend.com/plus/detail/ugly-duckling/2450033/12439',
'only_matching': True,
}]
_PRODUCT = 'MTOD'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.motortrendondemand.com',
'realm': 'motortrend',
'country': 'us',
}
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:4.39.1-gi1',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
class DiscoveryPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
'info_dict': {
@ -823,14 +955,45 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE):
}, {
'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/gb/video/olympics/dplus-sport-dplus-sport-sport/rugby-sevens-australia-samoa',
'only_matching': True,
}]
_PRODUCT = 'dplus_us'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.discoveryplus.com',
'realm': 'go',
'country': 'us',
}
_PRODUCT = None
_DISCO_API_PARAMS = None
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
def _real_extract(self, url):
video_id, country = self._match_valid_url(url).group('id', 'country')
if not country:
country = 'us'
self._PRODUCT = f'dplus_{country}'
if country in ('br', 'ca', 'us'):
self._DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.discoveryplus.com',
'realm': 'go',
'country': country,
}
else:
self._DISCO_API_PARAMS = {
'disco_host': 'eu1-prod-direct.discoveryplus.com',
'realm': 'dplay',
'country': country,
}
return self._get_disco_api_info(url, video_id, **self._DISCO_API_PARAMS)
class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE):
@ -984,16 +1147,22 @@ class DiscoveryPlusShowBaseIE(DPlayBaseIE):
class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno',
'only_matching': True,
}]
_PRODUCT = 'dplus_us'
_PRODUCT = 'dplus_it'
_DISCO_API_PARAMS = {
'disco_host': 'eu1-prod-direct.discoveryplus.com',
'realm': 'dplay',
@ -1002,8 +1171,8 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6',
'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
@ -1044,39 +1213,3 @@ class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE):
_SHOW_STR = 'show'
_INDEX = 4
_VIDEO_IE = DiscoveryPlusIndiaIE
class GlobalCyclingNetworkPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://plus\.globalcyclingnetwork\.com/watch/(?P<id>\d+)'
_TESTS = [{
'url': 'https://plus.globalcyclingnetwork.com/watch/1397691',
'info_dict': {
'id': '1397691',
'ext': 'mp4',
'title': 'The Athertons: Mountain Biking\'s Fastest Family',
'description': 'md5:75a81937fcd8b989eec6083a709cd837',
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/04/eb9e3026-4849-3001-8281-9356466f0557.png',
'series': 'gcn',
'creator': 'Gcn',
'upload_date': '20210309',
'timestamp': 1615248000,
'duration': 2531.0,
'tags': [],
},
'skip': 'Subscription required',
'params': {'skip_download': 'm3u8'},
}]
_PRODUCT = 'web'
_DISCO_API_PARAMS = {
'disco_host': 'disco-api-prod.globalcyclingnetwork.com',
'realm': 'gcn',
'country': 'us',
}
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:27.3.2',
'Authorization': self._get_auth(disco_base, display_id, realm),
})

23
yt_dlp/extractor/epidemicsound.py
View file

@ -2,6 +2,7 @@ from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
join_nonempty,
orderedSet,
parse_iso8601,
parse_qs,
@ -13,7 +14,7 @@ from ..utils import (
class EpidemicSoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/track/(?P<id>[0-9a-zA-Z]+)'
_VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/(?:(?P<sfx>sound-effects/tracks)|track)/(?P<id>[0-9a-zA-Z-]+)'
_TESTS = [{
'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/',
'md5': 'd98ff2ddb49e8acab9716541cbc9dfac',
@ -47,6 +48,20 @@ class EpidemicSoundIE(InfoExtractor):
'release_timestamp': 1700535606,
'release_date': '20231121',
},
}, {
'url': 'https://www.epidemicsound.com/sound-effects/tracks/2f02f54b-9faa-4daf-abac-1cfe9e9cef69/',
'md5': '35d7cf05bd8b614a84f0495a05de9388',
'info_dict': {
'id': '208931',
'ext': 'mp3',
'upload_date': '20240603',
'timestamp': 1717436529,
'categories': ['appliance'],
'display_id': '6b2NXLURPr',
'duration': 1.0,
'title': 'Oven, Grill, Door Open 01',
'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/default-sfx/3000x3000.jpg',
},
}]
@staticmethod
@ -77,8 +92,10 @@ class EpidemicSoundIE(InfoExtractor):
return f
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(f'https://www.epidemicsound.com/json/track/{video_id}', video_id)
video_id, is_sfx = self._match_valid_url(url).group('id', 'sfx')
json_data = self._download_json(join_nonempty(
'https://www.epidemicsound.com/json/track',
is_sfx and 'kosmos-id', video_id, delim='/'), video_id)
thumbnails = traverse_obj(json_data, [('imageUrl', 'cover')])
thumb_base_url = traverse_obj(json_data, ('coverArt', 'baseUrl', {url_or_none}))

67
yt_dlp/extractor/facebook.py
View file

@ -571,16 +571,21 @@ class FacebookIE(InfoExtractor):
# Formats larger than ~500MB will return error 403 unless chunk size is regulated
f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20
def extract_relay_data(_filter):
return self._parse_json(self._search_regex(
rf'data-sjs>({{.*?{_filter}.*?}})</script>',
webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
def yield_all_relay_data(_filter):
for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})</script>', webpage):
yield self._parse_json(relay_data, video_id, fatal=False) or {}
def extract_relay_prefetched_data(_filter):
return traverse_obj(extract_relay_data(_filter), (
'require', (None, (..., ..., ..., '__bbox', 'require')),
def extract_relay_data(_filter):
return next(filter(None, yield_all_relay_data(_filter)), {})
def extract_relay_prefetched_data(_filter, target_keys=None):
path = 'data'
if target_keys is not None:
path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys))
return traverse_obj(yield_all_relay_data(_filter), (
..., 'require', (None, (..., ..., ..., '__bbox', 'require')),
lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v),
..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {}
..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {}
if not video_data:
server_js_data = self._parse_json(self._search_regex([
@ -591,7 +596,8 @@ class FacebookIE(InfoExtractor):
if not video_data:
data = extract_relay_prefetched_data(
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)')
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)',
target_keys=('video', 'event', 'nodes', 'node', 'mediaset'))
if data:
entries = []
@ -957,6 +963,7 @@ class FacebookAdsIE(InfoExtractor):
'id': '899206155126718',
'ext': 'mp4',
'title': 'video by Kandao',
'description': 'md5:0822724069e3aca97cbed5dabbab282e',
'uploader': 'Kandao',
'uploader_id': '774114102743284',
'uploader_url': r're:^https?://.*',
@ -965,6 +972,22 @@ class FacebookAdsIE(InfoExtractor):
'upload_date': '20231214',
'like_count': int,
},
}, {
# key 'watermarked_video_sd_url' missing
'url': 'https://www.facebook.com/ads/library/?id=501152689226254',
'info_dict': {
'id': '501152689226254',
'ext': 'mp4',
'title': 'video by mat.nawrocki',
'description': 'md5:02a446ace7ff8c3c37a2892922492490',
'uploader': 'mat.nawrocki',
'uploader_id': '148586968341456',
'uploader_url': r're:^https?://.*',
'timestamp': 1723452305,
'thumbnail': r're:^https?://.*',
'upload_date': '20240812',
'like_count': int,
},
}, {
'url': 'https://www.facebook.com/ads/library/?id=893637265423481',
'info_dict': {
@ -1011,34 +1034,42 @@ class FacebookAdsIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
post_data = [self._parse_json(j, video_id, fatal=False)
for j in re.findall(r's\.handle\(({.*})\);requireLazy\(', webpage)]
data = traverse_obj(post_data, (
..., 'require', ..., ..., ..., 'props', 'deeplinkAdCard', 'snapshot', {dict}), get_all=False)
post_data = traverse_obj(
re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
data = get_first(post_data, (
'require', ..., ..., ..., '__bbox', 'require', ..., ..., ...,
'entryPointRoot', 'otherProps', 'deeplinkAdCard', 'snapshot', {dict}))
if not data:
raise ExtractorError('Unable to extract ad data')
title = data.get('title')
if not title or title == '{{product.name}}':
title = join_nonempty('display_format', 'page_name', delim=' by ', from_dict=data)
markup_id = traverse_obj(data, ('body', '__m', {str}))
markup = traverse_obj(post_data, (
..., 'require', ..., ..., ..., '__bbox', 'markup', lambda _, v: v[0].startswith(markup_id),
..., '__html', {clean_html}, {lambda x: not x.startswith('{{product.') and x}, any))
info_dict = traverse_obj(data, {
'description': ('link_description', {str}, {lambda x: x if x != '{{product.description}}' else None}),
info_dict = merge_dicts({
'title': title,
'description': markup or None,
}, traverse_obj(data, {
'description': ('link_description', {lambda x: x if not x.startswith('{{product.') else None}),
'uploader': ('page_name', {str}),
'uploader_id': ('page_id', {str_or_none}),
'uploader_url': ('page_profile_uri', {url_or_none}),
'timestamp': ('creation_time', {int_or_none}),
'like_count': ('page_like_count', {int_or_none}),
})
}))
entries = []
for idx, entry in enumerate(traverse_obj(
data, (('videos', 'cards'), lambda _, v: any(url_or_none(v[f]) for f in self._FORMATS_MAP))), 1,
data, (('videos', 'cards'), lambda _, v: any(url_or_none(v.get(f)) for f in self._FORMATS_MAP))), 1,
):
entries.append({
'id': f'{video_id}_{idx}',
'title': entry.get('title') or title,
'description': entry.get('link_description') or info_dict.get('description'),
'description': traverse_obj(entry, 'body', 'link_description') or info_dict.get('description'),
'thumbnail': url_or_none(entry.get('video_preview_image_url')),
'formats': self._extract_formats(entry),
})

5
yt_dlp/extractor/generic.py
View file

@ -43,6 +43,7 @@ from ..utils import (
xpath_text,
xpath_with_ns,
)
from ..utils._utils import _UnsafeExtensionError
class GenericIE(InfoExtractor):
@ -2446,9 +2447,13 @@ class GenericIE(InfoExtractor):
if not is_html(first_bytes):
self.report_warning(
'URL could be a direct video link, returning it as such.')
ext = determine_ext(url)
if ext not in _UnsafeExtensionError.ALLOWED_EXTENSIONS:
ext = 'unknown_video'
info_dict.update({
'direct': True,
'url': url,
'ext': ext,
})
return info_dict

9
yt_dlp/extractor/jiosaavn.py
View file

@ -158,7 +158,7 @@ class JioSaavnAlbumIE(JioSaavnBaseIE):
class JioSaavnPlaylistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:playlist'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/s/playlist/(?:[^/?#]+/){2}(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
'info_dict': {
@ -173,6 +173,13 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
'title': 'Mood Hindi',
},
'playlist_mincount': 801,
}, {
'url': 'https://www.jiosaavn.com/featured/taaza-tunes/Me5RridRfDk_',
'info_dict': {
'id': 'Me5RridRfDk_',
'title': 'Taaza Tunes',
},
'playlist_mincount': 301,
}]
_PAGE_SIZE = 50

205
yt_dlp/extractor/kick.py
View file

@ -1,9 +1,14 @@
import functools
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,
unified_timestamp,
@ -25,104 +30,192 @@ class KickBaseIE(InfoExtractor):
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
return self._download_json(
f'https://kick.com/api/v1/{path}', display_id, note=note,
f'https://kick.com/api/{path}', display_id, note=note,
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
class KickIE(KickBaseIE):
IE_NAME = 'kick:live'
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://kick.com/yuppy',
'url': 'https://kick.com/buddha',
'info_dict': {
'id': '6cde1-kickrp-joe-flemmingskick-info-heremust-knowmust-see21',
'id': '92722911-nopixel-40',
'ext': 'mp4',
'title': str,
'description': str,
'channel': 'yuppy',
'channel_id': '33538',
'uploader': 'Yuppy',
'uploader_id': '33793',
'upload_date': str,
'live_status': 'is_live',
'timestamp': int,
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:https?://.+\.jpg',
'categories': list,
'upload_date': str,
'channel': 'buddha',
'channel_id': '32807',
'uploader': 'Buddha',
'uploader_id': '33057',
'live_status': 'is_live',
'concurrent_view_count': int,
'release_timestamp': int,
'age_limit': 18,
'release_date': str,
},
'skip': 'livestream',
'params': {'skip_download': 'livestream'},
# 'skip': 'livestream',
}, {
'url': 'https://kick.com/kmack710',
'url': 'https://kick.com/xqc',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if KickClipIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
channel = self._match_id(url)
response = self._call_api(f'channels/{channel}', channel)
response = self._call_api(f'v2/channels/{channel}', channel)
if not traverse_obj(response, 'livestream', expected_type=dict):
raise UserNotLive(video_id=channel)
return {
'id': str(traverse_obj(
response, ('livestream', ('slug', 'id')), get_all=False, default=channel)),
'formats': self._extract_m3u8_formats(
response['playback_url'], channel, 'mp4', live=True),
'title': traverse_obj(
response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
'description': traverse_obj(response, ('user', 'bio')),
'channel': channel,
'channel_id': str_or_none(traverse_obj(response, 'id', ('livestream', 'channel_id'))),
'uploader': traverse_obj(response, 'name', ('user', 'username')),
'uploader_id': str_or_none(traverse_obj(response, 'user_id', ('user', 'id'))),
'is_live': True,
'timestamp': unified_timestamp(traverse_obj(response, ('livestream', 'created_at'))),
'thumbnail': traverse_obj(
response, ('livestream', 'thumbnail', 'url'), expected_type=url_or_none),
'categories': traverse_obj(response, ('recent_categories', ..., 'name')),
'formats': self._extract_m3u8_formats(response['playback_url'], channel, 'mp4', live=True),
**traverse_obj(response, {
'id': ('livestream', 'slug', {str}),
'title': ('livestream', 'session_title', {str}),
'description': ('user', 'bio', {str}),
'channel_id': (('id', ('livestream', 'channel_id')), {int}, {str_or_none}, any),
'uploader': (('name', ('user', 'username')), {str}, any),
'uploader_id': (('user_id', ('user', 'id')), {int}, {str_or_none}, any),
'timestamp': ('livestream', 'created_at', {unified_timestamp}),
'release_timestamp': ('livestream', 'start_time', {unified_timestamp}),
'thumbnail': ('livestream', 'thumbnail', 'url', {url_or_none}),
'categories': ('recent_categories', ..., 'name', {str}),
'concurrent_view_count': ('livestream', 'viewer_count', {int_or_none}),
'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}
class KickVODIE(KickBaseIE):
IE_NAME = 'kick:vod'
_VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://kick.com/video/58bac65b-e641-4476-a7ba-3707a35e60e3',
'url': 'https://kick.com/video/e74614f4-5270-4319-90ad-32179f19a45c',
'md5': '3870f94153e40e7121a6e46c068b70cb',
'info_dict': {
'id': '58bac65b-e641-4476-a7ba-3707a35e60e3',
'id': 'e74614f4-5270-4319-90ad-32179f19a45c',
'ext': 'mp4',
'title': '🤠REBIRTH IS BACK!!!!🤠!stake CODE JAREDFPS 🤠',
'description': 'md5:02b0c46f9b4197fb545ab09dddb85b1d',
'channel': 'jaredfps',
'channel_id': '26608',
'uploader': 'JaredFPS',
'uploader_id': '26799',
'upload_date': '20240402',
'timestamp': 1712097108,
'duration': 33859.0,
'title': r're:❎ MEGA DRAMA ❎ LIVE ❎ CLICK ❎ ULTIMATE SKILLS .+',
'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
'channel': 'xqc',
'channel_id': '668',
'uploader': 'xQc',
'uploader_id': '676',
'upload_date': '20240724',
'timestamp': 1721796562,
'duration': 18566.0,
'thumbnail': r're:^https?://.*\.jpg',
'categories': ['Call of Duty: Warzone'],
'view_count': int,
'categories': ['VALORANT'],
'age_limit': 0,
},
'params': {
'skip_download': 'm3u8',
},
'expected_warnings': [r'impersonation'],
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
response = self._call_api(f'video/{video_id}', video_id)
response = self._call_api(f'v1/video/{video_id}', video_id)
return {
'id': video_id,
'formats': self._extract_m3u8_formats(response['source'], video_id, 'mp4'),
'title': traverse_obj(
response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
'description': traverse_obj(response, ('livestream', 'channel', 'user', 'bio')),
'channel': traverse_obj(response, ('livestream', 'channel', 'slug')),
'channel_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'id'))),
'uploader': traverse_obj(response, ('livestream', 'channel', 'user', 'username')),
'uploader_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'user_id'))),
'timestamp': unified_timestamp(response.get('created_at')),
'duration': float_or_none(traverse_obj(response, ('livestream', 'duration')), scale=1000),
'thumbnail': traverse_obj(
response, ('livestream', 'thumbnail'), expected_type=url_or_none),
'categories': traverse_obj(response, ('livestream', 'categories', ..., 'name')),
**traverse_obj(response, {
'title': ('livestream', ('session_title', 'slug'), {str}, any),
'description': ('livestream', 'channel', 'user', 'bio', {str}),
'channel': ('livestream', 'channel', 'slug', {str}),
'channel_id': ('livestream', 'channel', 'id', {int}, {str_or_none}),
'uploader': ('livestream', 'channel', 'user', 'username', {str}),
'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}),
'timestamp': ('created_at', {parse_iso8601}),
'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}),
'thumbnail': ('livestream', 'thumbnail', {url_or_none}),
'categories': ('livestream', 'categories', ..., 'name', {str}),
'view_count': ('views', {int_or_none}),
'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}
class KickClipIE(KickBaseIE):
IE_NAME = 'kick:clips'
_VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/?\?(?:[^#]+&)?clip=(?P<id>clip_[\w-]+)'
_TESTS = [{
'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
'info_dict': {
'id': 'clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
'ext': 'mp4',
'title': 'Maddy detains Abd D:',
'channel': 'mxddy',
'channel_id': '133789',
'uploader': 'AbdCreates',
'uploader_id': '3309077',
'thumbnail': r're:^https?://.*\.jpeg',
'duration': 35,
'timestamp': 1682481453,
'upload_date': '20230426',
'view_count': int,
'like_count': int,
'categories': ['VALORANT'],
'age_limit': 18,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://kick.com/destiny?clip=clip_01H9SKET879NE7N9RJRRDS98J3',
'info_dict': {
'id': 'clip_01H9SKET879NE7N9RJRRDS98J3',
'title': 'W jews',
'ext': 'mp4',
'channel': 'destiny',
'channel_id': '1772249',
'uploader': 'punished_furry',
'uploader_id': '2027722',
'duration': 49.0,
'upload_date': '20230908',
'timestamp': 1694150180,
'thumbnail': 'https://clips.kick.com/clips/j3/clip_01H9SKET879NE7N9RJRRDS98J3/thumbnail.png',
'view_count': int,
'like_count': int,
'categories': ['Just Chatting'],
'age_limit': 0,
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._call_api(f'v2/clips/{clip_id}/play', clip_id)['clip']
clip_url = clip['clip_url']
if determine_ext(clip_url) == 'm3u8':
formats = self._extract_m3u8_formats(clip_url, clip_id, 'mp4')
else:
formats = [{'url': clip_url}]
return {
'id': clip_id,
'formats': formats,
**traverse_obj(clip, {
'title': ('title', {str}),
'channel': ('channel', 'slug', {str}),
'channel_id': ('channel', 'id', {int}, {str_or_none}),
'uploader': ('creator', 'username', {str}),
'uploader_id': ('creator', 'id', {int}, {str_or_none}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'duration': ('duration', {float_or_none}),
'categories': ('category', 'name', {str}, all),
'timestamp': ('created_at', {parse_iso8601}),
'view_count': ('views', {int_or_none}),
'like_count': ('likes', {int_or_none}),
'age_limit': ('is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}

78
yt_dlp/extractor/learningonscreen.py Normal file
View file

@ -0,0 +1,78 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
join_nonempty,
parse_duration,
unified_timestamp,
)
from ..utils.traversal import traverse_obj
class LearningOnScreenIE(InfoExtractor):
_VALID_URL = r'https?://learningonscreen\.ac\.uk/ondemand/index\.php/prog/(?P<id>\w+)'
_TESTS = [{
'url': 'https://learningonscreen.ac.uk/ondemand/index.php/prog/005D81B2?bcast=22757013',
'info_dict': {
'id': '005D81B2',
'ext': 'mp4',
'title': 'Planet Earth',
'duration': 3600.0,
'timestamp': 1164567600.0,
'upload_date': '20061126',
'thumbnail': 'https://stream.learningonscreen.ac.uk/trilt-cover-images/005D81B2-Planet-Earth-2006-11-26T190000Z-BBC4.jpg',
},
}]
def _real_initialize(self):
if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'):
self.raise_login_required(
'Use --cookies for authentication. See '
' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp '
'for how to manually pass cookies', method=None)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
details = traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'programme-details')}, {
'title': ({functools.partial(re.search, r'<h2>([^<]+)</h2>')}, 1, {clean_html}),
'timestamp': (
{functools.partial(get_element_by_class, 'broadcast-date')},
{functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}),
'duration': (
{functools.partial(get_element_by_class, 'prog-running-time')},
{clean_html}, {parse_duration}),
}))
title = details.pop('title', None) or traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'add-to-existing-playlist')},
{extract_attributes}, 'data-record-title', {clean_html}))
entries = self._parse_html5_media_entries(
'https://stream.learningonscreen.ac.uk', webpage, video_id, m3u8_id='hls', mpd_id='dash',
_headers={'Origin': 'https://learningonscreen.ac.uk', 'Referer': 'https://learningonscreen.ac.uk/'})
if not entries:
raise ExtractorError('No video found')
if len(entries) > 1:
duration = details.pop('duration', None)
for idx, entry in enumerate(entries, start=1):
entry.update(details)
entry['id'] = join_nonempty(video_id, idx)
entry['title'] = join_nonempty(title, idx)
return self.playlist_result(entries, video_id, title, duration=duration)
return {
**entries[0],
**details,
'id': video_id,
'title': title,
}

4
yt_dlp/extractor/mediaklikk.py
View file

@ -133,7 +133,9 @@ class MediaKlikkIE(InfoExtractor):
r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
player_data['video'] = player_data.pop('token')
player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data)
player_page = self._download_webpage(
'https://player.mediaklikk.hu/playernew/player.php', video_id,
query=player_data, headers={'Referer': url})
player_json = self._search_json(
r'\bpl\.setup\s*\(', player_page, 'player json', video_id, end_pattern=r'\);')
playlist_url = traverse_obj(

239
yt_dlp/extractor/mlb.py
View file

@ -1,16 +1,21 @@
import json
import re
import urllib.parse
import time
import uuid
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
join_nonempty,
jwt_decode_hs256,
parse_duration,
parse_iso8601,
try_get,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
@ -276,81 +281,225 @@ class MLBVideoIE(MLBBaseIE):
class MLBTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})'
_NETRC_MACHINE = 'mlb'
_TESTS = [{
'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638',
'info_dict': {
'id': '661581',
'ext': 'mp4',
'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies',
'release_date': '20220702',
'release_timestamp': 1656792300,
},
'params': {
'skip_download': True,
'params': {'skip_download': 'm3u8'},
}, {
# makeup game: has multiple dates, need to avoid games with 'rescheduleDate'
'url': 'https://www.mlb.com/tv/g747039/vd22541c4-5a29-45f7-822b-635ec041cf5e',
'info_dict': {
'id': '747039',
'ext': 'mp4',
'title': '2024-07-29 - Toronto Blue Jays @ Baltimore Orioles',
'release_date': '20240729',
'release_timestamp': 1722280200,
},
'params': {'skip_download': 'm3u8'},
}]
_GRAPHQL_INIT_QUERY = '''\
mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) {
initSession(device: $device, clientType: $clientType, experience: $experience) {
deviceId
sessionId
entitlements {
code
}
location {
countryCode
regionName
zipCode
latitude
longitude
}
clientExperience
features
}
}'''
_GRAPHQL_PLAYBACK_QUERY = '''\
mutation initPlaybackSession(
$adCapabilities: [AdExperienceType]
$mediaId: String!
$deviceId: String!
$sessionId: String!
$quality: PlaybackQuality
) {
initPlaybackSession(
adCapabilities: $adCapabilities
mediaId: $mediaId
deviceId: $deviceId
sessionId: $sessionId
quality: $quality
) {
playbackSessionId
playback {
url
token
expiration
cdn
}
}
}'''
_APP_VERSION = '7.8.2'
_device_id = None
_session_id = None
_access_token = None
_token_expiry = 0
@property
def _api_headers(self):
if (self._token_expiry - 120) <= time.time():
self.write_debug('Access token has expired; re-logging in')
self._perform_login(*self._get_login_info())
return {'Authorization': f'Bearer {self._access_token}'}
def _real_initialize(self):
if not self._access_token:
self.raise_login_required(
'All videos are only available to registered users', method='password')
def _set_device_id(self, username):
if not self._device_id:
self._device_id = self.cache.load(
self._NETRC_MACHINE, 'device_ids', default={}).get(username)
if self._device_id:
return
self._device_id = str(uuid.uuid4())
self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id})
def _perform_login(self, username, password):
data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356'
access_token = self._download_json(
'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token']
try:
self._access_token = self._download_json(
'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
'Logging in', 'Unable to log in', headers={
'User-Agent': 'okhttp/3.12.1',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=urlencode_postdata({
'grant_type': 'password',
'username': username,
'password': password,
'scope': 'openid offline_access',
'client_id': '0oa3e1nutA1HLzAKG356',
}))['access_token']
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 400:
raise ExtractorError('Invalid username or password', expected=True)
raise
entitlement = self._download_webpage(
f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Authorization': f'Bearer {access_token}',
})
self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0
self._set_device_id(username)
data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv'
self._access_token = self._download_json(
'https://us.edge.bamgrid.com/token', None,
self._session_id = self._call_api({
'operationName': 'initSession',
'query': self._GRAPHQL_INIT_QUERY,
'variables': {
'device': {
'appVersion': self._APP_VERSION,
'deviceFamily': 'desktop',
'knownDeviceId': self._device_id,
'languagePreference': 'ENGLISH',
'manufacturer': '',
'model': '',
'os': '',
'osVersion': '',
},
'clientType': 'WEB',
},
}, None, 'session ID')['data']['initSession']['sessionId']
def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True):
return self._download_json(
'https://media-gateway.mlb.com/graphql', video_id,
f'Downloading {description}', f'Unable to download {description}', fatal=fatal,
headers={
**self._api_headers,
'Accept': 'application/json',
'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token']
'Content-Type': 'application/json',
'x-client-name': 'WEB',
'x-client-version': self._APP_VERSION,
}, data=json.dumps(data, separators=(',', ':')).encode())
def _extract_formats_and_subtitles(self, broadcast, video_id):
feed = traverse_obj(broadcast, ('homeAway', {str.title}))
medium = traverse_obj(broadcast, ('type', {str}))
language = traverse_obj(broadcast, ('language', {str.lower}))
format_id = join_nonempty(feed, medium, language)
response = self._call_api({
'operationName': 'initPlaybackSession',
'query': self._GRAPHQL_PLAYBACK_QUERY,
'variables': {
'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'],
'deviceId': self._device_id,
'mediaId': broadcast['mediaId'],
'quality': 'PLACEHOLDER',
'sessionId': self._session_id,
},
}, video_id, f'{format_id} broadcast JSON', fatal=False)
playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict}))
m3u8_url = traverse_obj(playback, ('url', {url_or_none}))
token = traverse_obj(playback, ('token', {str}))
if not (m3u8_url and token):
errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
if 'not entitled' in errors:
raise ExtractorError(errors, expected=True)
elif errors: # Only warn when 'blacked out' since radio formats are available
self.report_warning(f'API returned errors for {format_id}: {errors}')
else:
self.report_warning(f'No formats available for {format_id} broadcast; skipping')
return [], {}
cdn_headers = {'x-cdn-token': token}
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
m3u8_id=format_id, fatal=False, headers=cdn_headers)
for fmt in fmts:
fmt['http_headers'] = cdn_headers
fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
fmt.setdefault('language', language)
if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':
fmt['source_preference'] = 10
return fmts, subs
def _real_extract(self, url):
video_id = self._match_id(url)
airings = self._download_json(
f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D',
video_id)['data']['Airings']
data = self._download_json(
'https://statsapi.mlb.com/api/v1/schedule', video_id, query={
'gamePk': video_id,
'hydrate': 'broadcasts(all),statusFlags',
})
metadata = traverse_obj(data, (
'dates', ..., 'games',
lambda _, v: str(v['gamePk']) == video_id and not v.get('rescheduleDate'), any))
broadcasts = traverse_obj(metadata, (
'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF'))
formats, subtitles = [], {}
for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
m3u8_url = traverse_obj(self._download_json(
airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
note=f'Downloading {format_id} stream info JSON',
errnote=f'Failed to download {format_id} stream info, skipping',
fatal=False, headers={
'Authorization': self._access_token,
'Accept': 'application/vnd.media-service+json; version=2',
}), ('stream', 'complete', {url_or_none}))
if not m3u8_url:
continue
f, s = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
formats.extend(f)
self._merge_subtitles(s, target=subtitles)
for broadcast in broadcasts:
fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False),
'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE',
'title': join_nonempty(
traverse_obj(metadata, ('officialDate', {str})),
traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})),
delim=' - '),
'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON',
'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})),
'formats': formats,
'subtitles': subtitles,
'http_headers': {'Authorization': f'Bearer {self._access_token}'},
}

157
yt_dlp/extractor/murrtube.py
View file

@ -5,39 +5,103 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
int_or_none,
try_get,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
parse_count,
remove_end,
update_url,
urlencode_postdata,
)
class MurrtubeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
murrtube:|
https?://murrtube\.net/videos/(?P<slug>[a-z0-9\-]+)\-
https?://murrtube\.net/(?:v/|videos/(?P<slug>[a-z0-9-]+?)-)
)
(?P<id>[a-f0-9]{8}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{12})
(?P<id>[A-Z0-9]{4}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})
'''
_TEST = {
_TESTS = [{
'url': 'https://murrtube.net/videos/inferno-x-skyler-148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
'md5': '169f494812d9a90914b42978e73aa690',
'md5': '70380878a77e8565d4aea7f68b8bbb35',
'info_dict': {
'id': '148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
'id': 'ca885d8456b95de529b6723b158032e11115d',
'ext': 'mp4',
'title': 'Inferno X Skyler',
'description': 'Humping a very good slutty sheppy (roomate)',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 284,
'uploader': 'Inferno Wolf',
'age_limit': 18,
'thumbnail': 'https://storage.murrtube.net/murrtube-production/ekbs3zcfvuynnqfx72nn2tkokvsd',
'comment_count': int,
'view_count': int,
'like_count': int,
'tags': ['hump', 'breed', 'Fursuit', 'murrsuit', 'bareback'],
},
}
}, {
'url': 'https://murrtube.net/v/0J2Q',
'md5': '31262f6ac56f0ca75e5a54a0f3fefcb6',
'info_dict': {
'id': '8442998c52134968d9caa36e473e1a6bac6ca',
'ext': 'mp4',
'uploader': 'Hayel',
'title': 'Who\'s in charge now?',
'description': 'md5:795791e97e5b0f1805ea84573f02a997',
'age_limit': 18,
'thumbnail': 'https://storage.murrtube.net/murrtube-production/fb1ojjwiucufp34ya6hxu5vfqi5s',
'comment_count': int,
'view_count': int,
'like_count': int,
},
}]
def _extract_count(self, name, html):
return parse_count(self._search_regex(
rf'([\d,]+)\s+<span[^>]*>{name}</span>', html, name, default=None))
def _real_initialize(self):
homepage = self._download_webpage(
'https://murrtube.net', None, note='Getting session token')
self._request_webpage(
'https://murrtube.net/accept_age_check', None, 'Setting age cookie',
data=urlencode_postdata(self._hidden_inputs(homepage)))
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id.startswith('murrtube:'):
raise ExtractorError('Support for murrtube: prefix URLs is broken')
video_page = self._download_webpage(url, video_id)
video_attrs = extract_attributes(get_element_html_by_id('video', video_page))
playlist = update_url(video_attrs['data-url'], query=None)
video_id = self._search_regex(r'/([\da-f]+)/index.m3u8', playlist, 'video id')
return {
'id': video_id,
'title': remove_end(self._og_search_title(video_page), ' - Murrtube'),
'age_limit': 18,
'formats': self._extract_m3u8_formats(playlist, video_id, 'mp4'),
'description': self._og_search_description(video_page),
'thumbnail': update_url(self._og_search_thumbnail(video_page, default=''), query=None) or None,
'uploader': clean_html(get_element_by_class('pl-1 is-size-6 has-text-lighter', video_page)),
'view_count': self._extract_count('Views', video_page),
'like_count': self._extract_count('Likes', video_page),
'comment_count': self._extract_count('Comments', video_page),
}
class MurrtubeUserIE(InfoExtractor):
_WORKING = False
IE_DESC = 'Murrtube user profile'
_VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)$'
_TESTS = [{
'url': 'https://murrtube.net/stormy',
'info_dict': {
'id': 'stormy',
},
'playlist_mincount': 27,
}]
_PAGE_SIZE = 10
def _download_gql(self, video_id, op, note=None, fatal=True):
result = self._download_json(
@ -46,73 +110,6 @@ class MurrtubeIE(InfoExtractor):
headers={'Content-Type': 'application/json'})
return result['data']
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_gql(video_id, {
'operationName': 'Medium',
'variables': {
'id': video_id,
},
'query': '''\
query Medium($id: ID!) {
medium(id: $id) {
title
description
key
duration
commentsCount
likesCount
viewsCount
thumbnailKey
tagList
user {
name
__typename
}
__typename
}
}'''})
meta = data['medium']
storage_url = 'https://storage.murrtube.net/murrtube/'
format_url = storage_url + meta.get('key', '')
thumbnail = storage_url + meta.get('thumbnailKey', '')
if determine_ext(format_url) == 'm3u8':
formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native', fatal=False)
else:
formats = [{'url': format_url}]
return {
'id': video_id,
'title': meta.get('title'),
'description': meta.get('description'),
'formats': formats,
'thumbnail': thumbnail,
'duration': int_or_none(meta.get('duration')),
'uploader': try_get(meta, lambda x: x['user']['name']),
'view_count': meta.get('viewsCount'),
'like_count': meta.get('likesCount'),
'comment_count': meta.get('commentsCount'),
'tags': meta.get('tagList'),
'age_limit': 18,
}
class MurrtubeUserIE(MurrtubeIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_DESC = 'Murrtube user profile'
_VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)$'
_TEST = {
'url': 'https://murrtube.net/stormy',
'info_dict': {
'id': 'stormy',
},
'playlist_mincount': 27,
}
_PAGE_SIZE = 10
def _fetch_page(self, username, user_id, page):
data = self._download_gql(username, {
'operationName': 'Media',

22
yt_dlp/extractor/niconico.py
View file

@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'info_dict': {
'id': 'sm22312215',
'ext': 'mp4',
@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['未設定'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# File downloaded with and without credentials are different, so omit
# the md5 field
@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor):
'view_count': int,
'genres': ['音楽・サウンド'],
'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# 'video exists but is marked as "deleted"
# md5 is unstable
@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor):
}, {
# video not available via `getflv`; "old" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm1151009',
'md5': 'f95a3d259172667b293530cc2e41ebda',
'info_dict': {
'id': 'sm1151009',
'ext': 'mp4',
@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['ゲーム'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# "New" HTML5 video
# md5 is unstable
'url': 'http://www.nicovideo.jp/watch/sm31464864',
'info_dict': {
'id': 'sm31464864',
@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['アニメ'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# Video without owner
'url': 'http://www.nicovideo.jp/watch/sm18238488',
'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
'info_dict': {
'id': 'sm18238488',
'ext': 'mp4',
@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['エンターテイメント'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True,
@ -458,9 +454,11 @@ class NiconicoIE(InfoExtractor):
if video_id.startswith('so'):
video_id = self._match_id(handle.url)
api_data = self._parse_json(self._html_search_regex(
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
api_data = traverse_obj(
self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
('data', 'response', {dict}))
if not api_data:
raise ExtractorError('Server response data not found')
except ExtractorError as e:
try:
api_data = self._download_json(

121
yt_dlp/extractor/olympics.py
View file

@ -1,9 +1,19 @@
from .common import InfoExtractor
from ..utils import int_or_none, try_get
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
parse_qs,
try_get,
update_url,
url_or_none,
)
from ..utils.traversal import traverse_obj
class OlympicsReplayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P<id>[^/#&?]+)'
_VALID_URL = r'https?://(?:www\.)?olympics\.com/[a-z]{2}/(?:paris-2024/)?(?:replay|videos?|original-series/episode)/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays',
'info_dict': {
@ -11,26 +21,105 @@ class OlympicsReplayIE(InfoExtractor):
'ext': 'mp4',
'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020',
'upload_date': '20210801',
'timestamp': 1627783200,
'timestamp': 1627797600,
'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3',
'uploader': 'International Olympic Committee',
},
'params': {
'skip_download': True,
'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2',
'duration': 7017.0,
},
}, {
'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
'only_matching': True,
'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024',
'info_dict': {
'id': '32633650-c5ee-4280-8b94-fb6defb6a9b5',
'ext': 'mp4',
'title': 'B-girl Nicka - Breaking Life, Road to Paris 2024 | Episode 1',
'upload_date': '20240517',
'timestamp': 1715948200,
'description': 'md5:f63d728a41270ec628f6ac33ce471bb1',
'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/a3j96l7j6so3vyfijby1',
'duration': 1321.0,
},
}, {
'url': 'https://olympics.com/en/paris-2024/videos/men-s-preliminaries-gbr-esp-ned-rsa-hockey-olympic-games-paris-2024',
'info_dict': {
'id': '3d96db23-8eee-4b7c-8ef5-488a0361026c',
'ext': 'mp4',
'title': 'Men\'s Preliminaries GBR-ESP & NED-RSA | Hockey | Olympic Games Paris 2024',
'upload_date': '20240727',
'timestamp': 1722066600,
},
'skip': 'Geo-restricted to RU, BR, BT, NP, TM, BD, TL',
}, {
'url': 'https://olympics.com/en/paris-2024/videos/dnp-suni-lee-i-have-goals-and-i-have-expectations-for-myself-but-i-also-am-trying-to-give-myself-grace',
'info_dict': {
'id': 'a42f37ab-8a74-41d0-a7d9-af27b7b02a90',
'ext': 'mp4',
'title': 'md5:c7cfbc9918636a98e66400a812e4d407',
'upload_date': '20240729',
'timestamp': 1722288600,
},
}]
_GEO_BYPASS = False
def _extract_from_nextjs_data(self, webpage, video_id):
data = traverse_obj(self._search_nextjs_data(webpage, video_id, default={}), (
'props', 'pageProps', 'page', 'items',
lambda _, v: v['name'] == 'videoPlaylist', 'data', 'currentVideo', {dict}, any))
if not data:
return None
geo_countries = traverse_obj(data, ('countries', ..., {str}))
if traverse_obj(data, ('geoRestrictedVideo', {bool})):
self.raise_geo_restricted(countries=geo_countries)
is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE'
m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl']
tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id)
try:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
tokenized_url, video_id, 'mp4', m3u8_id='hls')
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and 'georestricted' in e.cause.msg:
self.raise_geo_restricted(countries=geo_countries)
raise
return {
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
**traverse_obj(data, {
'id': ('videoID', {str}),
'title': ('title', {str}),
'timestamp': ('contentDate', {parse_iso8601}),
}),
}
def _tokenize_url(self, url, token, is_live, video_id):
return self._download_json(
'https://metering.olympics.com/tokengenerator', video_id,
'Downloading tokenized m3u8 url', query={
**parse_qs(url),
'url': update_url(url, query=None),
'service-id': 'live' if is_live else 'vod',
'user-auth': token,
})['data']['url']
def _legacy_tokenize_url(self, url, video_id):
return self._download_json(
'https://olympics.com/tokenGenerator', video_id,
'Downloading legacy tokenized m3u8 url', query={'url': url})
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if info := self._extract_from_nextjs_data(webpage, video_id):
return info
title = self._html_search_meta(('title', 'og:title', 'twitter:title'), webpage)
uuid = self._html_search_meta('episode_uid', webpage)
video_uuid = self._html_search_meta('episode_uid', webpage)
m3u8_url = self._html_search_meta('video_url', webpage)
json_ld = self._search_json_ld(webpage, uuid)
json_ld = self._search_json_ld(webpage, video_uuid)
thumbnails_list = json_ld.get('image')
if not thumbnails_list:
thumbnails_list = self._html_search_regex(
@ -48,12 +137,12 @@ class OlympicsReplayIE(InfoExtractor):
'width': width,
'height': int_or_none(try_get(width, lambda x: x * height_a / width_a)),
})
m3u8_url = self._download_json(
f'https://olympics.com/tokenGenerator?url={m3u8_url}', uuid, note='Downloading m3u8 url')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, 'mp4', m3u8_id='hls')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
return {
'id': uuid,
'id': video_uuid,
'title': title,
'thumbnails': thumbnails,
'formats': formats,

27
yt_dlp/extractor/patreon.py
View file

@ -420,7 +420,7 @@ class PatreonIE(PatreonBaseIE):
class PatreonCampaignIE(PatreonBaseIE):
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P<campaign_id>\d+))|(?P<vanity>[-\w]+))'
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m|api/campaigns)/(?P<campaign_id>\d+)|(?P<vanity>[-\w]+))'
_TESTS = [{
'url': 'https://www.patreon.com/dissonancepod/',
'info_dict': {
@ -442,25 +442,44 @@ class PatreonCampaignIE(PatreonBaseIE):
'url': 'https://www.patreon.com/m/4767637/posts',
'info_dict': {
'title': 'Not Just Bikes',
'channel_follower_count': int,
'id': '4767637',
'channel_id': '4767637',
'channel_url': 'https://www.patreon.com/notjustbikes',
'description': 'md5:595c6e7dca76ae615b1d38c298a287a1',
'description': 'md5:9f4b70051216c4d5c58afe580ffc8d0f',
'age_limit': 0,
'channel': 'Not Just Bikes',
'uploader_url': 'https://www.patreon.com/notjustbikes',
'uploader': 'Not Just Bikes',
'uploader': 'Jason',
'uploader_id': '37306634',
'thumbnail': r're:^https?://.*$',
},
'playlist_mincount': 71,
}, {
'url': 'https://www.patreon.com/api/campaigns/4243769/posts',
'info_dict': {
'title': 'Second Thought',
'channel_follower_count': int,
'id': '4243769',
'channel_id': '4243769',
'channel_url': 'https://www.patreon.com/secondthought',
'description': 'md5:69c89a3aba43efdb76e85eb023e8de8b',
'age_limit': 0,
'channel': 'Second Thought',
'uploader_url': 'https://www.patreon.com/secondthought',
'uploader': 'JT Chapman',
'uploader_id': '32718287',
'thumbnail': r're:^https?://.*$',
},
'playlist_mincount': 201,
}, {
'url': 'https://www.patreon.com/dissonancepod/posts',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/m/5932659',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/api/campaigns/4243769',
'only_matching': True,
}]
@classmethod

16
yt_dlp/extractor/picarto.py
View file

@ -5,6 +5,7 @@ from ..utils import (
ExtractorError,
str_or_none,
traverse_obj,
update_url,
)
@ -43,15 +44,16 @@ class PicartoIE(InfoExtractor):
url
}
}''' % (channel_id, channel_id), # noqa: UP031
})['data']
}, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']
metadata = data['channel']
if metadata.get('online') == 0:
raise ExtractorError('Stream is offline', expected=True)
title = metadata['title']
cdn_data = self._download_json(
data['getLoadBalancerUrl']['url'] + '/stream/json_' + metadata['stream_name'] + '.js',
cdn_data = self._download_json(''.join((
update_url(data['getLoadBalancerUrl']['url'], scheme='https'),
'/stream/json_', metadata['stream_name'], '.js')),
channel_id, 'Downloading load balancing info')
formats = []
@ -99,10 +101,10 @@ class PicartoVodIE(InfoExtractor):
},
'skip': 'The VOD does not exist',
}, {
'url': 'https://picarto.tv/ArtofZod/videos/772650',
'md5': '00067a0889f1f6869cc512e3e79c521b',
'url': 'https://picarto.tv/ArtofZod/videos/771008',
'md5': 'abef5322f2700d967720c4c6754b2a34',
'info_dict': {
'id': '772650',
'id': '771008',
'ext': 'mp4',
'title': 'Art of Zod - Drawing and Painting',
'thumbnail': r're:^https?://.*\.jpg',
@ -131,7 +133,7 @@ class PicartoVodIE(InfoExtractor):
}}
}}
}}''',
})['data']['video']
}, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']['video']
file_name = data['file_name']
netloc = urllib.parse.urlparse(data['video_recording_image_url']).netloc

36
yt_dlp/extractor/soundcloud.py
View file

@ -314,23 +314,11 @@ class SoundcloudBaseIE(InfoExtractor):
self.write_debug(f'"{identifier}" is not a requested format, skipping')
continue
stream = None
for retry in self.RetryManager(fatal=False):
try:
stream = self._call_api(
format_url, track_id, f'Downloading {identifier} format info JSON',
query=query, headers=self._HEADERS)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 429:
self.report_warning(
'You have reached the API rate limit, which is ~600 requests per '
'10 minutes. Use the --extractor-retries and --retry-sleep options '
'to configure an appropriate retry count and wait time', only_once=True)
retry.error = e.cause
else:
self.report_warning(e.msg)
# XXX: if not extract_flat, 429 error must be caught where _extract_info_dict is called
stream_url = traverse_obj(self._call_api(
format_url, track_id, f'Downloading {identifier} format info JSON',
query=query, headers=self._HEADERS), ('url', {url_or_none}))
stream_url = traverse_obj(stream, ('url', {url_or_none}))
if invalid_url(stream_url):
continue
format_urls.add(stream_url)
@ -647,7 +635,17 @@ class SoundcloudIE(SoundcloudBaseIE):
info = self._call_api(
info_json_url, full_title, 'Downloading info JSON', query=query, headers=self._HEADERS)
return self._extract_info_dict(info, full_title, token)
for retry in self.RetryManager():
try:
return self._extract_info_dict(info, full_title, token)
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
raise
self.report_warning(
'You have reached the API rate limit, which is ~600 requests per '
'10 minutes. Use the --extractor-retries and --retry-sleep options '
'to configure an appropriate retry count and wait time', only_once=True)
retry.error = e.cause
class SoundcloudPlaylistBaseIE(SoundcloudBaseIE):
@ -873,7 +871,7 @@ class SoundcloudUserPermalinkIE(SoundcloudPagedPlaylistBaseIE):
'id': '30909869',
'title': 'neilcic',
},
'playlist_mincount': 23,
'playlist_mincount': 22,
}]
def _real_extract(self, url):
@ -882,7 +880,7 @@ class SoundcloudUserPermalinkIE(SoundcloudPagedPlaylistBaseIE):
self._resolv_url(url), user_id, 'Downloading user info', headers=self._HEADERS)
return self._extract_playlist(
f'{self._API_V2_BASE}stream/users/{user["id"]}', str(user['id']), user.get('username'))
f'{self._API_V2_BASE}users/{user["id"]}/tracks', str(user['id']), user.get('username'))
class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):

64
yt_dlp/extractor/swearnet.py
View file

@ -1,55 +1,31 @@
from .common import InfoExtractor
from ..utils import ExtractorError, int_or_none, traverse_obj
from .vidyard import VidyardBaseIE
from ..utils import ExtractorError, int_or_none, make_archive_id
class SwearnetEpisodeIE(InfoExtractor):
class SwearnetEpisodeIE(VidyardBaseIE):
_VALID_URL = r'https?://www\.swearnet\.com/shows/(?P<id>[\w-]+)/seasons/(?P<season_num>\d+)/episodes/(?P<episode_num>\d+)'
_TESTS = [{
'url': 'https://www.swearnet.com/shows/gettin-learnt-with-ricky/seasons/1/episodes/1',
'info_dict': {
'id': '232819',
'id': 'wicK2EOzjOdxkUXGDIgcPw',
'display_id': '232819',
'ext': 'mp4',
'episode_number': 1,
'episode': 'Episode 1',
'duration': 719,
'description': 'md5:c48ef71440ce466284c07085cd7bd761',
'description': r're:Are you drunk and high and craving a grilled cheese sandwich.+',
'season': 'Season 1',
'title': 'Episode 1 - Grilled Cheese Sammich',
'season_number': 1,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/232819/_RX04IKIq60a2V6rIRqq_Q_small.jpg',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/custom/0dd74f9b-388a-452e-b570-b407fb64435b_small.jpg',
'tags': ['Getting Learnt with Ricky', 'drunk', 'grilled cheese', 'high'],
'_old_archive_ids': ['swearnetepisode 232819'],
},
}]
def _get_formats_and_subtitle(self, video_source, video_id):
video_source = video_source or {}
formats, subtitles = [], {}
for key, value in video_source.items():
if key == 'hls':
for video_hls in value:
fmts, subs = self._extract_m3u8_formats_and_subtitles(video_hls.get('url'), video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.extend({
'url': video_mp4.get('url'),
'ext': 'mp4',
} for video_mp4 in value)
return formats, subtitles
def _get_direct_subtitle(self, caption_json):
subs = {}
for caption in caption_json:
subs.setdefault(caption.get('language') or 'und', []).append({
'url': caption.get('vttUrl'),
'name': caption.get('name'),
})
return subs
def _real_extract(self, url):
display_id, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
webpage = self._download_webpage(url, display_id)
slug, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
webpage = self._download_webpage(url, slug)
try:
external_id = self._search_regex(r'externalid\s*=\s*"([^"]+)', webpage, 'externalid')
@ -58,22 +34,12 @@ class SwearnetEpisodeIE(InfoExtractor):
self.raise_login_required()
raise
json_data = self._download_json(
f'https://play.vidyard.com/player/{external_id}.json', display_id)['payload']['chapters'][0]
formats, subtitles = self._get_formats_and_subtitle(json_data['sources'], display_id)
self._merge_subtitles(self._get_direct_subtitle(json_data.get('captions')), target=subtitles)
info = self._process_video_json(self._fetch_video_json(external_id)['chapters'][0], external_id)
if info.get('display_id'):
info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
return {
'id': str(json_data['videoId']),
'title': json_data.get('name') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': (json_data.get('description')
or self._html_search_meta(['og:description', 'twitter:description'], webpage)),
'duration': int_or_none(json_data.get('seconds')),
'formats': formats,
'subtitles': subtitles,
**info,
'season_number': int_or_none(season_number),
'episode_number': int_or_none(episode_number),
'thumbnails': [{'url': thumbnail_url}
for thumbnail_url in traverse_obj(json_data, ('thumbnailUrls', ...))],
}

27
yt_dlp/extractor/tiktok.py
View file

@ -23,7 +23,6 @@ from ..utils import (
mimetype2ext,
parse_qs,
qualities,
remove_start,
srt_subtitles_timecode,
str_or_none,
traverse_obj,
@ -254,7 +253,16 @@ class TikTokBaseIE(InfoExtractor):
def _get_subtitles(self, aweme_detail, aweme_id, user_name):
# TODO: Extract text positioning info
EXT_MAP = { # From lowest to highest preference
'creator_caption': 'json',
'srt': 'srt',
'webvtt': 'vtt',
}
preference = qualities(tuple(EXT_MAP.values()))
subtitles = {}
# aweme/detail endpoint subs
captions_info = traverse_obj(
aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict)
@ -278,8 +286,8 @@ class TikTokBaseIE(InfoExtractor):
if not caption.get('url'):
continue
subtitles.setdefault(caption.get('lang') or 'en', []).append({
'ext': remove_start(caption.get('caption_format'), 'web'),
'url': caption['url'],
'ext': EXT_MAP.get(caption.get('Format')),
})
# webpage subs
if not subtitles:
@ -288,9 +296,14 @@ class TikTokBaseIE(InfoExtractor):
self._create_url(user_name, aweme_id), aweme_id, fatal=False)
for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])):
subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({
'ext': remove_start(caption.get('Format'), 'web'),
'url': caption['Url'],
'ext': EXT_MAP.get(caption.get('Format')),
})
# Deprioritize creator_caption json since it can't be embedded or used by media players
for lang, subs_list in subtitles.items():
subtitles[lang] = sorted(subs_list, key=lambda x: preference(x['ext']))
return subtitles
def _parse_url_key(self, url_key):
@ -1458,9 +1471,11 @@ class TikTokLiveIE(TikTokBaseIE):
if webpage:
data = self._get_sigi_state(webpage, uploader or room_id)
room_id = (traverse_obj(data, ('UserModule', 'users', ..., 'roomId', {str_or_none}), get_all=False)
or self._search_regex(r'snssdk\d*://live\?room_id=(\d+)', webpage, 'room ID', default=None)
or room_id)
room_id = (
traverse_obj(data, ((
('LiveRoom', 'liveRoomUserInfo', 'user'),
('UserModule', 'users', ...)), 'roomId', {str}, any))
or self._search_regex(r'snssdk\d*://live\?room_id=(\d+)', webpage, 'room ID', default=room_id))
uploader = uploader or traverse_obj(
data, ('LiveRoom', 'liveRoomUserInfo', 'user', 'uniqueId'),
('UserModule', 'users', ..., 'uniqueId'), get_all=False, expected_type=str)

28
yt_dlp/extractor/toggle.py
View file

@ -28,35 +28,11 @@ class ToggleIE(InfoExtractor):
'skip_download': 'm3u8 download',
},
}, {
'note': 'DRM-protected video',
'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
'info_dict': {
'id': '341413',
'ext': 'wvm',
'title': 'Dug\'s Special Mission',
'description': 'md5:e86c6f4458214905c1772398fabc93e0',
'upload_date': '20150827',
'timestamp': 1440644006,
},
'params': {
'skip_download': 'DRM-protected wvm download',
},
'only_matching': True,
}, {
# this also tests correct video id extraction
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
'info_dict': {
'id': '332861',
'ext': 'mp4',
'title': '28th SEA Games (5 Show) - Episode 11',
'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
'upload_date': '20150605',
'timestamp': 1433480166,
},
'params': {
'skip_download': 'DRM-protected wvm download',
},
'skip': 'm3u8 links are geo-restricted',
'only_matching': True,
}, {
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True,

7
yt_dlp/extractor/tv5mondeplus.py
View file

@ -96,7 +96,7 @@ class TV5MondePlusIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, display_id, impersonate=True)
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
self.raise_geo_restricted(countries=['FR'])
@ -122,8 +122,9 @@ class TV5MondePlusIE(InfoExtractor):
if not token:
continue
deferred_json = self._download_json(
f'https://api.tv5monde.com/player/asset/{d_param}/resolve?condenseKS=true', display_id,
note='Downloading deferred info', headers={'Authorization': f'Bearer {token}'}, fatal=False)
f'https://api.tv5monde.com/player/asset/{d_param}/resolve?condenseKS=true',
display_id, 'Downloading deferred info', fatal=False, impersonate=True,
headers={'Authorization': f'Bearer {token}'})
v_url = traverse_obj(deferred_json, (0, 'url', {url_or_none}))
if not v_url:
continue

72
yt_dlp/extractor/tva.py
View file

@ -1,60 +1,29 @@
import functools
import re
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import float_or_none, int_or_none, smuggle_url, strip_or_none
from ..utils.traversal import traverse_obj
class TVAIE(InfoExtractor):
_VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
IE_NAME = 'tvaplus'
IE_DESC = 'TVA+'
_VALID_URL = r'https?://(?:www\.)?tvaplus\.ca/(?:[^/?#]+/)*[\w-]+-(?P<id>\d+)(?:$|[#?])'
_TESTS = [{
'url': 'https://videos.tva.ca/details/_5596811470001',
'info_dict': {
'id': '5596811470001',
'ext': 'mp4',
'title': 'Un extrait de l\'épisode du dimanche 8 octobre 2017 !',
'uploader_id': '5481942443001',
'upload_date': '20171003',
'timestamp': 1507064617,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'https://video.tva.ca/details/_5596811470001',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
return {
'_type': 'url_transparent',
'id': video_id,
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['CA']}),
'ie_key': 'BrightcoveNew',
}
class QubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?qub\.ca/(?:[^/]+/)*[0-9a-z-]+-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.qub.ca/tvaplus/tva/alerte-amber/saison-1/episode-01-1000036619',
'url': 'https://www.tvaplus.ca/tva/alerte-amber/saison-1/episode-01-1000036619',
'md5': '949490fd0e7aee11d0543777611fbd53',
'info_dict': {
'id': '6084352463001',
'ext': 'mp4',
'title': 'Ép 01. Mon dernier jour',
'title': 'Mon dernier jour',
'uploader_id': '5481942443001',
'upload_date': '20190907',
'timestamp': 1567899756,
'description': 'md5:9c0d7fbb90939420c651fd977df90145',
'thumbnail': r're:https://.+\.jpg',
'episode': 'Ép 01. Mon dernier jour',
'episode': 'Mon dernier jour',
'episode_number': 1,
'tags': ['alerte amber', 'alerte amber saison 1', 'surdemande'],
'duration': 2625.963,
@ -64,23 +33,36 @@ class QubIE(InfoExtractor):
'channel': 'TVA',
},
}, {
'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943',
'only_matching': True,
'url': 'https://www.tvaplus.ca/tva/le-baiser-du-barbu/le-baiser-du-barbu-886644190',
'info_dict': {
'id': '6354448043112',
'ext': 'mp4',
'title': 'Le Baiser du barbu',
'uploader_id': '5481942443001',
'upload_date': '20240606',
'timestamp': 1717694023,
'description': 'md5:025b1219086c1cbf4bc27e4e034e8b57',
'thumbnail': r're:https://.+\.jpg',
'episode': 'Le Baiser du barbu',
'tags': ['fullepisode', 'films'],
'duration': 6053.504,
'series': 'Le Baiser du barbu',
'channel': 'TVA',
},
}]
# reference_id also works with old account_id(5481942443001)
# BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5813221784001/default_default/index.html?videoId=ref:%s'
_BC_URL_TMPL = 'https://players.brightcove.net/5481942443001/default_default/index.html?videoId={}'
def _real_extract(self, url):
entity_id = self._match_id(url)
webpage = self._download_webpage(url, entity_id)
entity = self._search_nextjs_data(webpage, entity_id)['props']['initialProps']['pageProps']['fallbackData']
entity = self._search_nextjs_data(webpage, entity_id)['props']['pageProps']['staticEntity']
video_id = entity['videoId']
episode = strip_or_none(entity.get('name'))
return {
'_type': 'url_transparent',
'url': f'https://videos.tva.ca/details/_{video_id}',
'ie_key': TVAIE.ie_key(),
'url': smuggle_url(self._BC_URL_TMPL.format(video_id), {'geo_countries': ['CA']}),
'ie_key': BrightcoveNewIE.ie_key(),
'id': video_id,
'title': episode,
'episode': episode,

26
yt_dlp/extractor/tver.py
View file

@ -10,7 +10,7 @@ from ..utils import (
class TVerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video)/)+(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video|olympic/paris2024/video)/)+(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'skip': 'videos are only available for 7 days',
'url': 'https://tver.jp/episodes/ep83nf3w4p',
@ -23,6 +23,20 @@ class TVerIE(InfoExtractor):
'channel': 'テレビ朝日',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://tver.jp/olympic/paris2024/video/6359578055112/',
'info_dict': {
'id': '6359578055112',
'ext': 'mp4',
'title': '堀米雄斗 金メダルで五輪連覇！「みんなの応援が最後に乗れたカギ」',
'timestamp': 1722279928,
'upload_date': '20240729',
'tags': ['20240729', 'japanese', 'japanmedal', 'paris'],
'uploader_id': '4774017240001',
'thumbnail': r're:https?://[^/?#]+boltdns\.net/[^?#]+/1920x1080/match/image\.jpg',
'duration': 670.571,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://tver.jp/corner/f0103888',
'only_matching': True,
@ -47,7 +61,15 @@ class TVerIE(InfoExtractor):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
if video_type not in {'series', 'episodes'}:
if video_type == 'olympic/paris2024/video':
# Player ID is taken from .content.brightcove.E200.pro.pc.account_id:
# https://tver.jp/olympic/paris2024/req/api/hook?q=https%3A%2F%2Folympic-assets.tver.jp%2Fweb-static%2Fjson%2Fconfig.json&d=
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % ('4774017240001', video_id),
{'geo_countries': ['JP']}), 'BrightcoveNew')
elif video_type not in {'series', 'episodes'}:
webpage = self._download_webpage(url, video_id, note='Resolving to new URL')
video_id = self._match_id(self._search_regex(
(r'canonical"\s*href="(https?://tver\.jp/[^"]+)"', r'&link=(https?://tver\.jp/[^?&]+)[?&]'),

4
yt_dlp/extractor/unsupported.py
View file

@ -49,6 +49,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
r'amazon\.(?:\w{2}\.)?\w+/gp/video',
r'music\.amazon\.(?:\w{2}\.)?\w+',
r'(?:watch|front)\.njpwworld\.com',
r'qub\.ca/vrai',
)
_TESTS = [{
@ -149,6 +150,9 @@ class KnownDRMIE(UnsupportedInfoExtractor):
}, {
'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
'only_matching': True,
}, {
'url': 'https://www.qub.ca/vrai/l-effet-bocuse-d-or/saison-1/l-effet-bocuse-d-or-saison-1-bande-annonce-1098225063',
'only_matching': True,
}]
def _real_extract(self, url):

426
yt_dlp/extractor/vidyard.py Normal file
View file

@ -0,0 +1,426 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
float_or_none,
int_or_none,
join_nonempty,
mimetype2ext,
parse_resolution,
str_or_none,
unescapeHTML,
url_or_none,
)
from ..utils.traversal import traverse_obj
class VidyardBaseIE(InfoExtractor):
_HEADERS = {'Referer': 'https://play.vidyard.com/'}
def _get_formats_and_subtitles(self, sources, video_id):
formats, subtitles = [], {}
def add_hls_fmts_and_subs(m3u8_url):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id='hls', headers=self._HEADERS, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
hls_list = isinstance(sources, dict) and sources.pop('hls', None)
if master_m3u8_url := traverse_obj(
hls_list, (lambda _, v: v['profile'] == 'auto', 'url', {url_or_none}, any)):
add_hls_fmts_and_subs(master_m3u8_url)
if not formats: # These are duplicate and unnecesary requests if we got 'auto' hls fmts
for variant_m3u8_url in traverse_obj(hls_list, (..., 'url', {url_or_none})):
add_hls_fmts_and_subs(variant_m3u8_url)
for source_type, source_list in traverse_obj(sources, ({dict.items}, ...)):
for source in traverse_obj(source_list, lambda _, v: url_or_none(v['url'])):
profile = source.get('profile')
formats.append({
'url': source['url'],
'ext': mimetype2ext(source.get('mimeType'), default=None),
'format_id': join_nonempty('http', source_type, profile),
**parse_resolution(profile),
})
self._remove_duplicate_formats(formats)
return formats, subtitles
def _get_direct_subtitles(self, caption_json):
subs = {}
for caption in traverse_obj(caption_json, lambda _, v: url_or_none(v['vttUrl'])):
subs.setdefault(caption.get('language') or 'und', []).append({
'url': caption['vttUrl'],
'name': caption.get('name'),
})
return subs
def _fetch_video_json(self, video_id):
return self._download_json(
f'https://play.vidyard.com/player/{video_id}.json', video_id)['payload']
def _process_video_json(self, json_data, video_id):
formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], video_id)
self._merge_subtitles(self._get_direct_subtitles(json_data.get('captions')), target=subtitles)
return {
**traverse_obj(json_data, {
'id': ('facadeUuid', {str}),
'display_id': ('videoId', {int}, {str_or_none}),
'title': ('name', {str}),
'description': ('description', {str}, {unescapeHTML}, {lambda x: x or None}),
'duration': ((
('milliseconds', {functools.partial(float_or_none, scale=1000)}),
('seconds', {int_or_none})), any),
'thumbnails': ('thumbnailUrls', ('small', 'normal'), {'url': {url_or_none}}),
'tags': ('tags', ..., 'name', {str}),
}),
'formats': formats,
'subtitles': subtitles,
'http_headers': self._HEADERS,
}
class VidyardIE(VidyardBaseIE):
_VALID_URL = [
r'https?://[\w-]+(?:\.hubs)?\.vidyard\.com/watch/(?P<id>[\w-]+)',
r'https?://(?:embed|share)\.vidyard\.com/share/(?P<id>[\w-]+)',
r'https?://play\.vidyard\.com/(?:player/)?(?P<id>[\w-]+)',
]
_EMBED_REGEX = [r'<iframe[^>]* src=["\'](?P<url>(?:https?:)?//play\.vidyard\.com/[\w-]+)']
_TESTS = [{
'url': 'https://vyexample03.hubs.vidyard.com/watch/oTDMPlUv--51Th455G5u7Q',
'info_dict': {
'id': 'oTDMPlUv--51Th455G5u7Q',
'display_id': '50347',
'ext': 'mp4',
'title': 'Homepage Video',
'description': 'Look I changed the description.',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/50347/OUPa5LTKV46849sLYngMqQ_small.jpg',
'duration': 99,
'tags': ['these', 'are', 'all', 'tags'],
},
}, {
'url': 'https://share.vidyard.com/watch/PaQzDAT1h8JqB8ivEu2j6Y?',
'info_dict': {
'id': 'PaQzDAT1h8JqB8ivEu2j6Y',
'display_id': '9281024',
'ext': 'mp4',
'title': 'Inline Embed',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/spacer.gif',
'duration': 41.186,
},
}, {
'url': 'https://embed.vidyard.com/share/oTDMPlUv--51Th455G5u7Q',
'info_dict': {
'id': 'oTDMPlUv--51Th455G5u7Q',
'display_id': '50347',
'ext': 'mp4',
'title': 'Homepage Video',
'description': 'Look I changed the description.',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/50347/OUPa5LTKV46849sLYngMqQ_small.jpg',
'duration': 99,
'tags': ['these', 'are', 'all', 'tags'],
},
}, {
# First video from playlist below
'url': 'https://embed.vidyard.com/share/SyStyHtYujcBHe5PkZc5DL',
'info_dict': {
'id': 'SyStyHtYujcBHe5PkZc5DL',
'display_id': '41974005',
'ext': 'mp4',
'title': 'Prepare the Frame and Track for Palm Beach Polysatin Shutters With BiFold Track',
'description': r're:In this video, you will learn how to prepare the frame.+',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/41974005/IJw7oCaJcF1h7WWu3OVZ8A_small.png',
'duration': 258.666,
},
}, {
# Playlist
'url': 'https://thelink.hubs.vidyard.com/watch/pwu7pCYWSwAnPxs8nDoFrE',
'info_dict': {
'id': 'pwu7pCYWSwAnPxs8nDoFrE',
'title': 'PLAYLIST - Palm Beach Shutters- Bi-Fold Track System Installation',
'entries': [{
'id': 'SyStyHtYujcBHe5PkZc5DL',
'display_id': '41974005',
'ext': 'mp4',
'title': 'Prepare the Frame and Track for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/41974005/IJw7oCaJcF1h7WWu3OVZ8A_small.png',
'duration': 258.666,
}, {
'id': '1Fw4B84jZTXLXWqkE71RiM',
'display_id': '5861113',
'ext': 'mp4',
'title': 'Palm Beach - Bi-Fold Track System "Frame Installation"',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861113/29CJ54s5g1_aP38zkKLHew_small.jpg',
'duration': 167.858,
}, {
'id': 'DqP3wBvLXSpxrcqpT5kEeo',
'display_id': '41976334',
'ext': 'mp4',
'title': 'Install the Track for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861090/RwG2VaTylUa6KhSTED1r1Q_small.png',
'duration': 94.229,
}, {
'id': 'opfybfxpzQArxqtQYB6oBU',
'display_id': '41976364',
'ext': 'mp4',
'title': 'Install the Panel for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5860926/JIOaJR08dM4QgXi_iQ2zGA_small.png',
'duration': 191.467,
}, {
'id': 'rWrXvkbTNNaNqD6189HJya',
'display_id': '41976382',
'ext': 'mp4',
'title': 'Adjust the Panels for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5860687/CwHxBv4UudAhOh43FVB4tw_small.png',
'duration': 138.155,
}, {
'id': 'eYPTB521MZ9TPEArSethQ5',
'display_id': '41976409',
'ext': 'mp4',
'title': 'Assemble and Install the Valance for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861425/0y68qlMU4O5VKU7bJ8i_AA_small.png',
'duration': 148.224,
}],
},
'playlist_count': 6,
}, {
# Non hubs.vidyard.com playlist
'url': 'https://salesforce.vidyard.com/watch/d4vqPjs7Q5EzVEis5QT3jd',
'info_dict': {
'id': 'd4vqPjs7Q5EzVEis5QT3jd',
'title': 'How To: Service Cloud: Import External Content in Lightning Knowledge',
'entries': [{
'id': 'mcjDpSZir2iSttbvFkx6Rv',
'display_id': '29479036',
'ext': 'mp4',
'title': 'Welcome to this Expert Coaching Series',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/ouyQi9WuwyiOupChUWNmjQ/7170d3485ba602e012df05_small.jpg',
'duration': 38.205,
}, {
'id': '84bPYwpg243G6xYEfJdYw9',
'display_id': '21820704',
'ext': 'mp4',
'title': 'Chapter 1 - Title + Agenda',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/HFPN0ZgQq4Ow8BghGcQSow/bfaa30123c8f6601e7d7f2_small.jpg',
'duration': 98.016,
}, {
'id': 'nP17fMuvA66buVHUrzqjTi',
'display_id': '21820707',
'ext': 'mp4',
'title': 'Chapter 2 - Import Options',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/rGRIF5nFjPI9OOA2qJ_Dbg/86a8d02bfec9a566845dd4_small.jpg',
'duration': 199.136,
}, {
'id': 'm54EcwXdpA5gDBH5rgCYoV',
'display_id': '21820710',
'ext': 'mp4',
'title': 'Chapter 3 - Importing Article Translations',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/IVX4XR8zpSsiNIHx45kz-A/1ccbf8a29a33856d06b3ed_small.jpg',
'duration': 184.352,
}, {
'id': 'j4nzS42oq4hE9oRV73w3eQ',
'display_id': '21820716',
'ext': 'mp4',
'title': 'Chapter 4 - Best Practices',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/BtrRrQpRDLbA4AT95YQyog/1f1e6b8e7fdc3fa95ec8d3_small.jpg',
'duration': 296.960,
}, {
'id': 'y28PYfW5pftvers9PXzisC',
'display_id': '21820727',
'ext': 'mp4',
'title': 'Chapter 5 - Migration Steps',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/K2CdQOXDfLcrVTF60r0bdw/a09239ada28b6ffce12b1f_small.jpg',
'duration': 620.640,
}, {
'id': 'YWU1eQxYvhj29SjYoPw5jH',
'display_id': '21820733',
'ext': 'mp4',
'title': 'Chapter 6 - Demo',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/rsmhP-cO8dAa8ilvFGCX0g/7911ef415167cd14032068_small.jpg',
'duration': 631.456,
}, {
'id': 'nmEvVqpwdJUgb74zKsLGxn',
'display_id': '29479037',
'ext': 'mp4',
'title': 'Schedule Your Follow-Up',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/Rtwc7X4PEkF4Ae5kHi-Jvw/174ebed3f34227b1ffa1d0_small.jpg',
'duration': 33.608,
}],
},
'playlist_count': 8,
}, {
# URL of iframe embed src
'url': 'https://play.vidyard.com/iDqTwWGrd36vaLuaCY3nTs.html',
'info_dict': {
'id': 'iDqTwWGrd36vaLuaCY3nTs',
'display_id': '9281009',
'ext': 'mp4',
'title': 'Lightbox Embed',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/spacer.gif',
'duration': 39.035,
},
}, {
# Player JSON URL
'url': 'https://play.vidyard.com/player/7GAApnNNbcZZ46k6JqJQSh.json?disable_analytics=0',
'info_dict': {
'id': '7GAApnNNbcZZ46k6JqJQSh',
'display_id': '820026',
'ext': 'mp4',
'title': 'The Art of Storytelling: How to Deliver Your Brand Story with Content & Social',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/MhbE-5sEFQu4x3fI6FkNlA/41eb5717c557cd19456910_small.jpg',
'duration': 2153.013,
'tags': ['Summit2017'],
},
}, {
'url': 'http://share.vidyard.com/share/diYeo6YR2yiGgL8odvS8Ri',
'only_matching': True,
}, {
'url': 'https://play.vidyard.com/FFlz3ZpxhIfKQ1fd9DAryA',
'only_matching': True,
}, {
'url': 'https://play.vidyard.com/qhMAu5A76GZVrFzOPgSf9A/type/standalone',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# URL containing inline/lightbox embedded video
'url': 'https://resources.altium.com/p/2-the-extreme-importance-of-pc-board-stack-up',
'info_dict': {
'id': 'GDx1oXrFWj4XHbipfoXaMn',
'display_id': '3225198',
'ext': 'mp4',
'title': 'The Extreme Importance of PC Board Stack Up',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/73_Q3_hBexWX7Og1sae6cg/9998fa4faec921439e2c04_small.jpg',
'duration': 3422.742,
},
}, {
# <script ... id="vidyard_embed_code_DXx2sW4WaLA6hTdGFz7ja8" src="//play.vidyard.com/DXx2sW4WaLA6hTdGFz7ja8.js?
'url': 'http://videos.vivint.com/watch/DXx2sW4WaLA6hTdGFz7ja8',
'info_dict': {
'id': 'DXx2sW4WaLA6hTdGFz7ja8',
'display_id': '2746529',
'ext': 'mp4',
'title': 'How To Powercycle the Smart Hub Panel',
'duration': 30.613,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/_-6cw8xQUJ3qiCs_JENc_A/b21d7a5e47967f49399d30_small.jpg',
},
}, {
# <script id="vidyard_embed_code_MIBHhiLVTxga7wqLsuoDjQ" src="//embed.vidyard.com/embed/MIBHhiLVTxga7wqLsuoDjQ/inline?v=2.1">
'url': 'https://www.babypips.com/learn/forex/introduction-to-metatrader4',
'info_dict': {
'id': 'MIBHhiLVTxga7wqLsuoDjQ',
'display_id': '20291',
'ext': 'mp4',
'title': 'Lesson 1 - Opening an MT4 Account',
'description': 'Never heard of MetaTrader4? Here\'s the 411 on the popular trading platform!',
'duration': 168,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/20291/IM-G2WXQR9VBLl2Cmzvftg_small.jpg',
},
}, {
# <iframe ... src="//play.vidyard.com/d61w8EQoZv1LDuPxDkQP2Q/type/background?preview=1"
'url': 'https://www.avaya.com/en/',
'info_dict': {
# These values come from the generic extractor and don't matter
'id': str,
'title': str,
'age_limit': 0,
'upload_date': str,
'description': str,
'thumbnail': str,
'timestamp': float,
},
'playlist': [{
'info_dict': {
'id': 'd61w8EQoZv1LDuPxDkQP2Q',
'display_id': '42456529',
'ext': 'mp4',
'title': 'GettyImages-1027',
'duration': 6.0,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/42061563/p6bY08d2N4e4IDz-7J4_wkgsPq3-qgcx_small.jpg',
},
}, {
'info_dict': {
'id': 'VAsYDi7eiqZRbHodUA2meC',
'display_id': '42456569',
'ext': 'mp4',
'title': 'GettyImages-1325598833',
'duration': 6.083,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/42052358/y3qrbDpn_2quWr_5XBi7yzS3UvEI__ZM_small.jpg',
},
}],
'playlist_count': 2,
}, {
# <div class="vidyard-player-embed" data-uuid="vpCWTVHw3qrciLtVY94YkS"
'url': 'https://www.gogoair.com/',
'info_dict': {
# These values come from the generic extractor and don't matter
'id': str,
'title': str,
'description': str,
'age_limit': 0,
},
'playlist': [{
'info_dict': {
'id': 'vpCWTVHw3qrciLtVY94YkS',
'display_id': '40780699',
'ext': 'mp4',
'title': 'Upgrade to AVANCE 100% worth it - Jason Talley, Owner and Pilot, Testimonial',
'description': 'md5:f609824839439a51990cef55ffc472aa',
'duration': 70.737,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/40780699/KzjfYZz5MZl2gHF_e-4i2c6ib1cLDweQ_small.jpg',
},
}, {
'info_dict': {
'id': 'xAmV9AsLbnitCw35paLBD8',
'display_id': '31130867',
'ext': 'mp4',
'title': 'Brad Keselowski goes faster with Gogo AVANCE inflight Wi-Fi',
'duration': 132.565,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/31130867/HknyDtLdm2Eih9JZ4A5XLjhfBX_6HRw5_small.jpg',
},
}, {
'info_dict': {
'id': 'RkkrFRNxfP79nwCQavecpF',
'display_id': '39009815',
'ext': 'mp4',
'title': 'Live Demo of Gogo Galileo',
'description': 'md5:e2df497236f4e12c3fef8b392b5f23e0',
'duration': 112.128,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/38144873/CWLlxfUbJ4Gh0ThbUum89IsEM4yupzMb_small.jpg',
},
}],
'playlist_count': 3,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
# Handle protocol-less embed URLs
for embed_url in super()._extract_embed_urls(url, webpage):
if embed_url.startswith('//'):
embed_url = f'https:{embed_url}'
yield embed_url
# Extract inline/lightbox embeds
for embed_element in re.findall(
r'(<(?:img|div)[^>]* class=(["\'])(?:[^>"\']* )?vidyard-player-embed(?: [^>"\']*)?\2[^>]+>)', webpage):
if video_id := extract_attributes(embed_element[0]).get('data-uuid'):
yield f'https://play.vidyard.com/{video_id}'
for embed_id in re.findall(r'<script[^>]* id=["\']vidyard_embed_code_([\w-]+)["\']', webpage):
yield f'https://play.vidyard.com/{embed_id}'
def _real_extract(self, url):
video_id = self._match_id(url)
video_json = self._fetch_video_json(video_id)
if len(video_json['chapters']) == 1:
return self._process_video_json(video_json['chapters'][0], video_id)
return self.playlist_result(
[self._process_video_json(chapter, video_id) for chapter in video_json['chapters']],
str(video_json['playerUuid']), video_json.get('name'))

160
yt_dlp/extractor/vimeo.py
View file

@ -1,6 +1,7 @@
import base64
import functools
import itertools
import json
import re
import urllib.parse
@ -14,6 +15,7 @@ from ..utils import (
determine_ext,
get_element_by_class,
int_or_none,
join_nonempty,
js_to_json,
merge_dicts,
parse_filesize,
@ -84,29 +86,23 @@ class VimeoBaseInfoExtractor(InfoExtractor):
expected=True)
return password
def _verify_video_password(self, url, video_id, password, token, vuid):
if url.startswith('http://'):
# vimeo only supports https now, but the user can give an http url
url = url.replace('http://', 'https://')
self._set_vimeo_cookie('vuid', vuid)
return self._download_webpage(
url + '/password', video_id, 'Verifying the password',
'Wrong password', data=urlencode_postdata({
'password': password,
'token': token,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': url,
})
def _extract_xsrft_and_vuid(self, webpage):
xsrft = self._search_regex(
r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
webpage, 'login token', group='xsrft')
vuid = self._search_regex(
r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
webpage, 'vuid', group='vuid')
return xsrft, vuid
def _verify_video_password(self, video_id, password, token):
url = f'https://vimeo.com/{video_id}'
try:
return self._download_webpage(
f'{url}/password', video_id,
'Submitting video password', data=json.dumps({
'password': password,
'token': token,
}, separators=(',', ':')).encode(), headers={
'Accept': '*/*',
'Content-Type': 'application/json',
'Referer': url,
}, impersonate=True)
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 418:
raise ExtractorError('Wrong password', expected=True)
raise
def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
vimeo_config = self._search_regex(
@ -216,16 +212,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
owner = video_data.get('owner') or {}
video_uploader_url = owner.get('url')
duration = int_or_none(video_data.get('duration'))
chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
chapters = [{
'title': current_chapter.get('title'),
'start_time': current_chapter.get('timecode'),
'end_time': next_chapter.get('timecode'),
} for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
if chapters and chapters[0]['start_time']: # Chapters may not start from 0
chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
return {
'id': str_or_none(video_data.get('id')) or video_id,
'title': video_title,
@ -233,8 +219,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
'uploader_url': video_uploader_url,
'thumbnails': thumbnails,
'duration': duration,
'chapters': chapters or None,
'duration': int_or_none(video_data.get('duration')),
'chapters': sorted(traverse_obj(config, (
'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, {
'title': ('title', {str}),
'start_time': ('timecode', {int_or_none}),
})), key=lambda c: c['start_time']) or None,
'formats': formats,
'subtitles': subtitles,
'live_status': live_status,
@ -712,6 +702,39 @@ class VimeoIE(VimeoBaseInfoExtractor):
'skip_download': True,
},
},
{
# chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308
'url': 'https://player.vimeo.com/video/756714419',
'info_dict': {
'id': '756714419',
'ext': 'mp4',
'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep',
'uploader': 'Alex Howard',
'uploader_id': 'user54729178',
'uploader_url': 'https://vimeo.com/user54729178',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280',
'duration': 2636,
'chapters': [
{'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
{'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'},
{'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'},
{'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'},
{'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'},
{'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"},
{'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'},
{'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'},
{'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'},
{'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'},
{'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'},
{'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'},
],
},
'params': {
'http_headers': {'Referer': 'https://sleepsuperconference.com'},
'skip_download': 'm3u8',
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
},
{
# user playlist alias -> https://vimeo.com/258705797
'url': 'https://vimeo.com/user26785108/newspiritualguide',
@ -745,21 +768,34 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise ExtractorError('Wrong video password', expected=True)
return checked
def _extract_from_api(self, video_id, unlisted_hash=None):
token = self._download_json(
'https://vimeo.com/_rv/jwt', video_id, headers={
'X-Requested-With': 'XMLHttpRequest',
})['token']
api_url = 'https://api.vimeo.com/videos/' + video_id
if unlisted_hash:
api_url += ':' + unlisted_hash
video = self._download_json(
api_url, video_id, headers={
'Authorization': 'jwt ' + token,
def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None):
return self._download_json(
join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'),
video_id, 'Downloading API JSON', headers={
'Authorization': f'jwt {jwt_token}',
'Accept': 'application/json',
}, query={
'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
})
def _extract_from_api(self, video_id, unlisted_hash=None):
viewer = self._download_json(
'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info')
for retry in (False, True):
try:
video = self._call_videos_api(video_id, viewer['jwt'], unlisted_hash)
except ExtractorError as e:
if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
and 'password' in traverse_obj(
e.cause.response.read(),
({bytes.decode}, {json.loads}, 'invalid_parameters', ..., 'field'),
)):
self._verify_video_password(
video_id, self._get_video_password(), viewer['xsrft'])
continue
raise
info = self._parse_config(self._download_json(
video['config_url'], video_id), video_id)
get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
@ -865,12 +901,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
redirect_url, video_id, headers)
return self._parse_config(config, video_id)
if re.search(r'<form[^>]+?id="pw_form"', webpage):
video_password = self._get_video_password()
token, vuid = self._extract_xsrft_and_vuid(webpage)
webpage = self._verify_video_password(
redirect_url, video_id, video_password, token, vuid)
vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
if vimeo_config:
seed_status = vimeo_config.get('seed_status') or {}
@ -1237,7 +1267,7 @@ class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
class VimeoReviewIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:review'
IE_DESC = 'Review pages on vimeo'
_VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
_VALID_URL = r'https?://vimeo\.com/(?P<user>[^/?#]+)/review/(?P<id>\d+)/(?P<hash>[\da-f]{10})'
_TESTS = [{
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
'md5': 'c507a72f780cacc12b2248bb4006d253',
@ -1283,28 +1313,22 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
}]
def _real_extract(self, url):
page_url, video_id = self._match_valid_url(url).groups()
data = self._download_json(
page_url.replace('/review/', '/review/data/'), video_id)
user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash')
data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}'
data = self._download_json(data_url, video_id)
if data.get('isLocked') is True:
video_password = self._get_video_password()
viewer = self._download_json(
'https://vimeo.com/_rv/viewer', video_id)
webpage = self._verify_video_password(
'https://vimeo.com/' + video_id, video_id,
video_password, viewer['xsrft'], viewer['vuid'])
clip_page_config = self._parse_json(self._search_regex(
r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
webpage, 'clip page config'), video_id)
config_url = clip_page_config['player']['config_url']
clip_data = clip_page_config.get('clip') or {}
else:
clip_data = data['clipData']
config_url = clip_data['configUrl']
self._verify_video_password(video_id, video_password, viewer['xsrft'])
data = self._download_json(data_url, video_id)
clip_data = data['clipData']
config_url = clip_data['configUrl']
config = self._download_json(config_url, video_id)
info_dict = self._parse_config(config, video_id)
source_format = self._extract_original_format(
page_url + '/action', video_id)
f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', video_id,
unlisted_hash=traverse_obj(config_url, ({parse_qs}, 'h', -1)))
if source_format:
info_dict['formats'].append(source_format)
info_dict['description'] = clean_html(clip_data.get('description'))

108
yt_dlp/extractor/vtv.py Normal file
View file

@ -0,0 +1,108 @@
from .common import InfoExtractor
from ..utils import extract_attributes, get_element_html_by_class, remove_start
class VTVGoIE(InfoExtractor):
_VALID_URL = [
r'https?://(?:www\.)?vtvgo\.vn/(kho-video|tin-tuc)/[\w.-]*?(?P<id>\d+)(?:\.[a-z]+|/)?(?:$|[?#])',
r'https?://(?:www\.)?vtvgo\.vn/digital/detail\.php\?(?:[^#]+&)?content_id=(?P<id>\d+)',
]
_TESTS = [{
'url': 'https://vtvgo.vn/kho-video/bep-vtv-vit-chao-rieng-so-24-888456.html',
'info_dict': {
'id': '888456',
'ext': 'mp4',
'title': 'Bếp VTV | Vịt chao riềng | Số 24',
'description': 'md5:2b4e93ec2b954304170d32be288ce2c8',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20230201/VIT-CHAO-RIENG_VTV_638108894672812459.jpg',
},
}, {
'url': 'https://vtvgo.vn/tin-tuc/hot-search-1-zlife-khong-ngo-toi-phai-khong-862074',
'info_dict': {
'id': '862074',
'ext': 'mp4',
'title': 'Hot Search #1 | Zlife | Không ngờ tới phải không? ',
'description': 'md5:e967d0e2efbbebbee8814a55799b4d0f',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20220504/6b9a8552-e71c-46ce-bc9d-50c9bb506f9c.jpeg',
},
}, {
'url': 'https://vtvgo.vn/kho-video/918311.html',
'info_dict': {
'id': '918311',
'title': 'Cà phê sáng | 05/02/2024 | Tái hiện hình ảnh Hà Nội xưa tại ngôi nhà di sản',
'ext': 'mp4',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240205/0506_ca_phe_sang_638427226021318322.jpg',
'description': 'md5:b121c67948f1ce58e6a036042fc14c1b',
},
}, {
'url': 'https://vtvgo.vn/digital/detail.php?digital_id=168&content_id=918634',
'info_dict': {
'id': '918634',
'ext': 'mp4',
'title': 'Gặp nhau cuối năm | Táo quân 2024',
'description': 'md5:a1c221e78e5954d29d49b2a11c20513c',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240210/d0f73369-8f03-4108-9edd-83d4bc3997b2.png',
},
}, {
'url': 'https://vtvgo.vn/digital/detail.php?content_id=919358',
'info_dict': {
'id': '919358',
'ext': 'mp4',
'title': 'Chúng ta của 8 năm sau | Tập 45 | Dương có bằng chứng, nhân chứng vạch mặt ông Khiêm',
'description': 'md5:16ff5208cac6585137f554472a4677f3',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240221/550deff9-7736-4a0e-8b5d-33274d97cd7d.jpg',
},
}, {
'url': 'https://vtvgo.vn/kho-video/888456',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex(
r'(?:var\s+link\s*=\s*|addPlayer\()["\'](https://[^"\']+/index\.m3u8)["\']', webpage, 'm3u8 url')
return {
'id': video_id,
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
}
class VTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vtv\.vn/video/[\w-]*?(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'https://vtv.vn/video/thoi-su-20h-vtv1-12-6-2024-680411.htm',
'info_dict': {
'id': '680411',
'ext': 'mp4',
'title': 'Thời sự 20h VTV1 - 12/6/2024 - Video đã phát trên VTV1 | VTV.VN',
'thumbnail': 'https://cdn-images.vtv.vn/zoom/600_315/66349b6076cb4dee98746cf1/2024/06/12/thumb/1206-ts-20h-02929741475480320806760.mp4/thumb0.jpg',
},
}, {
'url': 'https://vtv.vn/video/zlife-1-khong-ngo-toi-phai-khong-vtv24-560248.htm',
'info_dict': {
'id': '560248',
'ext': 'mp4',
'title': 'ZLife #1: Không ngờ tới phải không? | VTV24 - Video đã phát trên VTV-NEWS | VTV.VN',
'description': 'Ai đứng sau vụ việc thay đổi ảnh đại diện trên các trang mạng xã hội của VTV Digital tối 2/5?',
'thumbnail': 'https://video-thumbs.mediacdn.vn/zoom/600_315/vtv/2022/5/13/t67s6btf3ji-16524555726231894427334.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_vid = extract_attributes(get_element_html_by_class(
'VCSortableInPreviewMode', get_element_html_by_class(
'video-highlight-box', webpage)))['data-vid']
m3u8_url = f'https://cdn-videos.vtv.vn/{remove_start(data_vid, "vtv.mediacdn.vn/")}/master.m3u8'
return {
'id': video_id,
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
}

15
yt_dlp/extractor/yle_areena.py
View file

@ -11,6 +11,7 @@ from ..utils import (
class YleAreenaIE(InfoExtractor):
_VALID_URL = r'https?://areena\.yle\.fi/(?P<id>[\d-]+)'
_GEO_COUNTRIES = ['FI']
_TESTS = [
{
'url': 'https://areena.yle.fi/1-4371942',
@ -19,7 +20,7 @@ class YleAreenaIE(InfoExtractor):
'id': '0_a3tjk92c',
'ext': 'mp4',
'title': 'Pouchit',
'description': 'md5:d487309c3abbe5650265bbd1742d2f82',
'description': 'md5:01071d7056ceec375f63960f90c35366',
'series': 'Modernit miehet',
'season': 'Season 1',
'season_number': 1,
@ -87,8 +88,8 @@ class YleAreenaIE(InfoExtractor):
})
# Example title: 'K1, J2: Pouchit | Modernit miehet'
series, season_number, episode_number, episode = self._search_regex(
r'K(?P<season_no>[\d]+),\s*J(?P<episode_no>[\d]+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
season_number, episode_number, episode, series = self._search_regex(
r'K(?P<season_no>\d+),\s*J(?P<episode_no>\d+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
default=(None, None, None, None))
description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
@ -110,10 +111,12 @@ class YleAreenaIE(InfoExtractor):
'ie_key': KalturaIE.ie_key(),
}
else:
formats, subs = self._extract_m3u8_formats_and_subtitles(
video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls')
self._merge_subtitles(subs, target=subtitles)
info_dict = {
'id': video_id,
'formats': self._extract_m3u8_formats(
video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls'),
'formats': formats,
}
return {
@ -129,6 +132,6 @@ class YleAreenaIE(InfoExtractor):
or int_or_none(episode_number)),
'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
'subtitles': subtitles,
'subtitles': subtitles or None,
'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
}

2
yt_dlp/extractor/youku.py
View file

@ -136,7 +136,7 @@ class YoukuIE(InfoExtractor):
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0524',
'ccode': '0564',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,

359
yt_dlp/extractor/youtube.py
View file

@ -72,133 +72,169 @@ STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
# any clients starting with _ cannot be explicitly requested by the user
INNERTUBE_CLIENTS = {
'web': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20220801.00.00',
'clientVersion': '2.20240726.00.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
},
# Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
'web_safari': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20240726.00.00',
'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
},
'web_embedded': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_EMBEDDED_PLAYER',
'clientVersion': '1.20220731.00.00',
'clientVersion': '1.20240723.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 56,
},
'web_music': {
'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
'INNERTUBE_HOST': 'music.youtube.com',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_REMIX',
'clientVersion': '1.20220727.01.00',
'clientVersion': '1.20240724.00.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
},
'web_creator': {
'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_CREATOR',
'clientVersion': '1.20220726.00.00',
'clientVersion': '1.20240723.03.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
},
'android': {
'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID',
'clientVersion': '19.09.37',
'clientVersion': '19.29.37',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.youtube/19.29.37 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
'REQUIRE_JS_PLAYER': False,
},
'android_embedded': {
'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_EMBEDDED_PLAYER',
'clientVersion': '19.09.37',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
'REQUIRE_JS_PLAYER': False,
},
'android_music': {
'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_MUSIC',
'clientVersion': '6.42.52',
'clientVersion': '7.11.50',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.music/6.42.52 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.music/7.11.50 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
'REQUIRE_JS_PLAYER': False,
},
'android_creator': {
'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_CREATOR',
'clientVersion': '22.30.100',
'clientVersion': '24.30.100',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.creator/24.30.100 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
'REQUIRE_JS_PLAYER': False,
},
# YouTube Kids videos aren't returned on this client for some reason
'android_vr': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_VR',
'clientVersion': '1.57.29',
'deviceMake': 'Oculus',
'deviceModel': 'Quest 3',
'androidSdkVersion': 32,
'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.57.29 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip',
'osName': 'Android',
'osVersion': '12L',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 28,
'REQUIRE_JS_PLAYER': False,
},
'android_testsuite': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_TESTSUITE',
'clientVersion': '1.9',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/1.9 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 30,
'REQUIRE_JS_PLAYER': False,
'PLAYER_PARAMS': '2AMB',
},
# This client only has legacy formats and storyboards
'android_producer': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_PRODUCER',
'clientVersion': '0.111.1',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.producer/0.111.1 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 91,
'REQUIRE_JS_PLAYER': False,
},
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
'ios': {
'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS',
'clientVersion': '19.09.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
'clientVersion': '19.29.1',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtube/19.29.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_JS_PLAYER': False,
},
'ios_embedded': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MESSAGES_EXTENSION',
'clientVersion': '19.09.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
'REQUIRE_JS_PLAYER': False,
},
'ios_music': {
'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MUSIC',
'clientVersion': '6.33.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtubemusic/6.33.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
'clientVersion': '7.08.2',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtubemusic/7.08.2 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
@ -208,9 +244,12 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_CREATOR',
'clientVersion': '22.33.101',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
'clientVersion': '24.30.100',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.ytcreator/24.30.100 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
@ -219,19 +258,26 @@ INNERTUBE_CLIENTS = {
# mweb has 'ultralow' formats
# See: https://github.com/yt-dlp/yt-dlp/pull/557
'mweb': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'MWEB',
'clientVersion': '2.20220801.00.00',
'clientVersion': '2.20240726.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
},
'tv': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5',
'clientVersion': '7.20240724.13.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
},
# This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
# See: https://github.com/zerodytrash/YouTube-Internal-Clients
'tv_embedded': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
@ -249,6 +295,7 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 95,
'REQUIRE_JS_PLAYER': False,
},
}
@ -262,7 +309,7 @@ def _split_innertube_client(client_name):
def short_client_name(client_name):
main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
main, *parts = _split_innertube_client(client_name)[0].split('_')
return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
@ -270,27 +317,22 @@ def build_innertube_clients():
THIRD_PARTY = {
'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
}
BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android')
priority = qualities(BASE_CLIENTS[::-1])
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
ytcfg.setdefault('PLAYER_PARAMS', None)
ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
_, base_client, variant = _split_innertube_client(client)
ytcfg['priority'] = 10 * priority(base_client)
if not variant:
INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
embedscreen['priority'] -= 3
elif variant == 'embedded':
if variant == 'embedded':
ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
ytcfg['priority'] -= 2
else:
elif variant:
ytcfg['priority'] -= 3
@ -566,9 +608,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
or req_api_hostname or self._get_innertube_host(default_client or 'web'))
def _extract_api_key(self, ytcfg=None, default_client='web'):
return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
def _extract_context(self, ytcfg=None, default_client='web'):
context = get_first(
(ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
@ -614,13 +653,15 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
real_headers.update({'content-type': 'application/json'})
if headers:
real_headers.update(headers)
api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
or api_key or self._extract_api_key(default_client=default_client))
return self._download_json(
f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
video_id=video_id, fatal=fatal, note=note, errnote=errnote,
data=json.dumps(data).encode('utf8'), headers=real_headers,
query={'key': api_key, 'prettyPrint': 'false'})
query=filter_dict({
'key': self._configuration_arg(
'innertube_key', [api_key], ie_key=YoutubeIE.ie_key(), casesense=True)[0],
'prettyPrint': 'false',
}, cndn=lambda _, v: v))
def extract_yt_initial_data(self, item_id, webpage, fatal=True):
return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
@ -972,7 +1013,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
ep=ep, fatal=True, headers=headers,
video_id=item_id, query=query, note=note,
context=self._extract_context(ytcfg, default_client),
api_key=self._extract_api_key(ytcfg, default_client),
api_hostname=api_hostname, default_client=default_client)
except ExtractorError as e:
if not isinstance(e.cause, network_exceptions):
@ -1294,6 +1334,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
}
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_POTOKEN_EXPERIMENTS = ('51217476', '51217102')
_BROKEN_CLIENTS = {
short_client_name(client): client
for client in ('android', 'android_creator', 'android_music')
}
_DEFAULT_CLIENTS = ('ios', 'web_creator')
_GEO_BYPASS = False
@ -3128,11 +3174,42 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.write_debug(f'Decrypted nsig {s} => {ret}')
return ret
def _extract_n_function_name(self, jscode):
def _extract_n_function_name(self, jscode, player_url=None):
# Examples (with placeholders nfunc, narray, idx):
# * .get("n"))&&(b=nfunc(b)
# * .get("n"))&&(b=narray[idx](b)
# * b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c)
# * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("")
# * a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
funcname, idx = self._search_regex(
r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
if not idx:
r'''(?x)
(?:
\.get\("n"\)\)&&\(b=|
(?:
b=String\.fromCharCode\(110\)|
(?P<str_idx>[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\]
)
(?:
,[a-zA-Z0-9_$]+\(a\))?,c=a\.
(?:
get\(b\)|
[a-zA-Z0-9_$]+\[b\]\|\|null
)\)&&\(c=|
\b(?P<var>[a-zA-Z0-9_$]+)=
)(?P<nfunc>[a-zA-Z0-9_$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z]\)
(?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''',
jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None))
if not funcname:
self.report_warning(join_nonempty(
'Falling back to generic n function search',
player_url and f' player = {player_url}', delim='\n'))
return self._search_regex(
r'''(?xs)
;\s*(?P<name>[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\)
\s*\{(?:(?!};).)+?["']enhanced_except_''',
jscode, 'Initial JS player n function name', group='name')
elif not idx:
return funcname
return json.loads(js_to_json(self._search_regex(
@ -3141,26 +3218,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_n_function_code(self, video_id, player_url):
player_id = self._extract_player_info(player_url)
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2024.07.09')
jscode = func_code or self._load_player(video_id, player_url)
jsi = JSInterpreter(jscode)
if func_code:
return jsi, player_id, func_code
func_name = self._extract_n_function_name(jscode)
func_name = self._extract_n_function_name(jscode, player_url=player_url)
# For redundancy
func_code = self._search_regex(
rf'''(?xs){func_name}\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
# NB: The end of the regex is intentionally kept strict
{{(?P<code>.+?}}\s*return\ [\w$]+.join\(""\))}};''',
jscode, 'nsig function', group=('var', 'code'), default=None)
if func_code:
func_code = ([func_code[0]], func_code[1])
else:
self.write_debug('Extracting nsig function with jsinterp')
func_code = jsi.extract_function_code(func_name)
func_code = jsi.extract_function_code(func_name)
self.cache.store('youtube-nsig', player_id, func_code)
return jsi, player_id, func_code
@ -3662,9 +3729,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'videoId': video_id,
}
pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
if pp_arg:
yt_query['params'] = pp_arg
default_pp = traverse_obj(
INNERTUBE_CLIENTS, (_split_innertube_client(client)[0], 'PLAYER_PARAMS', {str}))
if player_params := self._configuration_arg('player_params', [default_pp], casesense=True)[0]:
yt_query['params'] = player_params
yt_query.update(self._generate_player_context(sts))
return self._extract_response(
@ -3676,30 +3744,40 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _get_requested_clients(self, url, smuggled_data):
requested_clients = []
android_clients = []
default = ['ios', 'web']
broken_clients = []
excluded_clients = []
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
for client in self._configuration_arg('player_client'):
if client == 'default':
requested_clients.extend(default)
requested_clients.extend(self._DEFAULT_CLIENTS)
elif client == 'all':
requested_clients.extend(allowed_clients)
elif client.startswith('-'):
excluded_clients.append(client[1:])
elif client not in allowed_clients:
self.report_warning(f'Skipping unsupported client {client}')
elif client.startswith('android'):
android_clients.append(client)
self.report_warning(f'Skipping unsupported client "{client}"')
elif client in self._BROKEN_CLIENTS.values():
broken_clients.append(client)
else:
requested_clients.append(client)
# Force deprioritization of broken Android clients for format de-duplication
requested_clients.extend(android_clients)
# Force deprioritization of _BROKEN_CLIENTS for format de-duplication
requested_clients.extend(broken_clients)
if not requested_clients:
requested_clients = default
requested_clients.extend(self._DEFAULT_CLIENTS)
for excluded_client in excluded_clients:
if excluded_client in requested_clients:
requested_clients.remove(excluded_client)
if not requested_clients:
raise ExtractorError('No player clients have been requested', expected=True)
if smuggled_data.get('is_music_url') or self.is_music_url(url):
requested_clients.extend(
f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
for requested_client in requested_clients:
_, base_client, variant = _split_innertube_client(requested_client)
music_client = f'{base_client}_music'
if variant != 'music' and music_client in INNERTUBE_CLIENTS:
requested_clients.append(music_client)
return orderedSet(requested_clients)
@ -3710,8 +3788,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return pr_id
def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
initial_pr = None
initial_pr = ignore_initial_response = None
if webpage:
if 'web' in clients:
experiments = traverse_obj(master_ytcfg, (
'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {lambda x: x.split(',')}, ...))
if all(x in experiments for x in self._POTOKEN_EXPERIMENTS):
self.report_warning(
'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response')
ignore_initial_response = True
initial_pr = self._search_json(
self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
@ -3741,8 +3826,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
skipped_clients = {}
while clients:
client, base_client, variant = _split_innertube_client(clients.pop())
player_ytcfg = master_ytcfg if client == 'web' else {}
if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
player_ytcfg = {}
if client == 'web':
player_ytcfg = self._get_default_ytcfg() if ignore_initial_response else master_ytcfg
elif 'configs' not in self._configuration_arg('player_skip'):
player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
@ -3755,11 +3842,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
player_url = self._download_player_url(video_id)
tried_iframe_fallback = True
try:
pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
except ExtractorError as e:
self.report_warning(e)
pr = initial_pr if client == 'web' and not ignore_initial_response else None
for retry in self.RetryManager(fatal=False):
try:
pr = pr or self._extract_player_response(
client, video_id, player_ytcfg or master_ytcfg, player_ytcfg,
player_url if require_js_player else None, initial_pr, smuggled_data)
except ExtractorError as e:
self.report_warning(e)
break
experiments = traverse_obj(pr, (
'responseContext', 'serviceTrackingParams', lambda _, v: v['service'] == 'GFEEDBACK',
'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ...))
if all(x in experiments for x in self._POTOKEN_EXPERIMENTS):
pr = None
retry.error = ExtractorError('API returned broken formats (poToken experiment detected)', expected=True)
if not pr:
continue
if pr_id := self._invalid_player_response(pr, video_id):
@ -3773,14 +3871,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f[STREAMING_DATA_CLIENT_NAME] = name
prs.append(pr)
# creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
append_client(f'{base_client}_creator')
elif self._is_agegated(pr):
if variant == 'tv_embedded':
append_client(f'{base_client}_embedded')
elif not variant:
append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
# tv_embedded can work around age-gate and age-verification IF the video is embeddable
if self._is_agegated(pr) and variant != 'tv_embedded':
append_client(f'tv_embedded.{base_client}')
# Unauthenticated users will only get tv_embedded client formats if age-gated
if self._is_agegated(pr) and not self.is_authenticated:
self.to_screen(
f'{video_id}: This video is age-restricted; some formats may be missing '
f'without authentication. {self._login_hint()}', only_once=True)
# EU countries require age-verification for accounts to access age-restricted videos
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
# If embedding is disabled for the video, _is_unplayable() will be truthy for tv_embedded
embedding_is_disabled = variant == 'tv_embedded' and self._is_unplayable(pr)
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
self.to_screen(
f'{video_id}: This video is age-restricted and YouTube is requiring '
'account age-verification; some formats may be missing', only_once=True)
# web_creator and mediaconnect can work around the age-verification requirement
# _producer, _testsuite, & _vr variants can also work around age-verification
append_client('web_creator', 'mediaconnect')
if skipped_clients:
self.report_warning(
@ -3916,13 +4027,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
# Android client formats are broken due to integrity check enforcement
# _BROKEN_CLIENTS return videoplayback URLs that expire after 30 seconds
# Ref: https://github.com/yt-dlp/yt-dlp/issues/9554
is_broken = client_name and client_name.startswith(short_client_name('android'))
is_broken = client_name in self._BROKEN_CLIENTS
if is_broken:
self.report_warning(
f'{video_id}: Android client formats are broken and may yield HTTP Error 403. '
'They will be deprioritized', only_once=True)
f'{video_id}: {self._BROKEN_CLIENTS[client_name]} client formats are broken '
'and may yield HTTP Error 403. They will be deprioritized', only_once=True)
name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
fps = int_or_none(fmt.get('fps')) or 0

18
yt_dlp/extractor/zaiko.py
View file

@ -66,7 +66,9 @@ class ZaikoIE(ZaikoBaseIE):
stream_meta['stream-access']['video_source'], video_id,
'Downloading player page', headers={'referer': 'https://zaiko.io/'})
player_meta = self._parse_vue_element_attr('player', player_page, video_id)
status = traverse_obj(player_meta, ('initial_event_info', 'status', {str}))
initial_event_info = traverse_obj(player_meta, ('initial_event_info', {dict})) or {}
status = traverse_obj(initial_event_info, ('status', {str}))
live_status, msg, expected = {
'vod': ('was_live', 'No VOD stream URL was found', False),
'archiving': ('post_live', 'Event VOD is still being processed', True),
@ -80,14 +82,20 @@ class ZaikoIE(ZaikoBaseIE):
'cancelled': ('not_live', 'Event has been cancelled', True),
}.get(status) or ('not_live', f'Unknown event status "{status}"', False)
stream_url = traverse_obj(player_meta, ('initial_event_info', 'endpoint', {url_or_none}))
if traverse_obj(initial_event_info, ('is_jwt_protected', {bool})):
stream_url = self._download_json(
initial_event_info['jwt_token_url'], video_id, 'Downloading JWT-protected stream URL',
'Failed to download JWT-protected stream URL')['playback_url']
else:
stream_url = traverse_obj(initial_event_info, ('endpoint', {url_or_none}))
formats = self._extract_m3u8_formats(
stream_url, video_id, live=True, fatal=False) if stream_url else []
if not formats:
self.raise_no_formats(msg, expected=expected)
thumbnail_urls = [
traverse_obj(player_meta, ('initial_event_info', 'poster_url')),
traverse_obj(initial_event_info, ('poster_url', {url_or_none})),
self._og_search_thumbnail(self._download_webpage(
f'https://zaiko.io/event/{video_id}', video_id, 'Downloading event page', fatal=False) or ''),
]
@ -103,9 +111,7 @@ class ZaikoIE(ZaikoBaseIE):
'release_timestamp': ('stream', 'start', 'timestamp', {int_or_none}),
'categories': ('event', 'genres', ..., {lambda x: x or None}),
}),
**traverse_obj(player_meta, ('initial_event_info', {
'alt_title': ('title', {str}),
})),
'alt_title': traverse_obj(initial_event_info, ('title', {str})),
'thumbnails': [{'url': url, 'id': url_basename(url)} for url in thumbnail_urls if url_or_none(url)],
}

24
yt_dlp/jsinterp.py
View file

@ -636,6 +636,8 @@ class JSInterpreter:
raise self.Exception(f'{member} {msg}', expr)
def eval_method():
nonlocal member
if (variable, member) == ('console', 'debug'):
if Debugger.ENABLED:
Debugger.write(self.interpret_expression(f'[{arg_str}]', local_vars, allow_recursion))
@ -644,6 +646,7 @@ class JSInterpreter:
types = {
'String': str,
'Math': float,
'Array': list,
}
obj = local_vars.get(variable, types.get(variable, NO_DEFAULT))
if obj is NO_DEFAULT:
@ -667,6 +670,21 @@ class JSInterpreter:
self.interpret_expression(v, local_vars, allow_recursion)
for v in self._separate(arg_str)]
# Fixup prototype call
if isinstance(obj, type) and member.startswith('prototype.'):
new_member, _, func_prototype = member.partition('.')[2].partition('.')
assertion(argvals, 'takes one or more arguments')
assertion(isinstance(argvals[0], obj), f'needs binding to type {obj}')
if func_prototype == 'call':
obj, *argvals = argvals
elif func_prototype == 'apply':
assertion(len(argvals) == 2, 'takes two arguments')
obj, argvals = argvals
assertion(isinstance(argvals, list), 'second argument needs to be a list')
else:
raise self.Exception(f'Unsupported Function method {func_prototype}', expr)
member = new_member
if obj is str:
if member == 'fromCharCode':
assertion(argvals, 'takes one or more arguments')
@ -691,9 +709,9 @@ class JSInterpreter:
obj.reverse()
return obj
elif member == 'slice':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(len(argvals) == 1, 'takes exactly one argument')
return obj[argvals[0]:]
assertion(isinstance(obj, (list, str)), 'must be applied on a list or string')
assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments')
return obj[slice(*argvals, None)]
elif member == 'splice':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(argvals, 'takes one or more arguments')

30
yt_dlp/networking/_curlcffi.py
View file

@ -2,6 +2,7 @@ from __future__ import annotations
import io
import math
import re
import urllib.parse
from ._helper import InstanceStoreMixin, select_proxy
@ -27,11 +28,12 @@ from ..utils import int_or_none
if curl_cffi is None:
raise ImportError('curl_cffi is not installed')
curl_cffi_version = tuple(int_or_none(x, default=0) for x in curl_cffi.__version__.split('.'))
if curl_cffi_version != (0, 5, 10):
curl_cffi_version = tuple(map(int, re.split(r'[^\d]+', curl_cffi.__version__)[:3]))
if curl_cffi_version != (0, 5, 10) and not ((0, 7, 0) <= curl_cffi_version < (0, 8, 0)):
curl_cffi._yt_dlp__version = f'{curl_cffi.__version__} (unsupported)'
raise ImportError('Only curl_cffi 0.5.10 is supported')
raise ImportError('Only curl_cffi versions 0.5.10, 0.7.X are supported')
import curl_cffi.requests
from curl_cffi.const import CurlECode, CurlOpt
@ -110,6 +112,13 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
_SUPPORTED_FEATURES = (Features.NO_PROXY, Features.ALL_PROXY)
_SUPPORTED_PROXY_SCHEMES = ('http', 'https', 'socks4', 'socks4a', 'socks5', 'socks5h')
_SUPPORTED_IMPERSONATE_TARGET_MAP = {
**({
ImpersonateTarget('chrome', '124', 'macos', '14'): curl_cffi.requests.BrowserType.chrome124,
ImpersonateTarget('chrome', '123', 'macos', '14'): curl_cffi.requests.BrowserType.chrome123,
ImpersonateTarget('chrome', '120', 'macos', '14'): curl_cffi.requests.BrowserType.chrome120,
ImpersonateTarget('chrome', '119', 'macos', '14'): curl_cffi.requests.BrowserType.chrome119,
ImpersonateTarget('chrome', '116', 'windows', '10'): curl_cffi.requests.BrowserType.chrome116,
} if curl_cffi_version >= (0, 7, 0) else {}),
ImpersonateTarget('chrome', '110', 'windows', '10'): curl_cffi.requests.BrowserType.chrome110,
ImpersonateTarget('chrome', '107', 'windows', '10'): curl_cffi.requests.BrowserType.chrome107,
ImpersonateTarget('chrome', '104', 'windows', '10'): curl_cffi.requests.BrowserType.chrome104,
@ -118,9 +127,15 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
ImpersonateTarget('chrome', '99', 'windows', '10'): curl_cffi.requests.BrowserType.chrome99,
ImpersonateTarget('edge', '101', 'windows', '10'): curl_cffi.requests.BrowserType.edge101,
ImpersonateTarget('edge', '99', 'windows', '10'): curl_cffi.requests.BrowserType.edge99,
**({
ImpersonateTarget('safari', '17.0', 'macos', '14'): curl_cffi.requests.BrowserType.safari17_0,
} if curl_cffi_version >= (0, 7, 0) else {}),
ImpersonateTarget('safari', '15.5', 'macos', '12'): curl_cffi.requests.BrowserType.safari15_5,
ImpersonateTarget('safari', '15.3', 'macos', '11'): curl_cffi.requests.BrowserType.safari15_3,
ImpersonateTarget('chrome', '99', 'android', '12'): curl_cffi.requests.BrowserType.chrome99_android,
**({
ImpersonateTarget('safari', '17.2', 'ios', '17.2'): curl_cffi.requests.BrowserType.safari17_2_ios,
} if curl_cffi_version >= (0, 7, 0) else {}),
}
def _create_instance(self, cookiejar=None):
@ -131,6 +146,9 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
extensions.pop('impersonate', None)
extensions.pop('cookiejar', None)
extensions.pop('timeout', None)
# CurlCFFIRH ignores legacy ssl options currently.
# Impersonation generally uses a looser SSL configuration than urllib/requests.
extensions.pop('legacy_ssl', None)
def send(self, request: Request) -> Response:
target = self._get_request_target(request)
@ -187,7 +205,7 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
timeout = self._calculate_timeout(request)
# set CURLOPT_LOW_SPEED_LIMIT and CURLOPT_LOW_SPEED_TIME to act as a read timeout. [1]
# curl_cffi does not currently do this. [2]
# This is required only for 0.5.10 [2]
# Note: CURLOPT_LOW_SPEED_TIME is in seconds, so we need to round up to the nearest second. [3]
# [1] https://unix.stackexchange.com/a/305311
# [2] https://github.com/yifeikong/curl_cffi/issues/156
@ -203,7 +221,7 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
data=request.data,
verify=self.verify,
max_redirects=5,
timeout=timeout,
timeout=(timeout, timeout),
impersonate=self._SUPPORTED_IMPERSONATE_TARGET_MAP.get(
self._get_request_target(request)),
interface=self.source_address,
@ -222,7 +240,7 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
elif (
e.code == CurlECode.PROXY
or (e.code == CurlECode.RECV_ERROR and 'Received HTTP code 407 from proxy after CONNECT' in str(e))
or (e.code == CurlECode.RECV_ERROR and 'CONNECT' in str(e))
):
raise ProxyError(cause=e) from e
else:

10
yt_dlp/networking/_requests.py
View file

@ -295,11 +295,12 @@ class RequestsRH(RequestHandler, InstanceStoreMixin):
super()._check_extensions(extensions)
extensions.pop('cookiejar', None)
extensions.pop('timeout', None)
extensions.pop('legacy_ssl', None)
def _create_instance(self, cookiejar):
def _create_instance(self, cookiejar, legacy_ssl_support=None):
session = RequestsSession()
http_adapter = RequestsHTTPAdapter(
ssl_context=self._make_sslcontext(),
ssl_context=self._make_sslcontext(legacy_ssl_support=legacy_ssl_support),
source_address=self.source_address,
max_retries=urllib3.util.retry.Retry(False),
)
@ -318,7 +319,10 @@ class RequestsRH(RequestHandler, InstanceStoreMixin):
max_redirects_exceeded = False
session = self._get_instance(cookiejar=self._get_cookiejar(request))
session = self._get_instance(
cookiejar=self._get_cookiejar(request),
legacy_ssl_support=request.extensions.get('legacy_ssl'),
)
try:
requests_res = session.request(

6
yt_dlp/networking/_urllib.py
View file

@ -348,14 +348,15 @@ class UrllibRH(RequestHandler, InstanceStoreMixin):
super()._check_extensions(extensions)
extensions.pop('cookiejar', None)
extensions.pop('timeout', None)
extensions.pop('legacy_ssl', None)
def _create_instance(self, proxies, cookiejar):
def _create_instance(self, proxies, cookiejar, legacy_ssl_support=None):
opener = urllib.request.OpenerDirector()
handlers = [
ProxyHandler(proxies),
HTTPHandler(
debuglevel=int(bool(self.verbose)),
context=self._make_sslcontext(),
context=self._make_sslcontext(legacy_ssl_support=legacy_ssl_support),
source_address=self.source_address),
HTTPCookieProcessor(cookiejar),
DataHandler(),
@ -391,6 +392,7 @@ class UrllibRH(RequestHandler, InstanceStoreMixin):
opener = self._get_instance(
proxies=self._get_proxies(request),
cookiejar=self._get_cookiejar(request),
legacy_ssl_support=request.extensions.get('legacy_ssl'),
)
try:
res = opener.open(urllib_req, timeout=self._calculate_timeout(request))

4
yt_dlp/networking/_websockets.py
View file

@ -118,6 +118,7 @@ class WebsocketsRH(WebSocketRequestHandler):
super()._check_extensions(extensions)
extensions.pop('timeout', None)
extensions.pop('cookiejar', None)
extensions.pop('legacy_ssl', None)
def close(self):
# Remove the logging handler that contains a reference to our logger
@ -154,13 +155,14 @@ class WebsocketsRH(WebSocketRequestHandler):
address=(wsuri.host, wsuri.port),
**create_conn_kwargs,
)
ssl_ctx = self._make_sslcontext(legacy_ssl_support=request.extensions.get('legacy_ssl'))
conn = websockets.sync.client.connect(
sock=sock,
uri=request.url,
additional_headers=headers,
open_timeout=timeout,
user_agent_header=None,
ssl_context=self._make_sslcontext() if wsuri.secure else None,
ssl_context=ssl_ctx if wsuri.secure else None,
close_timeout=0, # not ideal, but prevents yt-dlp hanging
)
return WebsocketsResponseAdapter(conn, url=request.url)

9
yt_dlp/networking/common.py
View file

@ -205,6 +205,7 @@ class RequestHandler(abc.ABC):
The following extensions are defined for RequestHandler:
- `cookiejar`: Cookiejar to use for this request.
- `timeout`: socket timeout to use for this request.
- `legacy_ssl`: Enable legacy SSL options for this request. See legacy_ssl_support.
To enable these, add extensions.pop('<extension>', None) to _check_extensions
Apart from the url protocol, proxies dict may contain the following keys:
@ -247,10 +248,10 @@ class RequestHandler(abc.ABC):
self.legacy_ssl_support = legacy_ssl_support
super().__init__()
def _make_sslcontext(self):
def _make_sslcontext(self, legacy_ssl_support=None):
return make_ssl_context(
verify=self.verify,
legacy_support=self.legacy_ssl_support,
legacy_support=legacy_ssl_support if legacy_ssl_support is not None else self.legacy_ssl_support,
use_certifi=not self.prefer_system_certs,
**self._client_cert,
)
@ -262,7 +263,8 @@ class RequestHandler(abc.ABC):
return float(request.extensions.get('timeout') or self.timeout)
def _get_cookiejar(self, request):
return request.extensions.get('cookiejar') or self.cookiejar
cookiejar = request.extensions.get('cookiejar')
return self.cookiejar if cookiejar is None else cookiejar
def _get_proxies(self, request):
return (request.proxies or self.proxies).copy()
@ -314,6 +316,7 @@ class RequestHandler(abc.ABC):
"""Check extensions for unsupported extensions. Subclasses should extend this."""
assert isinstance(extensions.get('cookiejar'), (YoutubeDLCookieJar, NoneType))
assert isinstance(extensions.get('timeout'), (float, int, NoneType))
assert isinstance(extensions.get('legacy_ssl'), (bool, NoneType))
def _validate(self, request):
self._check_url_scheme(request)

5
yt_dlp/options.py
View file

@ -462,6 +462,7 @@ def create_parser():
'the STREAM (stdout or stderr) to apply the setting to. '
'Can be one of "always", "auto" (default), "never", or '
'"no_color" (use non color terminal sequences). '
'Use "auto-tty" or "no_color-tty" to decide based on terminal support only. '
'Can be used multiple times'))
general.add_option(
'--compat-options',
@ -476,8 +477,8 @@ def create_parser():
'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext',
}, 'aliases': {
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx'],
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
'2021': ['2022', 'no-certifi', 'filename-sanitization'],
'2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
'2023': [],

2
yt_dlp/postprocessor/embedthumbnail.py
View file

@ -134,7 +134,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
meta = MP4(filename)
# NOTE: the 'covr' atom is a non-standard MPEG-4 atom,
# Apple iTunes 'M4A' files include the 'moov.udta.meta.ilst' atom.
meta.tags['covr'] = [MP4Cover(data=thumb_data, imageformat=f)]
meta.tags['covr'] = [MP4Cover(data=thumb_data, imageformat=f[type_])]
meta.save()
temp_filename = filename
except Exception as err:

6
yt_dlp/update.py
View file

@ -310,6 +310,7 @@ class Updater:
if isinstance(error, HTTPError) and error.status == 404:
continue
self._report_network_error(f'fetch update spec: {error}')
return None
self._report_error(
f'The requested tag {self.requested_tag} does not exist for {self.requested_repo}', True)
@ -557,9 +558,10 @@ class Updater:
def _report_network_error(self, action, delim=';', tag=None):
if not tag:
tag = self.requested_tag
path = tag if tag == 'latest' else f'tag/{tag}'
self._report_error(
f'Unable to {action}{delim} visit https://github.com/{self.requested_repo}/releases/'
+ tag if tag == 'latest' else f'tag/{tag}', True)
f'Unable to {action}{delim} visit '
f'https://github.com/{self.requested_repo}/releases/{path}', True)
# XXX: Everything below this line in this class is deprecated / for compat only
@property

46
yt_dlp/utils/_utils.py
View file

@ -1217,7 +1217,7 @@ def unified_timestamp(date_str, day_first=True):
return None
date_str = re.sub(r'\s+', ' ', re.sub(
r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?)(day)?', '', date_str))
r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?|sun)(day)?', '', date_str))
pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
timezone, date_str = extract_timezone(date_str)
@ -2984,6 +2984,7 @@ def parse_codecs(codecs_str):
str.strip, codecs_str.strip().strip(',').split(','))))
vcodec, acodec, scodec, hdr = None, None, None, None
for full_codec in split_codecs:
full_codec = re.sub(r'^([^.]+)', lambda m: m.group(1).lower(), full_codec)
parts = re.sub(r'0+(?=\d)', '', full_codec).split('.')
if parts[0] in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2',
'h263', 'h264', 'mp4v', 'hvc1', 'av1', 'theora', 'dvh1', 'dvhe'):
@ -5026,7 +5027,7 @@ MEDIA_EXTENSIONS = Namespace(
common_video=('avi', 'flv', 'mkv', 'mov', 'mp4', 'webm'),
video=('3g2', '3gp', 'f4v', 'mk3d', 'divx', 'mpg', 'ogv', 'm4v', 'wmv'),
common_audio=('aiff', 'alac', 'flac', 'm4a', 'mka', 'mp3', 'ogg', 'opus', 'wav'),
audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4p', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma', 'weba'),
audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma', 'weba'),
thumbnails=('jpg', 'png', 'webp'),
storyboards=('mhtml', ),
subtitles=('srt', 'vtt', 'ass', 'lrc'),
@ -5059,36 +5060,64 @@ class _UnsafeExtensionError(Exception):
# video
*MEDIA_EXTENSIONS.video,
'avif',
'asx',
'ismv',
'm2t',
'm2ts',
'm2v',
'm4s',
'mng',
'mp2v',
'mp4v',
'mpe',
'mpeg',
'mpeg1',
'mpeg2',
'mpeg4',
'mxf',
'ogm',
'qt',
'rm',
'swf',
'ts',
'vob',
'vp9',
'wvm',
# audio
*MEDIA_EXTENSIONS.audio,
'3ga',
'ac3',
'adts',
'aif',
'au',
'dts',
'isma',
'it',
'mid',
'mod',
'mpga',
'mp1',
'mp2',
'mp4a',
'mpa',
'ra',
'shn',
'xm',
# image
*MEDIA_EXTENSIONS.thumbnails,
'avif',
'bmp',
'gif',
'heic',
'ico',
'image',
'jng',
'jpeg',
'jxl',
'svg',
'tif',
'tiff',
'wbmp',
# subtitle
@ -5096,11 +5125,16 @@ class _UnsafeExtensionError(Exception):
'dfxp',
'fs',
'ismt',
'json3',
'sami',
'scc',
'srv1',
'srv2',
'srv3',
'ssa',
'tt',
'ttml',
'xml',
# others
*MEDIA_EXTENSIONS.manifests,
@ -5111,7 +5145,6 @@ class _UnsafeExtensionError(Exception):
'sbv',
'url',
'webloc',
'xml',
])
def __init__(self, extension, /):
@ -5120,6 +5153,9 @@ class _UnsafeExtensionError(Exception):
@classmethod
def sanitize_extension(cls, extension, /, *, prepend=False):
if extension is None:
return None
if '/' in extension or '\\' in extension:
raise cls(extension)

6
yt_dlp/version.py
View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.07.01'
__version__ = '2024.08.06'
RELEASE_GIT_HEAD = '5ce582448ececb8d9c30c8c31f58330090ced03a'
RELEASE_GIT_HEAD = '4d9231208332d4c32364b8cd814bff8b20232cae'
VARIANT = None
@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.07.01'
_pkg_version = '2024.08.06'