xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-30 17:14:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

merge 'master'

Browse Source
This commit is contained in:
Mozi 2025-01-29 05:49:12 +00:00
commit 85f96a8688
49 changed files with 1673 additions and 1507 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -92,6 +92,7 @@ updates_key.pem
*.class
*.isorted
*.stackdump
uv.lock
# Generated
AUTHORS

21
CONTRIBUTORS
View File

@ -715,3 +715,24 @@ Crypto90
MutantPiggieGolem1
Sanceilaks
Strkmn
0x9fff00
4ft35t
7x11x13
b5i
cotko
d3d9
Dioarya
finch71
hexahigh
InvalidUsernameException
jixunmoe
knackku
krandor
kvk-2015
lonble
msm595
n10dollar
NecroRomnt
pjrobertson
subsense
test20140

59
Changelog.md
View File

@ -4,6 +4,65 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2025.01.26
#### Core changes
- [Fix float comparison values in format filters](https://github.com/yt-dlp/yt-dlp/commit/f7d071e8aa3bf67ed7e0f881e749ca9ab50b3f8f) ([#11880](https://github.com/yt-dlp/yt-dlp/issues/11880)) by [bashonly](https://github.com/bashonly), [Dioarya](https://github.com/Dioarya)
- **utils**: `sanitize_path`: [Fix some incorrect behavior](https://github.com/yt-dlp/yt-dlp/commit/fc12e724a3b4988cfc467d2981887dde48c26b69) ([#11923](https://github.com/yt-dlp/yt-dlp/issues/11923)) by [Grub4K](https://github.com/Grub4K)
#### Extractor changes
- **1tv**: [Support sport1tv.ru domain](https://github.com/yt-dlp/yt-dlp/commit/61ae5dc34ac775d6c122575e21ef2153b1273a2b) ([#11889](https://github.com/yt-dlp/yt-dlp/issues/11889)) by [kvk-2015](https://github.com/kvk-2015)
- **abematv**: [Support season extraction](https://github.com/yt-dlp/yt-dlp/commit/c709cc41cbc16edc846e0a431cfa8508396d4cb6) ([#11771](https://github.com/yt-dlp/yt-dlp/issues/11771)) by [middlingphys](https://github.com/middlingphys)
- **bilibili**
- [Support space `/lists/` URLs](https://github.com/yt-dlp/yt-dlp/commit/465167910407449354eb48e9861efd0819f53eb5) ([#11964](https://github.com/yt-dlp/yt-dlp/issues/11964)) by [c-basalt](https://github.com/c-basalt)
- [Support space video list extraction without login](https://github.com/yt-dlp/yt-dlp/commit/78912ed9c81f109169b828c397294a6cf8eacf41) ([#12089](https://github.com/yt-dlp/yt-dlp/issues/12089)) by [grqz](https://github.com/grqz)
- **bilibilidynamic**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/9676b05715b61c8c5dd5598871e60d8807fb1a86) ([#11838](https://github.com/yt-dlp/yt-dlp/issues/11838)) by [finch71](https://github.com/finch71), [grqz](https://github.com/grqz)
- **bluesky**: [Prefer source format](https://github.com/yt-dlp/yt-dlp/commit/ccda63934df7de2823f0834218c4254c7c4d2e4c) ([#12154](https://github.com/yt-dlp/yt-dlp/issues/12154)) by [0x9fff00](https://github.com/0x9fff00)
- **crunchyroll**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/ff44ed53061e065804da6275d182d7928cc03a5e) ([#12195](https://github.com/yt-dlp/yt-dlp/issues/12195)) by [seproDev](https://github.com/seproDev)
- **dropout**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/164368610456e2d96b279f8b120dea08f7b1d74f) ([#12102](https://github.com/yt-dlp/yt-dlp/issues/12102)) by [bashonly](https://github.com/bashonly)
- **eggs**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/20c765d02385a105c8ef13b6f7a737491d29c19a) ([#11904](https://github.com/yt-dlp/yt-dlp/issues/11904)) by [seproDev](https://github.com/seproDev), [subsense](https://github.com/subsense)
- **funimation**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/cdcf1e86726b8fa44f7e7126bbf1c18e1798d25c) ([#12167](https://github.com/yt-dlp/yt-dlp/issues/12167)) by [doe1080](https://github.com/doe1080)
- **goodgame**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e7cc02b14d8d323f805d14325a9c95593a170d28) ([#12173](https://github.com/yt-dlp/yt-dlp/issues/12173)) by [NecroRomnt](https://github.com/NecroRomnt)
- **lbry**: [Support signed URLs](https://github.com/yt-dlp/yt-dlp/commit/de30f652ffb7623500215f5906844f2ae0d92c7b) ([#12138](https://github.com/yt-dlp/yt-dlp/issues/12138)) by [seproDev](https://github.com/seproDev)
- **naver**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/b3007c44cdac38187fc6600de76959a7079a44d1) ([#12037](https://github.com/yt-dlp/yt-dlp/issues/12037)) by [kclauhk](https://github.com/kclauhk)
- **nest**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/1ef3ee7500c4ab8c26f7fdc5b0ad1da4d16eec8e) ([#11747](https://github.com/yt-dlp/yt-dlp/issues/11747)) by [pabs3](https://github.com/pabs3), [seproDev](https://github.com/seproDev)
- **niconico**: series: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/bc88b904cd02314da41ce1b2fdf046d0680fe965) ([#11822](https://github.com/yt-dlp/yt-dlp/issues/11822)) by [test20140](https://github.com/test20140)
- **nrk**
- [Extract more formats](https://github.com/yt-dlp/yt-dlp/commit/89198bb23b4d03e0473ac408bfb50d67c2f71165) ([#12069](https://github.com/yt-dlp/yt-dlp/issues/12069)) by [hexahigh](https://github.com/hexahigh)
- [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/45732e2590a1bd0bc9608f5eb68c59341ca84f02) ([#12193](https://github.com/yt-dlp/yt-dlp/issues/12193)) by [hexahigh](https://github.com/hexahigh)
- **patreon**: [Extract attachment filename as `alt_title`](https://github.com/yt-dlp/yt-dlp/commit/e2e73b5c65593ec0a5e685663e6ec0f4aaffc1f1) ([#12000](https://github.com/yt-dlp/yt-dlp/issues/12000)) by [msm595](https://github.com/msm595)
- **pbs**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/13825ab77815ee6e1603abbecbb9f3795057b93c) ([#12024](https://github.com/yt-dlp/yt-dlp/issues/12024)) by [dirkf](https://github.com/dirkf), [krandor](https://github.com/krandor), [n10dollar](https://github.com/n10dollar)
- **piramidetv**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/af2c821d74049b519895288aca23cee81fc4b049) ([#10777](https://github.com/yt-dlp/yt-dlp/issues/10777)) by [HobbyistDev](https://github.com/HobbyistDev), [kclauhk](https://github.com/kclauhk), [seproDev](https://github.com/seproDev)
- **redgifs**: [Support `/ifr/` URLs](https://github.com/yt-dlp/yt-dlp/commit/4850ce91d163579fa615c3c0d44c9bd64682c22b) ([#11805](https://github.com/yt-dlp/yt-dlp/issues/11805)) by [invertico](https://github.com/invertico)
- **rtvslo.si**: show: [Extract more metadata](https://github.com/yt-dlp/yt-dlp/commit/3fc46086562857d5493cbcff687f76e4e4ed303f) ([#12136](https://github.com/yt-dlp/yt-dlp/issues/12136)) by [cotko](https://github.com/cotko)
- **senategov**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/68221ecc87c6a3f3515757bac2a0f9674a38e3f2) ([#9361](https://github.com/yt-dlp/yt-dlp/issues/9361)) by [Grabien](https://github.com/Grabien), [seproDev](https://github.com/seproDev)
- **soundcloud**
- [Extract more metadata](https://github.com/yt-dlp/yt-dlp/commit/6d304133ab32bcd1eb78ff1467f1a41dd9b66c33) ([#11945](https://github.com/yt-dlp/yt-dlp/issues/11945)) by [7x11x13](https://github.com/7x11x13)
- user: [Add `/comments` page support](https://github.com/yt-dlp/yt-dlp/commit/7bfb4f72e490310d2681c7f4815218a2ebbc73ee) ([#11999](https://github.com/yt-dlp/yt-dlp/issues/11999)) by [7x11x13](https://github.com/7x11x13)
- **subsplash**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/5d904b077d2f58ae44bdf208d2dcfcc3ff8347f5) ([#11054](https://github.com/yt-dlp/yt-dlp/issues/11054)) by [seproDev](https://github.com/seproDev), [subrat-lima](https://github.com/subrat-lima)
- **theatercomplextownppv**: [Support `live` URLs](https://github.com/yt-dlp/yt-dlp/commit/797d2472a299692e01ad1500e8c3b7bc1daa7fe4) ([#11720](https://github.com/yt-dlp/yt-dlp/issues/11720)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Fix thumbnail extraction](https://github.com/yt-dlp/yt-dlp/commit/9ff330948c92f6b2e1d9c928787362ab19cd6c62) ([#12142](https://github.com/yt-dlp/yt-dlp/issues/12142)) by [jixunmoe](https://github.com/jixunmoe)
- **vimp**: Playlist: [Add support for tags](https://github.com/yt-dlp/yt-dlp/commit/d4f5be1735c8feaeb3308666e0b878e9782f529d) ([#11688](https://github.com/yt-dlp/yt-dlp/issues/11688)) by [FestplattenSchnitzel](https://github.com/FestplattenSchnitzel)
- **weibo**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/a567f97b62ae9f6d6f5a9376c361512ab8dceda2) ([#12088](https://github.com/yt-dlp/yt-dlp/issues/12088)) by [4ft35t](https://github.com/4ft35t)
- **xhamster**: [Various improvements](https://github.com/yt-dlp/yt-dlp/commit/3b99a0f0e07f0120ab416f34a8f5ab75d4fdf1d1) ([#11738](https://github.com/yt-dlp/yt-dlp/issues/11738)) by [knackku](https://github.com/knackku)
- **xiaohongshu**: [Extract more formats](https://github.com/yt-dlp/yt-dlp/commit/f9f24ae376a9eaca777816479a4a29f6f0ce7681) ([#12147](https://github.com/yt-dlp/yt-dlp/issues/12147)) by [seproDev](https://github.com/seproDev)
- **youtube**
- [Download `tv` client Innertube config](https://github.com/yt-dlp/yt-dlp/commit/326fb1ffaf4e8349f1fe8ba2a81839652e044bff) ([#12168](https://github.com/yt-dlp/yt-dlp/issues/12168)) by [coletdjnz](https://github.com/coletdjnz)
- [Extract `media_type` for livestreams](https://github.com/yt-dlp/yt-dlp/commit/421bc72103d1faed473a451299cd17d6abb433bb) ([#11605](https://github.com/yt-dlp/yt-dlp/issues/11605)) by [nosoop](https://github.com/nosoop)
- [Restore convenience workarounds](https://github.com/yt-dlp/yt-dlp/commit/f0d4b8a5d6354b294bc9631cf15a7160b7bad5de) ([#12181](https://github.com/yt-dlp/yt-dlp/issues/12181)) by [bashonly](https://github.com/bashonly)
- [Update `ios` player client](https://github.com/yt-dlp/yt-dlp/commit/de82acf8769282ce321a86737ecc1d4bef0e82a7) ([#12155](https://github.com/yt-dlp/yt-dlp/issues/12155)) by [b5i](https://github.com/b5i)
- [Use different PO token for GVS and Player](https://github.com/yt-dlp/yt-dlp/commit/6b91d232e316efa406035915532eb126fbaeea38) ([#12090](https://github.com/yt-dlp/yt-dlp/issues/12090)) by [coletdjnz](https://github.com/coletdjnz)
- tab: [Improve shorts title extraction](https://github.com/yt-dlp/yt-dlp/commit/76ac023ff02f06e8c003d104f02a03deeddebdcd) ([#11997](https://github.com/yt-dlp/yt-dlp/issues/11997)) by [bashonly](https://github.com/bashonly), [d3d9](https://github.com/d3d9)
- **zdf**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bb69f5dab79fb32c4ec0d50e05f7fa26d05d54ba) ([#11041](https://github.com/yt-dlp/yt-dlp/issues/11041)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
#### Misc. changes
- **cleanup**: Miscellaneous: [3b45319](https://github.com/yt-dlp/yt-dlp/commit/3b4531934465580be22937fecbb6e1a3a9e2334f) by [bashonly](https://github.com/bashonly), [lonble](https://github.com/lonble), [pjrobertson](https://github.com/pjrobertson), [seproDev](https://github.com/seproDev)
### 2025.01.15
#### Extractor changes
- **youtube**: [Do not use `web_creator` as a default client](https://github.com/yt-dlp/yt-dlp/commit/c8541f8b13e743fcfa06667530d13fee8686e22a) ([#12087](https://github.com/yt-dlp/yt-dlp/issues/12087)) by [bashonly](https://github.com/bashonly)
### 2025.01.12
#### Core changes

13
README.md
View File

@ -1760,7 +1760,7 @@ # Replace all spaces and "_" in title and uploader with a `-`
# 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=tv,mweb;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=tv,mweb;formats=incomplete" --extractor-args "twitter:api=syndication"`
Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
@ -1769,7 +1769,7 @@ # EXTRACTOR ARGUMENTS
#### youtube
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.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` and `_creator` (e.g. `ios_creator`); and `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, or `web_creator,tv` is used when authenticating with cookies. The `_music` variants are added for `music.youtube.com` URLs. Some clients, such as `web` and `android`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, will only work with authentication. Not all clients support authentication via cookies. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web`
* `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 `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). 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)
@ -1781,7 +1781,7 @@ #### youtube
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
* `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage`
* `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID)
* `po_token`: Proof of Origin (PO) Token(s) to use for requesting video playback. Comma seperated list of PO Tokens in the format `CLIENT+PO_TOKEN`, e.g. `youtube:po_token=web+XXX,android+YYY`
* `po_token`: Proof of Origin (PO) Token(s) to use. Comma seperated list of PO Tokens in the format `CLIENT.CONTEXT+PO_TOKEN`, e.g. `youtube:po_token=web.gvs+XXX,web.player=XXX,web_safari.gvs+YYY`. Context can be either `gvs` (Google Video Server URLs) or `player` (Innertube player request)
#### youtubetab (YouTube playlists, channels, feeds, etc.)
* `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)
@ -1795,13 +1795,6 @@ #### generic
* `is_live`: Bypass live HLS detection and manually set `live_status` - a value of `false` will set `not_live`, any other value (or no value) will set `is_live`
* `impersonate`: Target(s) to try and impersonate with the initial webpage request; e.g. `generic:impersonate=safari,chrome-110`. Use `generic:impersonate` to impersonate any available target, and use `generic:impersonate=false` to disable impersonation (default)
#### funimation
* `language`: Audio languages to extract, e.g. `funimation:language=english,japanese`
* `version`: The video version to extract - `uncut` or `simulcast`
#### crunchyrollbeta (Crunchyroll)
* `hardsub`: One or more hardsub versions to extract (in order of preference), or `all` (default: `None` = no hardsubs will be extracted), e.g. `crunchyrollbeta:hardsub=en-US,de-DE`
#### vikichannel
* `video_types`: Types of videos to download - one or more of `episodes`, `movies`, `clips`, `trailers`

6
devscripts/changelog_override.json
View File

@ -239,5 +239,11 @@
"action": "add",
"when": "52c0ffe40ad6e8404d93296f575007b05b04c686",
"short": "[priority] **Login with OAuth is no longer supported for YouTube**\nDue to a change made by the site, yt-dlp is no longer able to support OAuth login for YouTube. [Read more](https://github.com/yt-dlp/yt-dlp/issues/11462#issuecomment-2471703090)"
},
{
"action": "change",
"when": "76ac023ff02f06e8c003d104f02a03deeddebdcd",
"short": "[ie/youtube:tab] Improve shorts title extraction (#11997)",
"authors": ["bashonly", "d3d9"]
}
]

16
supportedsites.md
View File

@ -171,6 +171,7 @@ # Supported sites
- **BilibiliCheese**
- **BilibiliCheeseSeason**
- **BilibiliCollectionList**
- **BiliBiliDynamic**
- **BilibiliFavoritesList**
- **BiliBiliPlayer**
- **BilibiliPlaylist**
@ -303,10 +304,6 @@ # Supported sites
- **CrowdBunker**
- **CrowdBunkerChannel**
- **Crtvg**
- **crunchyroll**: [*crunchyroll*](## "netrc machine")
- **crunchyroll:artist**: [*crunchyroll*](## "netrc machine")
- **crunchyroll:music**: [*crunchyroll*](## "netrc machine")
- **crunchyroll:playlist**: [*crunchyroll*](## "netrc machine")
- **CSpan**: C-SPAN
- **CSpanCongress**
- **CtsNews**: 華視新聞
@ -393,6 +390,8 @@ # Supported sites
- **Ebay**
- **egghead:course**: egghead.io course
- **egghead:lesson**: egghead.io lesson
- **eggs:artist**
- **eggs:single**
- **EinsUndEinsTV**: [*1und1tv*](## "netrc machine")
- **EinsUndEinsTVLive**: [*1und1tv*](## "netrc machine")
- **EinsUndEinsTVRecordings**: [*1und1tv*](## "netrc machine")
@ -477,9 +476,6 @@ # Supported sites
- **FrontendMastersCourse**: [*frontendmasters*](## "netrc machine")
- **FrontendMastersLesson**: [*frontendmasters*](## "netrc machine")
- **FujiTVFODPlus7**
- **Funimation**: [*funimation*](## "netrc machine")
- **funimation:page**: [*funimation*](## "netrc machine")
- **funimation:show**: [*funimation*](## "netrc machine")
- **Funk**
- **Funker530**
- **Fux**
@ -892,6 +888,8 @@ # Supported sites
- **nebula:video**: [*watchnebula*](## "netrc machine")
- **NekoHacker**
- **NerdCubedFeed**
- **Nest**
- **NestClip**
- **netease:album**: 网易云音乐 - 专辑
- **netease:djradio**: 网易云音乐 - 电台
- **netease:mv**: 网易云音乐 - MV
@ -1071,6 +1069,8 @@ # Supported sites
- **Pinkbike**
- **Pinterest**
- **PinterestCollection**
- **PiramideTV**
- **PiramideTVChannel**
- **pixiv:sketch**
- **pixiv:​sketch:user**
- **Pladform**
@ -1396,6 +1396,8 @@ # Supported sites
- **StretchInternet**
- **Stripchat**
- **stv:player**
- **Subsplash**
- **subsplash:playlist**
- **Substack**
- **SunPorno**
- **sverigesradio:episode**

35
test/test_YoutubeDL.py
View File

@ -486,11 +486,11 @@ def assert_syntax_error(format_spec):
def test_format_filtering(self):
formats = [
{'format_id': 'A', 'filesize': 500, 'width': 1000},
{'format_id': 'B', 'filesize': 1000, 'width': 500},
{'format_id': 'C', 'filesize': 1000, 'width': 400},
{'format_id': 'D', 'filesize': 2000, 'width': 600},
{'format_id': 'E', 'filesize': 3000},
{'format_id': 'A', 'filesize': 500, 'width': 1000, 'aspect_ratio': 1.0},
{'format_id': 'B', 'filesize': 1000, 'width': 500, 'aspect_ratio': 1.33},
{'format_id': 'C', 'filesize': 1000, 'width': 400, 'aspect_ratio': 1.5},
{'format_id': 'D', 'filesize': 2000, 'width': 600, 'aspect_ratio': 1.78},
{'format_id': 'E', 'filesize': 3000, 'aspect_ratio': 0.56},
{'format_id': 'F'},
{'format_id': 'G', 'filesize': 1000000},
]
@ -549,6 +549,31 @@ def test_format_filtering(self):
ydl.process_ie_result(info_dict)
self.assertEqual(ydl.downloaded_info_dicts, [])
ydl = YDL({'format': 'best[aspect_ratio=1]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'A')
ydl = YDL({'format': 'all[aspect_ratio > 1.00]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
ydl = YDL({'format': 'all[aspect_ratio < 1.00]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['E'])
ydl = YDL({'format': 'best[aspect_ratio=1.5]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'C')
ydl = YDL({'format': 'all[aspect_ratio!=1]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['E', 'D', 'C', 'B'])
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
def test_default_format_spec_without_ffmpeg(self):
ydl = YDL({})

37
test/test_utils.py
View File

@ -249,17 +249,36 @@ def _test_sanitize_path(self):
self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
self.assertEqual(sanitize_path('../abc'), '..\\abc')
self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
self.assertEqual(sanitize_path('\\abc'), '\\abc')
self.assertEqual(sanitize_path('C:abc'), 'C:abc')
self.assertEqual(sanitize_path('C:abc\\..\\'), 'C:..')
self.assertEqual(sanitize_path('C:\\abc:%(title)s.%(ext)s'), 'C:\\abc#%(title)s.%(ext)s')
# Check with nt._path_normpath if available
try:
import nt
nt_path_normpath = getattr(nt, '_path_normpath', None)
except Exception:
nt_path_normpath = None
for test, expected in [
('C:\\', 'C:\\'),
('../abc', '..\\abc'),
('../../abc', '..\\..\\abc'),
('./abc', 'abc'),
('./../abc', '..\\abc'),
('\\abc', '\\abc'),
('C:abc', 'C:abc'),
('C:abc\\..\\', 'C:'),
('C:abc\\..\\def\\..\\..\\', 'C:..'),
('C:\\abc\\xyz///..\\def\\', 'C:\\abc\\def'),
('abc/../', '.'),
('./abc/../', '.'),
]:
result = sanitize_path(test)
assert result == expected, f'{test} was incorrectly resolved'
assert result == sanitize_path(result), f'{test} changed after sanitizing again'
if nt_path_normpath:
assert result == nt_path_normpath(test), f'{test} does not match nt._path_normpath'
def test_sanitize_url(self):
self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')

2
yt_dlp/YoutubeDL.py
View File

@ -2121,7 +2121,7 @@ def _build_format_filter(self, filter_spec):
m = operator_rex.fullmatch(filter_spec)
if m:
try:
comparison_value = int(m.group('value'))
comparison_value = float(m.group('value'))
except ValueError:
comparison_value = parse_filesize(m.group('value'))
if comparison_value is None:

28
yt_dlp/extractor/_extractors.py
View File

@ -256,6 +256,7 @@
BilibiliCheeseIE,
BilibiliCheeseSeasonIE,
BilibiliCollectionListIE,
BiliBiliDynamicIE,
BilibiliFavoritesListIE,
BiliBiliIE,
BiliBiliPlayerIE,
@ -440,12 +441,6 @@
CrowdBunkerIE,
)
from .crtvg import CrtvgIE
from .crunchyroll import (
CrunchyrollArtistIE,
CrunchyrollBetaIE,
CrunchyrollBetaShowIE,
CrunchyrollMusicIE,
)
from .cspan import (
CSpanCongressIE,
CSpanIE,
@ -585,6 +580,10 @@
EggheadCourseIE,
EggheadLessonIE,
)
from .eggs import (
EggsArtistIE,
EggsIE,
)
from .eighttracks import EightTracksIE
from .eitb import EitbIE
from .elementorembed import ElementorEmbedIE
@ -700,11 +699,6 @@
FrontendMastersLessonIE,
)
from .fujitv import FujiTVFODPlus7IE
from .funimation import (
FunimationIE,
FunimationPageIE,
FunimationShowIE,
)
from .funk import FunkIE
from .funker530 import Funker530IE
from .fuyintv import FuyinTVIE
@ -1279,6 +1273,10 @@
)
from .nekohacker import NekoHackerIE
from .nerdcubed import NerdCubedFeedIE
from .nest import (
NestClipIE,
NestIE,
)
from .neteasemusic import (
NetEaseMusicAlbumIE,
NetEaseMusicDjRadioIE,
@ -1533,6 +1531,10 @@
PinterestCollectionIE,
PinterestIE,
)
from .piramidetv import (
PiramideTVChannelIE,
PiramideTVIE,
)
from .pixivsketch import (
PixivSketchIE,
PixivSketchUserIE,
@ -1984,6 +1986,10 @@
from .stretchinternet import StretchInternetIE
from .stripchat import StripchatIE
from .stv import STVPlayerIE
from .subsplash import (
SubsplashIE,
SubsplashPlaylistIE,
)
from .substack import SubstackIE
from .sunporno import SunPornoIE
from .sverigesradio import (

50
yt_dlp/extractor/abematv.py
View File

@ -421,14 +421,15 @@ def _real_extract(self, url):
class AbemaTVTitleIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/video/title/(?P<id>[^?/]+)'
_VALID_URL = r'https?://abema\.tv/video/title/(?P<id>[^?/#]+)/?(?:\?(?:[^#]+&)?s=(?P<season>[^&#]+))?'
_PAGE_SIZE = 25
_TESTS = [{
'url': 'https://abema.tv/video/title/90-1597',
'url': 'https://abema.tv/video/title/90-1887',
'info_dict': {
'id': '90-1597',
'id': '90-1887',
'title': 'シャッフルアイランド',
'description': 'md5:61b2425308f41a5282a926edda66f178',
},
'playlist_mincount': 2,
}, {
@ -436,41 +437,54 @@ class AbemaTVTitleIE(AbemaTVBaseIE):
'info_dict': {
'id': '193-132',
'title': '真心が届く~僕とスターのオフィス・ラブ!?~',
'description': 'md5:9b59493d1f3a792bafbc7319258e7af8',
},
'playlist_mincount': 16,
}, {
'url': 'https://abema.tv/video/title/25-102',
'url': 'https://abema.tv/video/title/25-1nzan-whrxe',
'info_dict': {
'id': '25-102',
'title': 'ソードアート・オンライン アリシゼーション',
'id': '25-1nzan-whrxe',
'title': 'ソードアート・オンライン',
'description': 'md5:c094904052322e6978495532bdbf06e6',
},
'playlist_mincount': 24,
'playlist_mincount': 25,
}, {
'url': 'https://abema.tv/video/title/26-2mzbynr-cph?s=26-2mzbynr-cph_s40',
'info_dict': {
'title': '〈物語〉シリーズ',
'id': '26-2mzbynr-cph',
'description': 'md5:e67873de1c88f360af1f0a4b84847a52',
},
'playlist_count': 59,
}]
def _fetch_page(self, playlist_id, series_version, page):
def _fetch_page(self, playlist_id, series_version, season_id, page):
query = {
'seriesVersion': series_version,
'offset': str(page * self._PAGE_SIZE),
'order': 'seq',
'limit': str(self._PAGE_SIZE),
}
if season_id:
query['seasonId'] = season_id
programs = self._call_api(
f'v1/video/series/{playlist_id}/programs', playlist_id,
note=f'Downloading page {page + 1}',
query={
'seriesVersion': series_version,
'offset': str(page * self._PAGE_SIZE),
'order': 'seq',
'limit': str(self._PAGE_SIZE),
})
query=query)
yield from (
self.url_result(f'https://abema.tv/video/episode/{x}')
for x in traverse_obj(programs, ('programs', ..., 'id')))
def _entries(self, playlist_id, series_version):
def _entries(self, playlist_id, series_version, season_id):
return OnDemandPagedList(
functools.partial(self._fetch_page, playlist_id, series_version),
functools.partial(self._fetch_page, playlist_id, series_version, season_id),
self._PAGE_SIZE)
def _real_extract(self, url):
playlist_id = self._match_id(url)
playlist_id, season_id = self._match_valid_url(url).group('id', 'season')
series_info = self._call_api(f'v1/video/series/{playlist_id}', playlist_id)
return self.playlist_result(
self._entries(playlist_id, series_info['version']), playlist_id=playlist_id,
self._entries(playlist_id, series_info['version'], season_id), playlist_id=playlist_id,
playlist_title=series_info.get('title'),
playlist_description=series_info.get('content'))

18
yt_dlp/extractor/acast.py
View File

@ -43,14 +43,14 @@ class ACastIE(ACastBaseIE):
_VALID_URL = r'''(?x:
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
(?:(?:embed|www|shows)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?"]+)
(?P<channel>[^/?#]+)/(?:episodes/)?(?P<id>[^/#?"]+)
)'''
_EMBED_REGEX = [rf'(?x)<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'url': 'https://shows.acast.com/sparpodcast/episodes/2.raggarmordet-rosterurdetforflutna',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
@ -59,7 +59,7 @@ class ACastIE(ACastBaseIE):
'timestamp': 1477346700,
'upload_date': '20161024',
'duration': 2766,
'creator': 'Third Ear Studio',
'creators': ['Third Ear Studio'],
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
'thumbnail': 'https://assets.pippa.io/shows/616ebe1886d7b1398620b943/616ebe33c7e6e70013cae7da.jpg',
@ -74,6 +74,9 @@ class ACastIE(ACastBaseIE):
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
'only_matching': True,
}, {
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
@ -110,7 +113,7 @@ class ACastChannelIE(ACastBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?acast\.com/|
(?:(?:www|shows)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<id>[^/#?]+)
@ -120,12 +123,15 @@ class ACastChannelIE(ACastBaseIE):
'info_dict': {
'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus',
'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
'description': 'md5:feca253de9947634605080cd9eeea2bf',
},
'playlist_mincount': 200,
}, {
'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True,
}, {
'url': 'https://shows.acast.com/sparpodcast',
'only_matching': True,
}]
@classmethod

113
yt_dlp/extractor/bilibili.py
View File

@ -4,7 +4,9 @@
import itertools
import json
import math
import random
import re
import string
import time
import urllib.parse
import uuid
@ -1177,28 +1179,26 @@ def _extract_playlist(self, fetch_page, get_metadata, get_entries):
class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>/video)?/?(?:[?#]|$)'
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)(?P<video>(?:/upload)?/video)?/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://space.bilibili.com/3985676/video',
'info_dict': {
'id': '3985676',
},
'playlist_mincount': 178,
'skip': 'login required',
}, {
'url': 'https://space.bilibili.com/313580179/video',
'info_dict': {
'id': '313580179',
},
'playlist_mincount': 92,
'skip': 'login required',
}]
def _real_extract(self, url):
playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video')
if not is_video_url:
self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. '
'To download audios, add a "/audio" to the URL')
'To download audios, add a "/upload/audio" to the URL')
def fetch_page(page_idx):
query = {
@ -1211,6 +1211,12 @@ def fetch_page(page_idx):
'ps': 30,
'tid': 0,
'web_location': 1550101,
'dm_img_list': '[]',
'dm_img_str': base64.b64encode(
''.join(random.choices(string.printable, k=random.randint(16, 64))).encode())[:-2].decode(),
'dm_cover_img_str': base64.b64encode(
''.join(random.choices(string.printable, k=random.randint(32, 128))).encode())[:-2].decode(),
'dm_img_inter': '{"ds":[],"wh":[6093,6631,31],"of":[430,760,380]}',
}
try:
@ -1221,14 +1227,14 @@ def fetch_page(page_idx):
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
'Request is blocked by server (412), please wait and try later.', expected=True)
raise
status_code = response['code']
if status_code == -401:
raise ExtractorError(
'Request is blocked by server (401), please add cookies, wait and try later.', expected=True)
elif status_code == -352 and not self.is_logged_in:
self.raise_login_required('Request is rejected, you need to login to access playlist')
'Request is blocked by server (401), please wait and try later.', expected=True)
elif status_code == -352:
raise ExtractorError('Request is rejected by server (352)', expected=True)
elif status_code != 0:
raise ExtractorError(f'Request failed ({status_code}): {response.get("message") or "Unknown error"}')
return response['data']
@ -1250,9 +1256,9 @@ def get_entries(page_data):
class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/audio'
_VALID_URL = r'https?://space\.bilibili\.com/(?P<id>\d+)/(?:upload/)?audio'
_TESTS = [{
'url': 'https://space.bilibili.com/313580179/audio',
'url': 'https://space.bilibili.com/313580179/upload/audio',
'info_dict': {
'id': '313580179',
},
@ -1275,7 +1281,8 @@ def get_metadata(page_data):
}
def get_entries(page_data):
for entry in page_data.get('data', []):
# data is None when the playlist is empty
for entry in page_data.get('data') or []:
yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
@ -1299,30 +1306,43 @@ def _extract_playlist(self, fetch_page, get_metadata, get_entries):
class BilibiliCollectionListIE(BilibiliSpaceListBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/collectiondetail/?\?sid=(?P<sid>\d+)'
_VALID_URL = [
r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/collectiondetail/?\?sid=(?P<sid>\d+)',
r'https?://space\.bilibili\.com/(?P<mid>\d+)/lists/(?P<sid>\d+)',
]
_TESTS = [{
'url': 'https://space.bilibili.com/2142762/channel/collectiondetail?sid=57445',
'url': 'https://space.bilibili.com/2142762/lists/3662502?type=season',
'info_dict': {
'id': '2142762_57445',
'title': '【完结】《底特律 变人》全结局流程解说',
'description': '',
'id': '2142762_3662502',
'title': '合集·《黑神话悟空》流程解说',
'description': '黑神话悟空 相关节目',
'uploader': '老戴在此',
'uploader_id': '2142762',
'timestamp': int,
'upload_date': str,
'thumbnail': 'https://archive.biliimg.com/bfs/archive/e0e543ae35ad3df863ea7dea526bc32e70f4c091.jpg',
'thumbnail': 'https://archive.biliimg.com/bfs/archive/22302e17dc849dd4533606d71bc89df162c3a9bf.jpg',
},
'playlist_mincount': 31,
'playlist_mincount': 62,
}, {
'url': 'https://space.bilibili.com/2142762/lists/3662502',
'only_matching': True,
}, {
'url': 'https://space.bilibili.com/2142762/channel/collectiondetail?sid=57445',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if BilibiliSeriesListIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
mid, sid = self._match_valid_url(url).group('mid', 'sid')
playlist_id = f'{mid}_{sid}'
def fetch_page(page_idx):
return self._download_json(
'https://api.bilibili.com/x/polymer/space/seasons_archives_list',
playlist_id, note=f'Downloading page {page_idx}',
'https://api.bilibili.com/x/polymer/web-space/seasons_archives_list',
playlist_id, note=f'Downloading page {page_idx}', headers={'Referer': url},
query={'mid': mid, 'season_id': sid, 'page_num': page_idx + 1, 'page_size': 30})['data']
def get_metadata(page_data):
@ -1349,9 +1369,12 @@ def get_entries(page_data):
class BilibiliSeriesListIE(BilibiliSpaceListBaseIE):
_VALID_URL = r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/seriesdetail/?\?\bsid=(?P<sid>\d+)'
_VALID_URL = [
r'https?://space\.bilibili\.com/(?P<mid>\d+)/channel/seriesdetail/?\?\bsid=(?P<sid>\d+)',
r'https?://space\.bilibili\.com/(?P<mid>\d+)/lists/(?P<sid>\d+)/?\?(?:[^#]+&)?type=series(?:[&#]|$)',
]
_TESTS = [{
'url': 'https://space.bilibili.com/1958703906/channel/seriesdetail?sid=547718&ctype=0',
'url': 'https://space.bilibili.com/1958703906/lists/547718?type=series',
'info_dict': {
'id': '1958703906_547718',
'title': '直播回放',
@ -1364,6 +1387,9 @@ class BilibiliSeriesListIE(BilibiliSpaceListBaseIE):
'modified_date': str,
},
'playlist_mincount': 513,
}, {
'url': 'https://space.bilibili.com/1958703906/channel/seriesdetail?sid=547718&ctype=0',
'only_matching': True,
}]
def _real_extract(self, url):
@ -1382,7 +1408,7 @@ def _real_extract(self, url):
def fetch_page(page_idx):
return self._download_json(
'https://api.bilibili.com/x/series/archives',
playlist_id, note=f'Downloading page {page_idx}',
playlist_id, note=f'Downloading page {page_idx}', headers={'Referer': url},
query={'mid': mid, 'series_id': sid, 'pn': page_idx + 1, 'ps': 30})['data']
def get_metadata(page_data):
@ -1861,6 +1887,47 @@ def _real_extract(self, url):
ie=BiliBiliIE.ie_key(), video_id=video_id)
class BiliBiliDynamicIE(InfoExtractor):
_VALID_URL = r'https?://(?:t\.bilibili\.com|(?:www\.)?bilibili\.com/opus)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://t.bilibili.com/998134289197432852',
'info_dict': {
'id': 'BV1TAmBYVEJr',
'ext': 'mp4',
'uploader_id': '1192648858',
'comment_count': int,
'_old_archive_ids': ['bilibili 113457567568273_part1'],
'thumbnail': 'http://i2.hdslb.com/bfs/archive/50091efd965d9f13ff6814f7ad374f90ab21e77d.jpg',
'duration': 929.238,
'upload_date': '20241110',
'uploader': '何同学工作室',
'like_count': int,
'view_count': int,
'title': '美国小朋友就玩这个？！何同学工作室11月开箱',
'description': '本期产品信息：\n机器狗\n气味模拟器\nCloudboom Strike LS\n无弦吉他\n蓝牙磁带音箱\n神奇画板',
'timestamp': 1731232800,
'tags': list,
'chapters': list,
},
}]
def _real_extract(self, url):
post_id = self._match_id(url)
# Without the newer chrome UA, the API will return an error (-352)
post_data = self._download_json(
'https://api.bilibili.com/x/polymer/web-dynamic/v1/detail', post_id,
query={'id': post_id}, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
})
video_url = traverse_obj(post_data, (
'data', 'item', (None, 'orig'), 'modules', 'module_dynamic',
(('major', ('archive', 'pgc')), ('additional', ('reserve', 'common'))),
'jump_url', {url_or_none}, any, {self._proto_relative_url}))
if not video_url or (self.suitable(video_url) and post_id == self._match_id(video_url)):
raise ExtractorError('No valid video URL found', expected=True)
return self.url_result(video_url)
class BiliIntlBaseIE(InfoExtractor):
_API_URL = 'https://api.bilibili.tv/intl/gateway'
_NETRC_MACHINE = 'biliintl'

25
yt_dlp/extractor/bluesky.py
View File

@ -88,7 +88,7 @@ class BlueskyIE(InfoExtractor):
},
}, {
'url': 'https://bsky.app/profile/de1.pds.tentacle.expert/post/3l3w4tnezek2e',
'md5': '1af9c7fda061cf7593bbffca89e43d1c',
'md5': 'cc0110ed1f6b0247caac8234cc1e861d',
'info_dict': {
'id': '3l3w4tnezek2e',
'ext': 'mp4',
@ -133,6 +133,8 @@ class BlueskyIE(InfoExtractor):
'channel_follower_count': int,
'categories': ['Entertainment'],
'tags': [],
'chapters': list,
'heatmap': 'count:100',
},
'add_ie': ['Youtube'],
}, {
@ -184,14 +186,14 @@ class BlueskyIE(InfoExtractor):
},
},
}, {
'url': 'https://bsky.app/profile/alt.bun.how/post/3l7rdfxhyds2f',
'url': 'https://bsky.app/profile/cinny.bun.how/post/3l7rdfxhyds2f',
'md5': '8775118b235cf9fa6b5ad30f95cda75c',
'info_dict': {
'id': '3l7rdfxhyds2f',
'ext': 'mp4',
'uploader': 'cinnamon',
'uploader_id': 'alt.bun.how',
'uploader_url': 'https://bsky.app/profile/alt.bun.how',
'uploader_id': 'cinny.bun.how',
'uploader_url': 'https://bsky.app/profile/cinny.bun.how',
'channel_id': 'did:plc:7x6rtuenkuvxq3zsvffp2ide',
'channel_url': 'https://bsky.app/profile/did:plc:7x6rtuenkuvxq3zsvffp2ide',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
@ -284,17 +286,19 @@ def _get_service_endpoint(self, did, video_id):
services, ('service', lambda _, x: x['type'] == 'AtprotoPersonalDataServer',
'serviceEndpoint', {url_or_none}, any)) or 'https://bsky.social'
def _real_extract(self, url):
handle, video_id = self._match_valid_url(url).group('handle', 'id')
post = self._download_json(
def _extract_post(self, handle, post_id):
return self._download_json(
'https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread',
video_id, query={
'uri': f'at://{handle}/app.bsky.feed.post/{video_id}',
post_id, query={
'uri': f'at://{handle}/app.bsky.feed.post/{post_id}',
'depth': 0,
'parentHeight': 0,
})['thread']['post']
def _real_extract(self, url):
handle, video_id = self._match_valid_url(url).group('handle', 'id')
post = self._extract_post(handle, video_id)
entries = []
# app.bsky.embed.video.view/app.bsky.embed.external.view
entries.extend(self._extract_videos(post, video_id))
@ -341,6 +345,7 @@ def _extract_videos(self, root, video_id, embed_path='embed', record_path='recor
formats.append({
'format_id': 'blob',
'quality': 1,
'url': update_url_query(
self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': video_cid}),
**traverse_obj(root, (*embed_path, 'aspectRatio', {

692
yt_dlp/extractor/crunchyroll.py
View File

@ -1,692 +0,0 @@
import base64
import uuid
from .common import InfoExtractor
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
format_field,
int_or_none,
jwt_decode_hs256,
parse_age_limit,
parse_count,
parse_iso8601,
qualities,
time_seconds,
traverse_obj,
url_or_none,
urlencode_postdata,
)
class CrunchyrollBaseIE(InfoExtractor):
_BASE_URL = 'https://www.crunchyroll.com'
_API_BASE = 'https://api.crunchyroll.com'
_NETRC_MACHINE = 'crunchyroll'
_SWITCH_USER_AGENT = 'Crunchyroll/1.8.0 Nintendo Switch/12.3.12.0 UE4/4.27'
_REFRESH_TOKEN = None
_AUTH_HEADERS = None
_AUTH_EXPIRY = None
_API_ENDPOINT = None
_BASIC_AUTH = 'Basic ' + base64.b64encode(':'.join((
't-kdgp2h8c3jub8fn0fq',
'yfLDfMfrYvKXh4JXS1LEI2cCqu1v5Wan',
)).encode()).decode()
_IS_PREMIUM = None
_LOCALE_LOOKUP = {
'ar': 'ar-SA',
'de': 'de-DE',
'': 'en-US',
'es': 'es-419',
'es-es': 'es-ES',
'fr': 'fr-FR',
'it': 'it-IT',
'pt-br': 'pt-BR',
'pt-pt': 'pt-PT',
'ru': 'ru-RU',
'hi': 'hi-IN',
}
def _set_auth_info(self, response):
CrunchyrollBaseIE._IS_PREMIUM = 'cr_premium' in traverse_obj(response, ('access_token', {jwt_decode_hs256}, 'benefits', ...))
CrunchyrollBaseIE._AUTH_HEADERS = {'Authorization': response['token_type'] + ' ' + response['access_token']}
CrunchyrollBaseIE._AUTH_EXPIRY = time_seconds(seconds=traverse_obj(response, ('expires_in', {float_or_none}), default=300) - 10)
def _request_token(self, headers, data, note='Requesting token', errnote='Failed to request token'):
try:
return self._download_json(
f'{self._BASE_URL}/auth/v1/token', None, note=note, errnote=errnote,
headers=headers, data=urlencode_postdata(data), impersonate=True)
except ExtractorError as error:
if not isinstance(error.cause, HTTPError) or error.cause.status != 403:
raise
if target := error.cause.response.extensions.get('impersonate'):
raise ExtractorError(f'Got HTTP Error 403 when using impersonate target "{target}"')
raise ExtractorError(
'Request blocked by Cloudflare. '
'Install the required impersonation dependency if possible, '
'or else navigate to Crunchyroll in your browser, '
'then pass the fresh cookies (with --cookies-from-browser or --cookies) '
'and your browser\'s User-Agent (with --user-agent)', expected=True)
def _perform_login(self, username, password):
if not CrunchyrollBaseIE._REFRESH_TOKEN:
CrunchyrollBaseIE._REFRESH_TOKEN = self.cache.load(self._NETRC_MACHINE, username)
if CrunchyrollBaseIE._REFRESH_TOKEN:
return
try:
login_response = self._request_token(
headers={'Authorization': self._BASIC_AUTH}, data={
'username': username,
'password': password,
'grant_type': 'password',
'scope': 'offline_access',
}, note='Logging in', errnote='Failed to log in')
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 401:
raise ExtractorError('Invalid username and/or password', expected=True)
raise
CrunchyrollBaseIE._REFRESH_TOKEN = login_response['refresh_token']
self.cache.store(self._NETRC_MACHINE, username, CrunchyrollBaseIE._REFRESH_TOKEN)
self._set_auth_info(login_response)
def _update_auth(self):
if CrunchyrollBaseIE._AUTH_HEADERS and CrunchyrollBaseIE._AUTH_EXPIRY > time_seconds():
return
auth_headers = {'Authorization': self._BASIC_AUTH}
if CrunchyrollBaseIE._REFRESH_TOKEN:
data = {
'refresh_token': CrunchyrollBaseIE._REFRESH_TOKEN,
'grant_type': 'refresh_token',
'scope': 'offline_access',
}
else:
data = {'grant_type': 'client_id'}
auth_headers['ETP-Anonymous-ID'] = uuid.uuid4()
try:
auth_response = self._request_token(auth_headers, data)
except ExtractorError as error:
username, password = self._get_login_info()
if not username or not isinstance(error.cause, HTTPError) or error.cause.status != 400:
raise
self.to_screen('Refresh token has expired. Re-logging in')
CrunchyrollBaseIE._REFRESH_TOKEN = None
self.cache.store(self._NETRC_MACHINE, username, None)
self._perform_login(username, password)
return
self._set_auth_info(auth_response)
def _locale_from_language(self, language):
config_locale = self._configuration_arg('metadata', ie_key=CrunchyrollBetaIE, casesense=True)
return config_locale[0] if config_locale else self._LOCALE_LOOKUP.get(language)
def _call_base_api(self, endpoint, internal_id, lang, note=None, query={}):
self._update_auth()
if not endpoint.startswith('/'):
endpoint = f'/{endpoint}'
query = query.copy()
locale = self._locale_from_language(lang)
if locale:
query['locale'] = locale
return self._download_json(
f'{self._BASE_URL}{endpoint}', internal_id, note or f'Calling API: {endpoint}',
headers=CrunchyrollBaseIE._AUTH_HEADERS, query=query)
def _call_api(self, path, internal_id, lang, note='api', query={}):
if not path.startswith(f'/content/v2/{self._API_ENDPOINT}/'):
path = f'/content/v2/{self._API_ENDPOINT}/{path}'
try:
result = self._call_base_api(
path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query)
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 404:
return None
raise
if not result:
raise ExtractorError(f'Unexpected response when downloading {note} JSON')
return result
def _extract_chapters(self, internal_id):
# if no skip events are available, a 403 xml error is returned
skip_events = self._download_json(
f'https://static.crunchyroll.com/skip-events/production/{internal_id}.json',
internal_id, note='Downloading chapter info', fatal=False, errnote=False)
if not skip_events:
return None
chapters = []
for event in ('recap', 'intro', 'credits', 'preview'):
start = traverse_obj(skip_events, (event, 'start', {float_or_none}))
end = traverse_obj(skip_events, (event, 'end', {float_or_none}))
# some chapters have no start and/or ending time, they will just be ignored
if start is None or end is None:
continue
chapters.append({'title': event.capitalize(), 'start_time': start, 'end_time': end})
return chapters
def _extract_stream(self, identifier, display_id=None):
if not display_id:
display_id = identifier
self._update_auth()
headers = {**CrunchyrollBaseIE._AUTH_HEADERS, 'User-Agent': self._SWITCH_USER_AGENT}
try:
stream_response = self._download_json(
f'https://cr-play-service.prd.crunchyrollsvc.com/v1/{identifier}/console/switch/play',
display_id, note='Downloading stream info', errnote='Failed to download stream info', headers=headers)
except ExtractorError as error:
if self.get_param('ignore_no_formats_error'):
self.report_warning(error.orig_msg)
return [], {}
elif isinstance(error.cause, HTTPError) and error.cause.status == 420:
raise ExtractorError(
'You have reached the rate-limit for active streams; try again later', expected=True)
raise
available_formats = {'': ('', '', stream_response['url'])}
for hardsub_lang, stream in traverse_obj(stream_response, ('hardSubs', {dict.items}, lambda _, v: v[1]['url'])):
available_formats[hardsub_lang] = (f'hardsub-{hardsub_lang}', hardsub_lang, stream['url'])
requested_hardsubs = [('' if val == 'none' else val) for val in (self._configuration_arg('hardsub') or ['none'])]
hardsub_langs = [lang for lang in available_formats if lang]
if hardsub_langs and 'all' not in requested_hardsubs:
full_format_langs = set(requested_hardsubs)
self.to_screen(f'Available hardsub languages: {", ".join(hardsub_langs)}')
self.to_screen(
'To extract formats of a hardsub language, use '
'"--extractor-args crunchyrollbeta:hardsub=<language_code or all>". '
'See https://github.com/yt-dlp/yt-dlp#crunchyrollbeta-crunchyroll for more info',
only_once=True)
else:
full_format_langs = set(map(str.lower, available_formats))
audio_locale = traverse_obj(stream_response, ('audioLocale', {str}))
hardsub_preference = qualities(requested_hardsubs[::-1])
formats, subtitles = [], {}
for format_id, hardsub_lang, stream_url in available_formats.values():
if hardsub_lang.lower() in full_format_langs:
adaptive_formats, dash_subs = self._extract_mpd_formats_and_subtitles(
stream_url, display_id, mpd_id=format_id, headers=CrunchyrollBaseIE._AUTH_HEADERS,
fatal=False, note=f'Downloading {f"{format_id} " if hardsub_lang else ""}MPD manifest')
self._merge_subtitles(dash_subs, target=subtitles)
else:
continue # XXX: Update this if meta mpd formats work; will be tricky with token invalidation
for f in adaptive_formats:
if f.get('acodec') != 'none':
f['language'] = audio_locale
f['quality'] = hardsub_preference(hardsub_lang.lower())
formats.extend(adaptive_formats)
for locale, subtitle in traverse_obj(stream_response, (('subtitles', 'captions'), {dict.items}, ...)):
subtitles.setdefault(locale, []).append(traverse_obj(subtitle, {'url': 'url', 'ext': 'format'}))
# Invalidate stream token to avoid rate-limit
error_msg = 'Unable to invalidate stream token; you may experience rate-limiting'
if stream_token := stream_response.get('token'):
self._request_webpage(Request(
f'https://cr-play-service.prd.crunchyrollsvc.com/v1/token/{identifier}/{stream_token}/inactive',
headers=headers, method='PATCH'), display_id, 'Invalidating stream token', error_msg, fatal=False)
else:
self.report_warning(error_msg)
return formats, subtitles
class CrunchyrollCmsBaseIE(CrunchyrollBaseIE):
_API_ENDPOINT = 'cms'
_CMS_EXPIRY = None
def _call_cms_api_signed(self, path, internal_id, lang, note='api'):
if not CrunchyrollCmsBaseIE._CMS_EXPIRY or CrunchyrollCmsBaseIE._CMS_EXPIRY <= time_seconds():
response = self._call_base_api('index/v2', None, lang, 'Retrieving signed policy')['cms_web']
CrunchyrollCmsBaseIE._CMS_QUERY = {
'Policy': response['policy'],
'Signature': response['signature'],
'Key-Pair-Id': response['key_pair_id'],
}
CrunchyrollCmsBaseIE._CMS_BUCKET = response['bucket']
CrunchyrollCmsBaseIE._CMS_EXPIRY = parse_iso8601(response['expires']) - 10
if not path.startswith('/cms/v2'):
path = f'/cms/v2{CrunchyrollCmsBaseIE._CMS_BUCKET}/{path}'
return self._call_base_api(
path, internal_id, lang, f'Downloading {note} JSON (signed cms)', query=CrunchyrollCmsBaseIE._CMS_QUERY)
class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
IE_NAME = 'crunchyroll'
_VALID_URL = r'''(?x)
https?://(?:beta\.|www\.)?crunchyroll\.com/
(?:(?P<lang>\w{2}(?:-\w{2})?)/)?
watch/(?!concert|musicvideo)(?P<id>\w+)'''
_TESTS = [{
# Premium only
'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
'info_dict': {
'id': 'GY2P1Q98Y',
'ext': 'mp4',
'duration': 1380.241,
'timestamp': 1459632600,
'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
'title': 'World Trigger Episode 73 – To the Future',
'upload_date': '20160402',
'series': 'World Trigger',
'series_id': 'GR757DMKY',
'season': 'World Trigger',
'season_id': 'GR9P39NJ6',
'season_number': 1,
'episode': 'To the Future',
'episode_number': 73,
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'chapters': 'count:2',
'age_limit': 14,
'like_count': int,
'dislike_count': int,
},
'params': {
'skip_download': 'm3u8',
'extractor_args': {'crunchyrollbeta': {'hardsub': ['de-DE']}},
'format': 'bv[format_id~=hardsub]',
},
}, {
# Premium only
'url': 'https://www.crunchyroll.com/watch/GYE5WKQGR',
'info_dict': {
'id': 'GYE5WKQGR',
'ext': 'mp4',
'duration': 366.459,
'timestamp': 1476788400,
'description': 'md5:74b67283ffddd75f6e224ca7dc031e76',
'title': 'SHELTER – Porter Robinson presents Shelter the Animation',
'upload_date': '20161018',
'series': 'SHELTER',
'series_id': 'GYGG09WWY',
'season': 'SHELTER',
'season_id': 'GR09MGK4R',
'season_number': 1,
'episode': 'Porter Robinson presents Shelter the Animation',
'episode_number': 0,
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'age_limit': 14,
'like_count': int,
'dislike_count': int,
},
'params': {'skip_download': True},
}, {
'url': 'https://www.crunchyroll.com/watch/GJWU2VKK3/cherry-blossom-meeting-and-a-coming-blizzard',
'info_dict': {
'id': 'GJWU2VKK3',
'ext': 'mp4',
'duration': 1420.054,
'description': 'md5:2d1c67c0ec6ae514d9c30b0b99a625cd',
'title': 'The Ice Guy and His Cool Female Colleague Episode 1 – Cherry Blossom Meeting and a Coming Blizzard',
'series': 'The Ice Guy and His Cool Female Colleague',
'series_id': 'GW4HM75NP',
'season': 'The Ice Guy and His Cool Female Colleague',
'season_id': 'GY9PC21VE',
'season_number': 1,
'episode': 'Cherry Blossom Meeting and a Coming Blizzard',
'episode_number': 1,
'chapters': 'count:2',
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'timestamp': 1672839000,
'upload_date': '20230104',
'age_limit': 14,
'like_count': int,
'dislike_count': int,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.crunchyroll.com/watch/GM8F313NQ',
'info_dict': {
'id': 'GM8F313NQ',
'ext': 'mp4',
'title': 'Garakowa -Restore the World-',
'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
'duration': 3996.104,
'age_limit': 13,
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
},
'params': {'skip_download': 'm3u8'},
'skip': 'no longer exists',
}, {
'url': 'https://www.crunchyroll.com/watch/G62PEZ2E6',
'info_dict': {
'id': 'G62PEZ2E6',
'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
'age_limit': 13,
'duration': 65.138,
'title': 'Garakowa -Restore the World-',
},
'playlist_mincount': 5,
}, {
'url': 'https://www.crunchyroll.com/de/watch/GY2P1Q98Y',
'only_matching': True,
}, {
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
'only_matching': True,
}]
# We want to support lazy playlist filtering and movie listings cannot be inside a playlist
_RETURN_TYPE = 'video'
def _real_extract(self, url):
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
# We need to use unsigned API call to allow ratings query string
response = traverse_obj(self._call_api(
f'objects/{internal_id}', internal_id, lang, 'object info', {'ratings': 'true'}), ('data', 0, {dict}))
if not response:
raise ExtractorError(f'No video with id {internal_id} could be found (possibly region locked?)', expected=True)
object_type = response.get('type')
if object_type == 'episode':
result = self._transform_episode_response(response)
elif object_type == 'movie':
result = self._transform_movie_response(response)
elif object_type == 'movie_listing':
first_movie_id = traverse_obj(response, ('movie_listing_metadata', 'first_movie_id'))
if not self._yes_playlist(internal_id, first_movie_id):
return self.url_result(f'{self._BASE_URL}/{lang}watch/{first_movie_id}', CrunchyrollBetaIE, first_movie_id)
def entries():
movies = self._call_api(f'movie_listings/{internal_id}/movies', internal_id, lang, 'movie list')
for movie_response in traverse_obj(movies, ('data', ...)):
yield self.url_result(
f'{self._BASE_URL}/{lang}watch/{movie_response["id"]}',
CrunchyrollBetaIE, **self._transform_movie_response(movie_response))
return self.playlist_result(entries(), **self._transform_movie_response(response))
else:
raise ExtractorError(f'Unknown object type {object_type}')
if not self._IS_PREMIUM and traverse_obj(response, (f'{object_type}_metadata', 'is_premium_only')):
message = f'This {object_type} is for premium members only'
if CrunchyrollBaseIE._REFRESH_TOKEN:
self.raise_no_formats(message, expected=True, video_id=internal_id)
else:
self.raise_login_required(message, method='password', metadata_available=True)
else:
result['formats'], result['subtitles'] = self._extract_stream(internal_id)
result['chapters'] = self._extract_chapters(internal_id)
def calculate_count(item):
return parse_count(''.join((item['displayed'], item.get('unit') or '')))
result.update(traverse_obj(response, ('rating', {
'like_count': ('up', {calculate_count}),
'dislike_count': ('down', {calculate_count}),
})))
return result
@staticmethod
def _transform_episode_response(data):
metadata = traverse_obj(data, (('episode_metadata', None), {dict}), get_all=False) or {}
return {
'id': data['id'],
'title': ' \u2013 '.join((
('{}{}'.format(
format_field(metadata, 'season_title'),
format_field(metadata, 'episode', ' Episode %s'))),
format_field(data, 'title'))),
**traverse_obj(data, {
'episode': ('title', {str}),
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
'thumbnails': ('images', 'thumbnail', ..., ..., {
'url': ('source', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}),
}),
**traverse_obj(metadata, {
'duration': ('duration_ms', {float_or_none(scale=1000)}),
'timestamp': ('upload_date', {parse_iso8601}),
'series': ('series_title', {str}),
'series_id': ('series_id', {str}),
'season': ('season_title', {str}),
'season_id': ('season_id', {str}),
'season_number': ('season_number', ({int}, {float_or_none})),
'episode_number': ('sequence_number', ({int}, {float_or_none})),
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
'language': ('audio_locale', {str}),
}, get_all=False),
}
@staticmethod
def _transform_movie_response(data):
metadata = traverse_obj(data, (('movie_metadata', 'movie_listing_metadata', None), {dict}), get_all=False) or {}
return {
'id': data['id'],
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
'thumbnails': ('images', 'thumbnail', ..., ..., {
'url': ('source', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}),
}),
**traverse_obj(metadata, {
'duration': ('duration_ms', {float_or_none(scale=1000)}),
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
}),
}
class CrunchyrollBetaShowIE(CrunchyrollCmsBaseIE):
IE_NAME = 'crunchyroll:playlist'
_VALID_URL = r'''(?x)
https?://(?:beta\.|www\.)?crunchyroll\.com/
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
series/(?P<id>\w+)'''
_TESTS = [{
'url': 'https://www.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
'info_dict': {
'id': 'GY19NQ2QR',
'title': 'Girl Friend BETA',
'description': 'md5:99c1b22ee30a74b536a8277ced8eb750',
# XXX: `thumbnail` does not get set from `thumbnails` in playlist
# 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'age_limit': 14,
},
'playlist_mincount': 10,
}, {
'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR',
'only_matching': True,
}]
def _real_extract(self, url):
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
def entries():
seasons_response = self._call_cms_api_signed(f'seasons?series_id={internal_id}', internal_id, lang, 'seasons')
for season in traverse_obj(seasons_response, ('items', ..., {dict})):
episodes_response = self._call_cms_api_signed(
f'episodes?season_id={season["id"]}', season['id'], lang, 'episode list')
for episode_response in traverse_obj(episodes_response, ('items', ..., {dict})):
yield self.url_result(
f'{self._BASE_URL}/{lang}watch/{episode_response["id"]}',
CrunchyrollBetaIE, **CrunchyrollBetaIE._transform_episode_response(episode_response))
return self.playlist_result(
entries(), internal_id,
**traverse_obj(self._call_api(f'series/{internal_id}', internal_id, lang, 'series'), ('data', 0, {
'title': ('title', {str}),
'description': ('description', {lambda x: x.replace(r'\r\n', '\n')}),
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
'thumbnails': ('images', ..., ..., ..., {
'url': ('source', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}),
})))
class CrunchyrollMusicIE(CrunchyrollBaseIE):
IE_NAME = 'crunchyroll:music'
_VALID_URL = r'''(?x)
https?://(?:www\.)?crunchyroll\.com/
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
watch/(?P<type>concert|musicvideo)/(?P<id>\w+)'''
_TESTS = [{
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79',
'info_dict': {
'ext': 'mp4',
'id': 'MV5B02C79',
'display_id': 'egaono-hana',
'title': 'Egaono Hana',
'track': 'Egaono Hana',
'artists': ['Goose house'],
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'genres': ['J-Pop'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C',
'info_dict': {
'ext': 'mp4',
'id': 'MV88BB7F2C',
'display_id': 'crossing-field',
'title': 'Crossing Field',
'track': 'Crossing Field',
'artists': ['LiSA'],
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'genres': ['Anime'],
},
'params': {'skip_download': 'm3u8'},
'skip': 'no longer exists',
}, {
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135',
'info_dict': {
'ext': 'mp4',
'id': 'MC2E2AC135',
'display_id': 'live-is-smile-always-364joker-at-yokohama-arena',
'title': 'LiVE is Smile Always-364+JOKER- at YOKOHAMA ARENA',
'track': 'LiVE is Smile Always-364+JOKER- at YOKOHAMA ARENA',
'artists': ['LiSA'],
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
'description': 'md5:747444e7e6300907b7a43f0a0503072e',
'genres': ['J-Pop'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79/egaono-hana',
'only_matching': True,
}, {
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135/live-is-smile-always-364joker-at-yokohama-arena',
'only_matching': True,
}, {
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
'only_matching': True,
}]
_API_ENDPOINT = 'music'
def _real_extract(self, url):
lang, internal_id, object_type = self._match_valid_url(url).group('lang', 'id', 'type')
path, name = {
'concert': ('concerts', 'concert info'),
'musicvideo': ('music_videos', 'music video info'),
}[object_type]
response = traverse_obj(self._call_api(f'{path}/{internal_id}', internal_id, lang, name), ('data', 0, {dict}))
if not response:
raise ExtractorError(f'No video with id {internal_id} could be found (possibly region locked?)', expected=True)
result = self._transform_music_response(response)
if not self._IS_PREMIUM and response.get('isPremiumOnly'):
message = f'This {response.get("type") or "media"} is for premium members only'
if CrunchyrollBaseIE._REFRESH_TOKEN:
self.raise_no_formats(message, expected=True, video_id=internal_id)
else:
self.raise_login_required(message, method='password', metadata_available=True)
else:
result['formats'], _ = self._extract_stream(f'music/{internal_id}', internal_id)
return result
@staticmethod
def _transform_music_response(data):
return {
'id': data['id'],
**traverse_obj(data, {
'display_id': 'slug',
'title': 'title',
'track': 'title',
'artists': ('artist', 'name', all),
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n') or None}),
'thumbnails': ('images', ..., ..., {
'url': ('source', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}),
'genres': ('genres', ..., 'displayValue'),
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
}),
}
class CrunchyrollArtistIE(CrunchyrollBaseIE):
IE_NAME = 'crunchyroll:artist'
_VALID_URL = r'''(?x)
https?://(?:www\.)?crunchyroll\.com/
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
artist/(?P<id>\w{10})'''
_TESTS = [{
'url': 'https://www.crunchyroll.com/artist/MA179CB50D',
'info_dict': {
'id': 'MA179CB50D',
'title': 'LiSA',
'genres': ['Anime', 'J-Pop', 'Rock'],
'description': 'md5:16d87de61a55c3f7d6c454b73285938e',
},
'playlist_mincount': 83,
}, {
'url': 'https://www.crunchyroll.com/artist/MA179CB50D/lisa',
'only_matching': True,
}]
_API_ENDPOINT = 'music'
def _real_extract(self, url):
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
response = traverse_obj(self._call_api(
f'artists/{internal_id}', internal_id, lang, 'artist info'), ('data', 0))
def entries():
for attribute, path in [('concerts', 'concert'), ('videos', 'musicvideo')]:
for internal_id in traverse_obj(response, (attribute, ...)):
yield self.url_result(f'{self._BASE_URL}/watch/{path}/{internal_id}', CrunchyrollMusicIE, internal_id)
return self.playlist_result(entries(), **self._transform_artist_response(response))
@staticmethod
def _transform_artist_response(data):
return {
'id': data['id'],
**traverse_obj(data, {
'title': 'name',
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
'thumbnails': ('images', ..., ..., {
'url': ('source', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
}),
'genres': ('genres', ..., 'displayValue'),
}),
}

37
yt_dlp/extractor/cwtv.py
View File

@ -8,28 +8,29 @@
str_or_none,
update_url_query,
)
from ..utils.traversal import traverse_obj
class CWTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
_TESTS = [{
'url': 'https://www.cwtv.com/shows/all-american-homecoming/ready-or-not/?play=d848488f-f62a-40fd-af1f-6440b1821aab',
'url': 'https://www.cwtv.com/shows/continuum/a-stitch-in-time/?play=9149a1e1-4cb2-46d7-81b2-47d35bbd332b',
'info_dict': {
'id': 'd848488f-f62a-40fd-af1f-6440b1821aab',
'id': '9149a1e1-4cb2-46d7-81b2-47d35bbd332b',
'ext': 'mp4',
'title': 'Ready Or Not',
'description': 'Simone is concerned about changes taking place at Bringston; JR makes a decision about his future.',
'thumbnail': r're:^https?://.*\.jpe?g$',
'duration': 2547,
'timestamp': 1720519200,
'title': 'A Stitch in Time',
'description': r're:(?s)City Protective Services officer Kiera Cameron is transported from 2077.+',
'thumbnail': r're:https?://.+\.jpe?g',
'duration': 2632,
'timestamp': 1736928000,
'uploader': 'CWTV',
'chapters': 'count:6',
'series': 'All American: Homecoming',
'season_number': 3,
'chapters': 'count:5',
'series': 'Continuum',
'season_number': 1,
'episode_number': 1,
'age_limit': 0,
'upload_date': '20240709',
'season': 'Season 3',
'age_limit': 14,
'upload_date': '20250115',
'season': 'Season 1',
'episode': 'Episode 1',
},
'params': {
@ -42,7 +43,7 @@ class CWTVIE(InfoExtractor):
'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
'ext': 'mp4',
'title': 'Legends of Yesterday',
'description': 'Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote location to keep them hidden from Vandal Savage while they figure out how to defeat him.',
'description': r're:(?s)Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote.+',
'duration': 2665,
'series': 'Arrow',
'season_number': 4,
@ -71,7 +72,7 @@ class CWTVIE(InfoExtractor):
'timestamp': 1444107300,
'age_limit': 14,
'uploader': 'CWTV',
'thumbnail': r're:^https?://.*\.jpe?g$',
'thumbnail': r're:https?://.+\.jpe?g',
'chapters': 'count:4',
'episode': 'Episode 20',
'season': 'Season 11',
@ -94,9 +95,9 @@ class CWTVIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
f'https://images.cwtv.com/feed/mobileapp/video-meta/apiversion_12/guid_{video_id}', video_id)
if data.get('result') != 'ok':
raise ExtractorError(data['msg'], expected=True)
f'https://images.cwtv.com/feed/app-2/video-meta/apiversion_22/device_android/guid_{video_id}', video_id)
if traverse_obj(data, 'result') != 'ok':
raise ExtractorError(traverse_obj(data, (('error_msg', 'msg'), {str}, any)), expected=True)
video_data = data['video']
title = video_data['title']
mpx_url = update_url_query(

2
yt_dlp/extractor/dropout.py
View File

@ -135,7 +135,7 @@ def _real_extract(self, url):
self.raise_login_required(method='any')
raise ExtractorError(login_err, expected=True)
embed_url = self._search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
embed_url = self._html_search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
thumbnail = self._og_search_thumbnail(webpage)
watch_info = get_element_by_id('watch-info', webpage) or ''

155
yt_dlp/extractor/eggs.py Normal file
View File

@ -0,0 +1,155 @@
import secrets
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
int_or_none,
parse_iso8601,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class EggsBaseIE(InfoExtractor):
_API_HEADERS = {
'Accept': '*/*',
'apVersion': '8.2.00',
'deviceName': 'Android',
}
def _real_initialize(self):
self._API_HEADERS['deviceId'] = secrets.token_hex(8)
def _call_api(self, endpoint, video_id):
return self._download_json(
f'https://app-front-api.eggs.mu/v1/{endpoint}', video_id,
headers=self._API_HEADERS)
def _extract_music_info(self, data):
if yt_url := traverse_obj(data, ('youtubeUrl', {url_or_none})):
return self.url_result(yt_url, ie=YoutubeIE)
artist_name = traverse_obj(data, ('artist', 'artistName', {str_or_none}))
music_id = traverse_obj(data, ('musicId', {str_or_none}))
webpage_url = None
if artist_name and music_id:
webpage_url = f'https://eggs.mu/artist/{artist_name}/song/{music_id}'
return {
'id': music_id,
'vcodec': 'none',
'webpage_url': webpage_url,
'extractor_key': EggsIE.ie_key(),
'extractor': EggsIE.IE_NAME,
**traverse_obj(data, {
'title': ('musicTitle', {str}),
'url': ('musicDataPath', {url_or_none}),
'uploader': ('artist', 'displayName', {str}),
'uploader_id': ('artist', 'artistId', {str_or_none}),
'thumbnail': ('imageDataPath', {url_or_none}),
'view_count': ('numberOfMusicPlays', {int_or_none}),
'like_count': ('numberOfLikes', {int_or_none}),
'comment_count': ('numberOfComments', {int_or_none}),
'composers': ('composer', {str}, all),
'tags': ('tags', ..., {str}),
'timestamp': ('releaseDate', {parse_iso8601}),
'artist': ('artist', 'displayName', {str}),
})}
class EggsIE(EggsBaseIE):
IE_NAME = 'eggs:single'
_VALID_URL = r'https?://eggs\.mu/artist/[^/?#]+/song/(?P<id>[\da-f-]+)'
_TESTS = [{
'url': 'https://eggs.mu/artist/32_sunny_girl/song/0e95fd1d-4d61-4d5b-8b18-6092c551da90',
'info_dict': {
'id': '0e95fd1d-4d61-4d5b-8b18-6092c551da90',
'ext': 'm4a',
'title': 'シネマと信号',
'uploader': 'Sunny Girl',
'thumbnail': r're:https?://.*\.jpg(?:\?.*)?$',
'uploader_id': '1607',
'like_count': int,
'timestamp': 1731327327,
'composers': ['橘高連太郎'],
'view_count': int,
'comment_count': int,
'artists': ['Sunny Girl'],
'upload_date': '20241111',
'tags': ['SunnyGirl', 'シネマと信号'],
},
}, {
'url': 'https://eggs.mu/artist/KAMO_3pband/song/1d4bc45f-1af6-47a9-8b30-a70cae350b4f',
'info_dict': {
'id': '80cLKA2wnoA',
'ext': 'mp4',
'title': 'KAMO「いい女だから」Audio',
'uploader': 'KAMO',
'live_status': 'not_live',
'channel_id': 'UCsHLBw2__5Q9y55skXPotOg',
'channel_follower_count': int,
'description': 'md5:d260da711ecbec3e720293dc11401b87',
'availability': 'public',
'uploader_id': '@KAMO_band',
'upload_date': '20240925',
'thumbnail': 'https://i.ytimg.com/vi/80cLKA2wnoA/maxresdefault.jpg',
'comment_count': int,
'channel_url': 'https://www.youtube.com/channel/UCsHLBw2__5Q9y55skXPotOg',
'view_count': int,
'duration': 151,
'like_count': int,
'channel': 'KAMO',
'playable_in_embed': True,
'uploader_url': 'https://www.youtube.com/@KAMO_band',
'tags': [],
'timestamp': 1727271121,
'age_limit': 0,
'categories': ['People & Blogs'],
},
'add_ie': ['Youtube'],
'params': {'skip_download': 'Youtube'},
}]
def _real_extract(self, url):
song_id = self._match_id(url)
json_data = self._call_api(f'musics/{song_id}', song_id)
return self._extract_music_info(json_data)
class EggsArtistIE(EggsBaseIE):
IE_NAME = 'eggs:artist'
_VALID_URL = r'https?://eggs\.mu/artist/(?P<id>\w+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://eggs.mu/artist/32_sunny_girl',
'info_dict': {
'id': '32_sunny_girl',
'thumbnail': 'https://image-pro.eggs.mu/profile/1607.jpeg?updated_at=2024-04-03T20%3A06%3A00%2B09%3A00',
'description': 'Muddy Mine / 東京高田馬場CLUB PHASE / Gt.Vo 橘高 連太郎 / Ba.Cho 小野 ゆうき / Dr 大森 りゅうひこ',
'title': 'Sunny Girl',
},
'playlist_mincount': 18,
}, {
'url': 'https://eggs.mu/artist/KAMO_3pband',
'info_dict': {
'id': 'KAMO_3pband',
'description': '川崎発３ピースバンド',
'thumbnail': 'https://image-pro.eggs.mu/profile/35217.jpeg?updated_at=2024-11-27T16%3A31%3A50%2B09%3A00',
'title': 'KAMO',
},
'playlist_mincount': 2,
}]
def _real_extract(self, url):
artist_id = self._match_id(url)
artist_data = self._call_api(f'artists/{artist_id}', artist_id)
song_data = self._call_api(f'artists/{artist_id}/musics', artist_id)
return self.playlist_result(
traverse_obj(song_data, ('data', ..., {dict}, {self._extract_music_info})),
playlist_id=artist_id, **traverse_obj(artist_data, {
'title': ('displayName', {str}),
'description': ('profile', {str}),
'thumbnail': ('imageDataPath', {url_or_none}),
}))

5
yt_dlp/extractor/firsttv.py
View File

@ -12,7 +12,7 @@
class FirstTVIE(InfoExtractor):
IE_NAME = '1tv'
IE_DESC = 'Первый канал'
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?:sport)?1tv\.ru/(?:[^/?#]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# single format
@ -52,6 +52,9 @@ class FirstTVIE(InfoExtractor):
}, {
'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
'only_matching': True,
}, {
'url': 'https://www.sport1tv.ru/sport/chempionat-rossii-po-figurnomu-kataniyu-2025',
'only_matching': True,
}]
def _real_extract(self, url):

349
yt_dlp/extractor/funimation.py
View File

@ -1,349 +0,0 @@
import random
import re
import string
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
join_nonempty,
js_to_json,
make_archive_id,
orderedSet,
qualities,
str_or_none,
traverse_obj,
try_get,
urlencode_postdata,
)
class FunimationBaseIE(InfoExtractor):
_NETRC_MACHINE = 'funimation'
_REGION = None
_TOKEN = None
def _get_region(self):
region_cookie = self._get_cookies('https://www.funimation.com').get('region')
region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
return region or traverse_obj(
self._download_json(
'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
note='Checking geo-location', errnote='Unable to fetch geo-location information'),
'region') or 'US'
def _perform_login(self, username, password):
if self._TOKEN:
return
try:
data = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
None, 'Logging in', data=urlencode_postdata({
'username': username,
'password': password,
}))
FunimationBaseIE._TOKEN = data['token']
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
error = self._parse_json(e.cause.response.read().decode(), None)['error']
raise ExtractorError(error, expected=True)
raise
class FunimationPageIE(FunimationBaseIE):
IE_NAME = 'funimation:page'
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
'info_dict': {
'id': '210050',
'ext': 'mp4',
'title': 'Broadcast Dub Preview',
# Other metadata is tested in FunimationIE
},
'params': {
'skip_download': 'm3u8',
},
'add_ie': ['Funimation'],
}, {
# Not available in US
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
'only_matching': True,
}, {
# with lang code
'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
'only_matching': True,
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
}, {
'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
'only_matching': True,
}]
def _real_initialize(self):
if not self._REGION:
FunimationBaseIE._REGION = self._get_region()
def _real_extract(self, url):
locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')
video_id = traverse_obj(self._download_json(
f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
f'{show}_{episode}', query={
'deviceType': 'web',
'region': self._REGION,
'locale': locale or 'en',
}), ('videoList', ..., 'id'), get_all=False)
return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)
class FunimationIE(FunimationBaseIE):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.funimation.com/player/210051',
'info_dict': {
'id': '210050',
'display_id': 'broadcast-dub-preview',
'ext': 'mp4',
'title': 'Broadcast Dub Preview',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
'episode': 'Broadcast Dub Preview',
'episode_id': '210050',
'season': 'Extras',
'season_id': '166038',
'season_number': 99,
'series': 'Attack on Titan: Junior High',
'description': '',
'duration': 155,
},
'params': {
'skip_download': 'm3u8',
},
}, {
'note': 'player_id should be extracted with the relevent compat-opt',
'url': 'https://www.funimation.com/player/210051',
'info_dict': {
'id': '210051',
'display_id': 'broadcast-dub-preview',
'ext': 'mp4',
'title': 'Broadcast Dub Preview',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
'episode': 'Broadcast Dub Preview',
'episode_id': '210050',
'season': 'Extras',
'season_id': '166038',
'season_number': 99,
'series': 'Attack on Titan: Junior High',
'description': '',
'duration': 155,
},
'params': {
'skip_download': 'm3u8',
'compat_opts': ['seperate-video-versions'],
},
}]
@staticmethod
def _get_experiences(episode):
for lang, lang_data in episode.get('languages', {}).items():
for video_data in lang_data.values():
for version, f in video_data.items():
yield lang, version.title(), f
def _get_episode(self, webpage, experience_id=None, episode_id=None, fatal=True):
""" Extract the episode, season and show objects given either episode/experience id """
show = self._parse_json(
self._search_regex(
r'show\s*=\s*({.+?})\s*;', webpage, 'show data', fatal=fatal),
experience_id, transform_source=js_to_json, fatal=fatal) or []
for season in show.get('seasons', []):
for episode in season.get('episodes', []):
if episode_id is not None:
if str(episode.get('episodePk')) == episode_id:
return episode, season, show
continue
for _, _, f in self._get_experiences(episode):
if f.get('experienceId') == experience_id:
return episode, season, show
if fatal:
raise ExtractorError('Unable to find episode information')
else:
self.report_warning('Unable to find episode information')
return {}, {}, {}
def _real_extract(self, url):
initial_experience_id = self._match_id(url)
webpage = self._download_webpage(
url, initial_experience_id, note=f'Downloading player webpage for {initial_experience_id}')
episode, season, show = self._get_episode(webpage, experience_id=int(initial_experience_id))
episode_id = str(episode['episodePk'])
display_id = episode.get('slug') or episode_id
formats, subtitles, thumbnails, duration = [], {}, [], 0
requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
language_preference = qualities((requested_languages or [''])[::-1])
source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])
for lang, version, fmt in self._get_experiences(episode):
experience_id = str(fmt['experienceId'])
if ((only_initial_experience and experience_id != initial_experience_id)
or (requested_languages and lang.lower() not in requested_languages)
or (requested_versions and version.lower() not in requested_versions)):
continue
thumbnails.append({'url': fmt.get('poster')})
duration = max(duration, fmt.get('duration', 0))
format_name = f'{version} {lang} ({experience_id})'
self.extract_subtitles(
subtitles, experience_id, display_id=display_id, format_name=format_name,
episode=episode if experience_id == initial_experience_id else episode_id)
headers = {}
if self._TOKEN:
headers['Authorization'] = f'Token {self._TOKEN}'
page = self._download_json(
f'https://www.funimation.com/api/showexperience/{experience_id}/',
display_id, headers=headers, expected_status=403, query={
'pinst_id': ''.join(random.choices(string.digits + string.ascii_letters, k=8)),
}, note=f'Downloading {format_name} JSON')
sources = page.get('items') or []
if not sources:
error = try_get(page, lambda x: x['errors'][0], dict)
if error:
self.report_warning('{} said: Error {} - {}'.format(
self.IE_NAME, error.get('code'), error.get('detail') or error.get('title')))
else:
self.report_warning('No sources found for format')
current_formats = []
for source in sources:
source_url = source.get('src')
source_type = source.get('videoType') or determine_ext(source_url)
if source_type == 'm3u8':
current_formats.extend(self._extract_m3u8_formats(
source_url, display_id, 'mp4', m3u8_id='{}-{}'.format(experience_id, 'hls'), fatal=False,
note=f'Downloading {format_name} m3u8 information'))
else:
current_formats.append({
'format_id': f'{experience_id}-{source_type}',
'url': source_url,
})
for f in current_formats:
# TODO: Convert language to code
f.update({
'language': lang,
'format_note': version,
'source_preference': source_preference(version.lower()),
'language_preference': language_preference(lang.lower()),
})
formats.extend(current_formats)
if not formats and (requested_languages or requested_versions):
self.raise_no_formats(
'There are no video formats matching the requested languages/versions', expected=True, video_id=display_id)
self._remove_duplicate_formats(formats)
return {
'id': episode_id,
'_old_archive_ids': [make_archive_id(self, initial_experience_id)],
'display_id': display_id,
'duration': duration,
'title': episode['episodeTitle'],
'description': episode.get('episodeSummary'),
'episode': episode.get('episodeTitle'),
'episode_number': int_or_none(episode.get('episodeId')),
'episode_id': episode_id,
'season': season.get('seasonTitle'),
'season_number': int_or_none(season.get('seasonId')),
'season_id': str_or_none(season.get('seasonPk')),
'series': show.get('showTitle'),
'formats': formats,
'thumbnails': thumbnails,
'subtitles': subtitles,
'_format_sort_fields': ('lang', 'source'),
}
def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
if isinstance(episode, str):
webpage = self._download_webpage(
f'https://www.funimation.com/player/{experience_id}/', display_id,
fatal=False, note=f'Downloading player webpage for {format_name}')
episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)
for _, version, f in self._get_experiences(episode):
for source in f.get('sources'):
for text_track in source.get('textTracks'):
if not text_track.get('src'):
continue
sub_type = text_track.get('type').upper()
sub_type = sub_type if sub_type != 'FULL' else None
current_sub = {
'url': text_track['src'],
'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' '),
}
lang = join_nonempty(text_track.get('language', 'und'),
version if version != 'Simulcast' else None,
sub_type, delim='_')
if current_sub not in subtitles.get(lang, []):
subtitles.setdefault(lang, []).append(current_sub)
return subtitles
class FunimationShowIE(FunimationBaseIE):
IE_NAME = 'funimation:show'
_VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.funimation.com/en/shows/sk8-the-infinity',
'info_dict': {
'id': '1315000',
'title': 'SK8 the Infinity',
},
'playlist_count': 13,
'params': {
'skip_download': True,
},
}, {
# without lang code
'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/',
'info_dict': {
'id': '39643',
'title': 'Ouran High School Host Club',
},
'playlist_count': 26,
'params': {
'skip_download': True,
},
}]
def _real_initialize(self):
if not self._REGION:
FunimationBaseIE._REGION = self._get_region()
def _real_extract(self, url):
base_url, locale, display_id = self._match_valid_url(url).groups()
show_info = self._download_json(
'https://title-api.prd.funimationsvc.com/v2/shows/{}?region={}&deviceType=web&locale={}'.format(
display_id, self._REGION, locale or 'en'), display_id)
items_info = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id={}'.format(
show_info.get('id')), display_id)
vod_items = traverse_obj(items_info, ('items', ..., lambda k, _: re.match(r'(?i)mostRecent[AS]vod', k), 'item'))
return {
'_type': 'playlist',
'id': str_or_none(show_info['id']),
'title': show_info['name'],
'entries': orderedSet(
self.url_result(
'{}/{}'.format(base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
vod_item.get('episodeId'), vod_item.get('episodeName'))
for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
}

58
yt_dlp/extractor/goodgame.py
View File

@ -1,40 +1,48 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
str_or_none,
traverse_obj,
url_or_none,
)
class GoodGameIE(InfoExtractor):
IE_NAME = 'goodgame:stream'
_VALID_URL = r'https?://goodgame\.ru/channel/(?P<id>\w+)'
_VALID_URL = r'https?://goodgame\.ru/(?!channel/)(?P<id>[\w.*-]+)'
_TESTS = [{
'url': 'https://goodgame.ru/channel/Pomi/#autoplay',
'url': 'https://goodgame.ru/TGW#autoplay',
'info_dict': {
'id': 'pomi',
'id': '7998',
'ext': 'mp4',
'title': r're:Reynor vs Special \(1/2,bo3\) Wardi Spring EU \- playoff \(финальный день\) \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'channel_id': '1644',
'channel': 'Pomi',
'channel_url': 'https://goodgame.ru/channel/Pomi/',
'description': 'md5:4a87b775ee7b2b57bdccebe285bbe171',
'thumbnail': r're:^https?://.*\.jpg$',
'channel_id': '7998',
'title': r're:шоуматч Happy \(NE\) vs Fortitude \(UD\), потом ладдер и дс \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'channel_url': 'https://goodgame.ru/TGW',
'thumbnail': 'https://hls.goodgame.ru/previews/7998_240.jpg',
'uploader': 'TGW',
'channel': 'JosephStalin',
'live_status': 'is_live',
'view_count': int,
'age_limit': 18,
'channel_follower_count': int,
'uploader_id': '2899',
'concurrent_view_count': int,
},
'params': {'skip_download': 'm3u8'},
'skip': 'May not be online',
}, {
'url': 'https://goodgame.ru/Mr.Gray',
'only_matching': True,
}, {
'url': 'https://goodgame.ru/HeDoPa3yMeHue*',
'only_matching': True,
}]
def _real_extract(self, url):
channel_name = self._match_id(url)
response = self._download_json(f'https://api2.goodgame.ru/v2/streams/{channel_name}', channel_name)
player_id = response['channel']['gg_player_src']
response = self._download_json(f'https://goodgame.ru/api/4/users/{channel_name}/stream', channel_name)
player_id = response['streamkey']
formats, subtitles = [], {}
if response.get('status') == 'Live':
if response.get('status'):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://hls.goodgame.ru/manifest/{player_id}_master.m3u8',
channel_name, 'mp4', live=True)
@ -45,13 +53,17 @@ def _real_extract(self, url):
'id': player_id,
'formats': formats,
'subtitles': subtitles,
'title': traverse_obj(response, ('channel', 'title')),
'channel': channel_name,
'channel_id': str_or_none(traverse_obj(response, ('channel', 'id'))),
'channel_url': response.get('url'),
'description': clean_html(traverse_obj(response, ('channel', 'description'))),
'thumbnail': traverse_obj(response, ('channel', 'thumb')),
'is_live': bool(formats),
'view_count': int_or_none(response.get('viewers')),
'age_limit': 18 if traverse_obj(response, ('channel', 'adult')) else None,
**traverse_obj(response, {
'title': ('title', {str}),
'channel': ('channelkey', {str}),
'channel_id': ('id', {str_or_none}),
'channel_url': ('link', {url_or_none}),
'uploader': ('streamer', 'username', {str}),
'uploader_id': ('streamer', 'id', {str_or_none}),
'thumbnail': ('preview', {url_or_none}, {self._proto_relative_url}),
'concurrent_view_count': ('viewers', {int_or_none}),
'channel_follower_count': ('followers', {int_or_none}),
'age_limit': ('adult', {bool}, {lambda x: 18 if x else None}),
}),
}

4
yt_dlp/extractor/laracasts.py
View File

@ -39,7 +39,7 @@ def _parse_episode(self, episode):
'description': ('body', {clean_html}),
'thumbnail': ('largeThumbnail', {url_or_none}),
'duration': ('length', {int_or_none}),
'date': ('dateSegments', 'published', {unified_strdate}),
'upload_date': ('dateSegments', 'published', {unified_strdate}),
}))
@ -54,7 +54,7 @@ class LaracastsIE(LaracastsBaseIE):
'title': 'Hello, Laravel',
'ext': 'mp4',
'duration': 519,
'date': '20240312',
'upload_date': '20240312',
'thumbnail': 'https://laracasts.s3.amazonaws.com/videos/thumbnails/youtube/30-days-to-learn-laravel-11-1.png',
'description': 'md5:ddd658bb241975871d236555657e1dd1',
'season_number': 1,

8
yt_dlp/extractor/lbry.py
View File

@ -310,7 +310,13 @@ def _real_extract(self, url):
if stream_type in self._SUPPORTED_STREAM_TYPES:
claim_id, is_live = result['claim_id'], False
streaming_url = self._call_api_proxy(
'get', claim_id, {'uri': uri}, 'streaming url')['streaming_url']
'get', claim_id, {
'uri': uri,
**traverse_obj(parse_qs(url), {
'signature': ('signature', 0),
'signature_ts': ('signature_ts', 0),
}),
}, 'streaming url')['streaming_url']
# GET request to v3 API returns original video/audio file if available
direct_url = re.sub(r'/api/v\d+/', '/api/v3/', streaming_url)

21
yt_dlp/extractor/naver.py
View File

@ -72,6 +72,7 @@ def extract_formats(streams, stream_type, query={}):
'abr': int_or_none(bitrate.get('audio')),
'filesize': int_or_none(stream.get('size')),
'protocol': 'm3u8_native' if stream_type == 'HLS' else None,
'extra_param_to_segment_url': urllib.parse.urlencode(query, doseq=True) if stream_type == 'HLS' else None,
})
extract_formats(get_list('video'), 'H264')
@ -168,6 +169,26 @@ class NaverIE(NaverBaseIE):
'duration': 277,
'thumbnail': r're:^https?://.*\.jpg',
},
}, {
'url': 'https://tv.naver.com/v/67838091',
'md5': '126ea384ab033bca59672c12cca7a6be',
'info_dict': {
'id': '67838091',
'ext': 'mp4',
'title': '[라인W 날씨] 내일 아침 서울 체감 -19도…호남·충남 대설',
'description': 'md5:fe026e25634c85845698aed4b59db5a7',
'timestamp': 1736347853,
'upload_date': '20250108',
'uploader': 'KBS뉴스',
'uploader_id': 'kbsnews',
'uploader_url': 'https://tv.naver.com/kbsnews',
'view_count': int,
'like_count': int,
'comment_count': int,
'duration': 69,
'thumbnail': r're:^https?://.*\.jpg',
},
'params': {'format': 'HLS_144P'},
}, {
'url': 'http://tvcast.naver.com/v/81652',
'only_matching': True,

117
yt_dlp/extractor/nest.py Normal file
View File

@ -0,0 +1,117 @@
from .common import InfoExtractor
from ..utils import ExtractorError, float_or_none, update_url_query, url_or_none
from ..utils.traversal import traverse_obj
class NestIE(InfoExtractor):
_VALID_URL = r'https?://video\.nest\.com/(?:embedded/)?live/(?P<id>\w+)'
_EMBED_REGEX = [rf'<iframe [^>]*\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://video.nest.com/embedded/live/4fvYdSo8AX?autoplay=0',
'info_dict': {
'id': '4fvYdSo8AX',
'ext': 'mp4',
'title': 'startswith:Outside ',
'alt_title': 'Outside',
'description': '<null>',
'location': 'Los Angeles',
'availability': 'public',
'thumbnail': r're:https?://',
'live_status': 'is_live',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://video.nest.com/live/4fvYdSo8AX',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.pacificblue.biz/noyo-harbor-webcam/',
'info_dict': {
'id': '4fvYdSo8AX',
'ext': 'mp4',
'title': 'startswith:Outside ',
'alt_title': 'Outside',
'description': '<null>',
'location': 'Los Angeles',
'availability': 'public',
'thumbnail': r're:https?://',
'live_status': 'is_live',
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
item = self._download_json(
'https://video.nest.com/api/dropcam/cameras.get_by_public_token',
video_id, query={'token': video_id})['items'][0]
uuid = item.get('uuid')
stream_domain = item.get('live_stream_host')
if not stream_domain or not uuid:
raise ExtractorError('Unable to construct playlist URL')
thumb_domain = item.get('nexus_api_nest_domain_host')
return {
'id': video_id,
**traverse_obj(item, {
'description': ('description', {str}),
'title': (('title', 'name', 'where'), {str}, filter, any),
'alt_title': ('name', {str}),
'location': ((('timezone', {lambda x: x.split('/')[1].replace('_', ' ')}), 'where'), {str}, filter, any),
}),
'thumbnail': update_url_query(
f'https://{thumb_domain}/get_image',
{'uuid': uuid, 'public': video_id}) if thumb_domain else None,
'availability': self._availability(is_private=item.get('is_public') is False),
'formats': self._extract_m3u8_formats(
f'https://{stream_domain}/nexus_aac/{uuid}/playlist.m3u8',
video_id, 'mp4', live=True, query={'public': video_id}),
'is_live': True,
}
class NestClipIE(InfoExtractor):
_VALID_URL = r'https?://video\.nest\.com/(?:embedded/)?clip/(?P<id>\w+)'
_EMBED_REGEX = [rf'<iframe [^>]*\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://video.nest.com/clip/f34c9dd237a44eca9a0001af685e3dff',
'info_dict': {
'id': 'f34c9dd237a44eca9a0001af685e3dff',
'ext': 'mp4',
'title': 'NestClip video #f34c9dd237a44eca9a0001af685e3dff',
'thumbnail': 'https://clips.dropcam.com/f34c9dd237a44eca9a0001af685e3dff.jpg',
'timestamp': 1735413474.468,
'upload_date': '20241228',
},
}, {
'url': 'https://video.nest.com/embedded/clip/34e0432adc3c46a98529443d8ad5aa76',
'info_dict': {
'id': '34e0432adc3c46a98529443d8ad5aa76',
'ext': 'mp4',
'title': 'Shootout at Veterans Boulevard at Fleur De Lis Drive',
'thumbnail': 'https://clips.dropcam.com/34e0432adc3c46a98529443d8ad5aa76.jpg',
'upload_date': '20230817',
'timestamp': 1692262897.191,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://video.nest.com/api/dropcam/videos.get_by_filename', video_id,
query={'filename': f'{video_id}.mp4'})
return {
'id': video_id,
**traverse_obj(data, ('items', 0, {
'title': ('title', {str}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'url': ('download_url', {url_or_none}),
'timestamp': ('start_time', {float_or_none}),
})),
}

34
yt_dlp/extractor/niconico.py
View File

@ -592,8 +592,8 @@ def _call_api(self, list_id, resource, query):
@staticmethod
def _parse_owner(item):
return {
'uploader': traverse_obj(item, ('owner', 'name')),
'uploader_id': traverse_obj(item, ('owner', 'id')),
'uploader': traverse_obj(item, ('owner', ('name', ('user', 'nickname')), {str}, any)),
'uploader_id': traverse_obj(item, ('owner', 'id', {str})),
}
def _fetch_page(self, list_id, page):
@ -666,7 +666,7 @@ def _real_extract(self, url):
mylist.get('name'), mylist.get('description'), **self._parse_owner(mylist))
class NiconicoSeriesIE(InfoExtractor):
class NiconicoSeriesIE(NiconicoPlaylistBaseIE):
IE_NAME = 'niconico:series'
_VALID_URL = r'https?://(?:(?:www\.|sp\.)?nicovideo\.jp(?:/user/\d+)?|nico\.ms)/series/(?P<id>\d+)'
@ -675,6 +675,9 @@ class NiconicoSeriesIE(InfoExtractor):
'info_dict': {
'id': '110226',
'title': 'ご立派ァ！のシリーズ',
'description': '楽しそうな外人の吹き替えをさせたら終身名誉ホモガキの右に出る人はいませんね…',
'uploader': 'アルファるふぁ',
'uploader_id': '44113208',
},
'playlist_mincount': 10,
}, {
@ -682,6 +685,9 @@ class NiconicoSeriesIE(InfoExtractor):
'info_dict': {
'id': '12312',
'title': 'バトルスピリッツ　お勧めカード紹介(調整中)',
'description': '',
'uploader': '野鳥',
'uploader_id': '2275360',
},
'playlist_mincount': 103,
}, {
@ -689,19 +695,21 @@ class NiconicoSeriesIE(InfoExtractor):
'only_matching': True,
}]
def _call_api(self, list_id, resource, query):
return self._download_json(
f'https://nvapi.nicovideo.jp/v2/series/{list_id}', list_id,
f'Downloading {resource}', query=query,
headers=self._API_HEADERS)['data']
def _real_extract(self, url):
list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id)
series = self._call_api(list_id, 'list', {
'pageSize': 1,
})['detail']
title = self._search_regex(
(r'<title>「(.+)（全',
r'<div class="TwitterShareButton"\s+data-text="(.+)\s+https:'),
webpage, 'title', fatal=False)
if title:
title = unescapeHTML(title)
json_data = next(self._yield_json_ld(webpage, None, fatal=False))
return self.playlist_from_matches(
traverse_obj(json_data, ('itemListElement', ..., 'url')), list_id, title, ie=NiconicoIE)
return self.playlist_result(
self._entries(list_id), list_id,
series.get('title'), series.get('description'), **self._parse_owner(series))
class NiconicoHistoryIE(NiconicoPlaylistBaseIE):

38
yt_dlp/extractor/nrk.py
View File

@ -12,6 +12,7 @@
parse_iso8601,
str_or_none,
try_get,
update_url_query,
url_or_none,
urljoin,
)
@ -27,6 +28,12 @@ class NRKBaseIE(InfoExtractor):
)/'''
def _extract_nrk_formats(self, asset_url, video_id):
asset_url = update_url_query(asset_url, {
# Remove 'adap' to return all streams (known values are: small, large, small_h265, large_h265)
'adap': [],
# Disable subtitles since they are fetched separately
's': 0,
})
if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
return self._extract_akamai_formats(asset_url, video_id)
asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
@ -58,7 +65,10 @@ def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None
return self._download_json(
urljoin('https://psapi.nrk.no/', path),
video_id, note or f'Downloading {item} JSON',
fatal=fatal, query=query)
fatal=fatal, query=query, headers={
# Needed for working stream URLs, see https://github.com/yt-dlp/yt-dlp/issues/12192
'Accept': 'application/vnd.nrk.psapi+json; version=9; player=tv-player; device=player-core',
})
class NRKIE(NRKBaseIE):
@ -77,13 +87,17 @@ class NRKIE(NRKBaseIE):
_TESTS = [{
# video
'url': 'http://www.nrk.no/video/PS*150533',
'md5': 'f46be075326e23ad0e524edfcb06aeb6',
'md5': '2b88a652ad2e275591e61cf550887eec',
'info_dict': {
'id': '150533',
'ext': 'mp4',
'title': 'Dompap og andre fugler i Piip-Show',
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
'duration': 262,
'upload_date': '20140325',
'thumbnail': r're:^https?://gfx\.nrk\.no/.*$',
'timestamp': 1395751833,
'alt_title': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
},
}, {
# audio
@ -95,6 +109,10 @@ class NRKIE(NRKBaseIE):
'title': 'Slik høres internett ut når du er blind',
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
'duration': 20,
'timestamp': 1398429565,
'alt_title': 'Cathrine Lie Wathne er blind, og bruker hurtigtaster for å navigere seg rundt på ulike nettsider.',
'thumbnail': 'https://gfx.nrk.no/urxQMSXF-WnbfjBH5ke2igLGyN27EdJVWZ6FOsEAclhA',
'upload_date': '20140425',
},
}, {
'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
@ -152,7 +170,7 @@ def call_playback_api(item, query=None):
return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query)
raise
# known values for preferredCdn: akamai, iponly, minicdn and telenor
# known values for preferredCdn: akamai, globalconnect and telenor
manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
video_id = try_get(manifest, lambda x: x['id'], str) or video_id
@ -307,6 +325,13 @@ class NRKTVIE(InfoExtractor):
'ext': 'vtt',
}],
},
'upload_date': '20170627',
'timestamp': 1498591822,
'thumbnail': 'https://gfx.nrk.no/myRSc4vuFlahB60P3n6swwRTQUZI1LqJZl9B7icZFgzA',
'alt_title': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
@ -321,6 +346,13 @@ class NRKTVIE(InfoExtractor):
'series': '20 spørsmål',
'episode': '23. mai 2014',
'age_limit': 0,
'timestamp': 1584593700,
'thumbnail': 'https://gfx.nrk.no/u7uCe79SEfPVGRAGVp2_uAZnNc4mfz_kjXg6Bgek8lMQ',
'season_id': '126936',
'upload_date': '20200319',
'season': 'Season 2014',
'season_number': 2014,
'episode_number': 3,
},
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',

4
yt_dlp/extractor/patreon.py
View File

@ -63,6 +63,7 @@ class PatreonIE(PatreonBaseIE):
'info_dict': {
'id': '743933',
'ext': 'mp3',
'alt_title': 'cd166.mp3',
'title': 'Episode 166: David Smalley of Dogma Debate',
'description': 'md5:34d207dd29aa90e24f1b3f58841b81c7',
'uploader': 'Cognitive Dissonance Podcast',
@ -280,7 +281,7 @@ def _real_extract(self, url):
video_id = self._match_id(url)
post = self._call_api(
f'posts/{video_id}', video_id, query={
'fields[media]': 'download_url,mimetype,size_bytes',
'fields[media]': 'download_url,mimetype,size_bytes,file_name',
'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title,current_user_can_view',
'fields[user]': 'full_name,url',
'fields[post_tag]': 'value',
@ -317,6 +318,7 @@ def _real_extract(self, url):
'ext': ext,
'filesize': size_bytes,
'url': download_url,
'alt_title': traverse_obj(media_attributes, ('file_name', {str})),
})
elif include_type == 'user':

58
yt_dlp/extractor/pbs.py
View File

@ -47,7 +47,7 @@ class PBSIE(InfoExtractor):
(r'video\.kpbs\.org', 'KPBS San Diego (KPBS)'), # http://www.kpbs.org/
(r'video\.kqed\.org', 'KQED (KQED)'), # http://www.kqed.org
(r'vids\.kvie\.org', 'KVIE Public Television (KVIE)'), # http://www.kvie.org
(r'video\.pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/
(r'(?:video\.|www\.)pbssocal\.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/
(r'video\.valleypbs\.org', 'ValleyPBS (KVPT)'), # http://www.valleypbs.org/
(r'video\.cptv\.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'), # http://cptv.org
(r'watch\.knpb\.org', 'KNPB Channel 5 (KNPB)'), # http://www.knpb.org/
@ -61,7 +61,7 @@ class PBSIE(InfoExtractor):
(r'video\.wyomingpbs\.org', 'Wyoming PBS (KCWC)'), # http://www.wyomingpbs.org
(r'video\.cpt12\.org', 'Colorado Public Television / KBDI 12 (KBDI)'), # http://www.cpt12.org/
(r'video\.kbyueleven\.org', 'KBYU-TV (KBYU)'), # http://www.kbyutv.org/
(r'video\.thirteen\.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org
(r'(?:video\.|www\.)thirteen\.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org
(r'video\.wgbh\.org', 'WGBH/Channel 2 (WGBH)'), # http://wgbh.org
(r'video\.wgby\.org', 'WGBY (WGBY)'), # http://www.wgby.org
(r'watch\.njtvonline\.org', 'NJTV Public Media NJ (WNJT)'), # http://www.njtvonline.org/
@ -185,12 +185,13 @@ class PBSIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://
(?:
# Direct video URL
(?:{})/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
# Article with embedded player (or direct video)
(?:www\.)?pbs\.org/(?:[^/]+/){{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)
# Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/?#]+) |
# Direct video URL, or article with embedded player
(?:{})/(?:
(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/#]|$) |
(?:[^/?#]+/){{1,5}}(?P<presumptive_id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])
)
)
'''.format('|'.join(next(zip(*_STATIONS))))
@ -207,16 +208,40 @@ class PBSIE(InfoExtractor):
'description': 'md5:31b664af3c65fd07fa460d306b837d00',
'duration': 3190,
},
'skip': 'dead URL',
},
{
'url': 'https://www.thirteen.org/programs/the-woodwrights-shop/carving-away-with-mary-may-tioglz/',
'info_dict': {
'id': '3004803331',
'ext': 'mp4',
'title': "The Woodwright's Shop - Carving Away with Mary May",
'description': 'md5:7cbaaaa8b9bcc78bd8f0e31911644e28',
'duration': 1606,
'display_id': 'carving-away-with-mary-may-tioglz',
'chapters': [],
'thumbnail': 'https://image.pbs.org/video-assets/NcnTxNl-asset-mezzanine-16x9-K0Keoyv.jpg',
},
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
'md5': '6f722cb3c3982186d34b0f13374499c7',
'md5': '372b12b670070de39438b946474df92f',
'info_dict': {
'id': '2365297690',
'ext': 'mp4',
'title': 'FRONTLINE - Losing Iraq',
'description': 'md5:5979a4d069b157f622d02bff62fbe654',
'duration': 5050,
'chapters': [
{'start_time': 0.0, 'end_time': 1234.0, 'title': 'After Saddam, Chaos'},
{'start_time': 1233.0, 'end_time': 1719.0, 'title': 'The Insurgency Takes Root'},
{'start_time': 1718.0, 'end_time': 2461.0, 'title': 'A Light Footprint'},
{'start_time': 2460.0, 'end_time': 3589.0, 'title': 'The Surge '},
{'start_time': 3588.0, 'end_time': 4355.0, 'title': 'The Withdrawal '},
{'start_time': 4354.0, 'end_time': 5051.0, 'title': 'ISIS on the March '},
],
'display_id': 'losing-iraq',
'thumbnail': 'https://image.pbs.org/video-assets/pbs/frontline/138098/images/mezzanine_401.jpg',
},
},
{
@ -403,6 +428,19 @@ class PBSIE(InfoExtractor):
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
},
{
'url': 'https://www.pbssocal.org/shows/newshour/clip/capehart-johnson-1715984001',
'info_dict': {
'id': '3091549094',
'ext': 'mp4',
'title': 'PBS NewsHour - Capehart and Johnson on the unusual Biden-Trump debate plans',
'description': 'Capehart and Johnson on how the Biden-Trump debates could shape the campaign season',
'display_id': 'capehart-johnson-1715984001',
'duration': 593,
'thumbnail': 'https://image.pbs.org/video-assets/mF3oSVn-asset-mezzanine-16x9-QeXjXPy.jpg',
'chapters': [],
},
},
{
'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
'only_matching': True,
@ -463,10 +501,12 @@ def _extract_webpage(self, url):
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer
r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
r'\bclass="passportcoveplayer"[^>]+\bdata-media="(\d+)', # https://www.thirteen.org/programs/the-woodwrights-shop/who-wrote-the-book-of-sloyd-fggvvq/
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)', # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/
r'\bhttps?://player\.pbs\.org/[\w-]+player/(\d+)', # last pattern to avoid false positives
]
media_id = self._search_regex(

99
yt_dlp/extractor/piramidetv.py Normal file
View File

@ -0,0 +1,99 @@
from .common import InfoExtractor
from ..utils import parse_iso8601, smuggle_url, unsmuggle_url, url_or_none
from ..utils.traversal import traverse_obj
class PiramideTVIE(InfoExtractor):
_VALID_URL = r'https?://piramide\.tv/video/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://piramide.tv/video/wWtBAORdJUTh',
'info_dict': {
'id': 'wWtBAORdJUTh',
'ext': 'mp4',
'title': 'md5:79f9c8183ea6a35c836923142cf0abcc',
'description': '',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/W86PgQDn/thumbnails/B9gpIxkH.jpg',
'channel': 'León Picarón',
'channel_id': 'leonpicaron',
'timestamp': 1696460362,
'upload_date': '20231004',
},
}, {
'url': 'https://piramide.tv/video/wcYn6li79NgN',
'info_dict': {
'id': 'wcYn6li79NgN',
'ext': 'mp4',
'title': 'ACEPTO TENER UN BEBE CON MI NOVIA\u2026? | Parte 1',
'description': '',
'channel': 'ARTA GAME',
'channel_id': 'arta_game',
'thumbnail': 'https://cdn.jwplayer.com/v2/media/cnEdGp5X/thumbnails/rHAaWfP7.jpg',
'timestamp': 1703434976,
'upload_date': '20231224',
},
}]
def _extract_video(self, video_id):
video_data = self._download_json(
f'https://hermes.piramide.tv/video/data/{video_id}', video_id, fatal=False)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://cdn.piramide.tv/video/{video_id}/manifest.m3u8', video_id, fatal=False)
next_video = traverse_obj(video_data, ('video', 'next_video', 'id', {str}))
return next_video, {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(video_data, ('video', {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('media', 'thumbnail', {url_or_none}),
'channel': ('channel', 'name', {str}),
'channel_id': ('channel', 'id', {str}),
'timestamp': ('date', {parse_iso8601}),
})),
}
def _entries(self, video_id):
visited = set()
while True:
visited.add(video_id)
next_video, info = self._extract_video(video_id)
yield info
if not next_video or next_video in visited:
break
video_id = next_video
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
if self._yes_playlist(video_id, video_id, smuggled_data):
return self.playlist_result(self._entries(video_id), video_id)
return self._extract_video(video_id)[1]
class PiramideTVChannelIE(InfoExtractor):
_VALID_URL = r'https?://piramide\.tv/channel/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://piramide.tv/channel/thekalo',
'playlist_mincount': 10,
'info_dict': {
'id': 'thekalo',
},
}]
def _entries(self, channel_name):
videos = self._download_json(
f'https://hermes.piramide.tv/channel/list/{channel_name}/date/100000', channel_name)
for video in traverse_obj(videos, ('videos', lambda _, v: v['id'])):
yield self.url_result(smuggle_url(
f'https://piramide.tv/video/{video["id"]}', {'force_noplaylist': True}),
**traverse_obj(video, {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
}))
def _real_extract(self, url):
channel_name = self._match_id(url)
return self.playlist_result(self._entries(channel_name), channel_name)

6
yt_dlp/extractor/plvideo.py
View File

@ -26,7 +26,7 @@ class PlVideoIE(InfoExtractor):
'comment_count': int,
'tags': ['rusia', 'cuba', 'russia', 'miguel díaz-canel'],
'description': 'md5:a1a395d900d77a86542a91ee0826c115',
'released_timestamp': 1715096124,
'release_timestamp': 1715096124,
'channel_is_verified': True,
'like_count': int,
'timestamp': 1715095911,
@ -62,7 +62,7 @@ class PlVideoIE(InfoExtractor):
'title': 'Белоусов отменил приказы о кадровом резерве на гражданской службе',
'channel_follower_count': int,
'view_count': int,
'released_timestamp': 1732961458,
'release_timestamp': 1732961458,
},
}]
@ -119,7 +119,7 @@ def _real_extract(self, url):
'channel_is_verified': ('channel', 'verified', {bool}),
'tags': ('tags', ..., {str}),
'timestamp': ('createdAt', {parse_iso8601}),
'released_timestamp': ('publishedAt', {parse_iso8601}),
'release_timestamp': ('publishedAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
'view_count': ('stats', 'viewTotalCount', {int_or_none}),
'like_count': ('stats', 'likeCount', {int_or_none}),

18
yt_dlp/extractor/redgifs.py
View File

@ -114,7 +114,7 @@ def _paged_entries(self, ep, item_id, query, fields):
class RedGifsIE(RedGifsBaseInfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?redgifs\.com/watch/|thumbs2\.redgifs\.com/)(?P<id>[^-/?#\.]+)'
_VALID_URL = r'https?://(?:(?:www\.)?redgifs\.com/(?:watch|ifr)/|thumbs2\.redgifs\.com/)(?P<id>[^-/?#\.]+)'
_TESTS = [{
'url': 'https://www.redgifs.com/watch/squeakyhelplesswisent',
'info_dict': {
@ -147,6 +147,22 @@ class RedGifsIE(RedGifsBaseInfoExtractor):
'age_limit': 18,
'tags': list,
},
}, {
'url': 'https://www.redgifs.com/ifr/squeakyhelplesswisent',
'info_dict': {
'id': 'squeakyhelplesswisent',
'ext': 'mp4',
'title': 'Hotwife Legs Thick',
'timestamp': 1636287915,
'upload_date': '20211107',
'uploader': 'ignored52',
'duration': 16,
'view_count': int,
'like_count': int,
'categories': list,
'age_limit': 18,
'tags': list,
},
}]
def _real_extract(self, url):

7
yt_dlp/extractor/rtvslo.py
View File

@ -176,6 +176,8 @@ class RTVSLOShowIE(InfoExtractor):
'info_dict': {
'id': '173250997',
'title': 'Ekipa Bled',
'description': 'md5:c88471e27a1268c448747a5325319ab7',
'thumbnail': 'https://img.rtvcdn.si/_up/ava/ava_misc/show_logos/173250997/logo_wide1.jpg',
},
'playlist_count': 18,
}]
@ -187,4 +189,7 @@ def _real_extract(self, url):
return self.playlist_from_matches(
re.findall(r'<a [^>]*\bhref="(/arhiv/[^"]+)"', webpage),
playlist_id, self._html_extract_title(webpage),
getter=urljoin('https://365.rtvslo.si'), ie=RTVSLOIE)
getter=urljoin('https://365.rtvslo.si'), ie=RTVSLOIE,
description=self._og_search_description(webpage),
thumbnail=self._og_search_thumbnail(webpage),
)

219
yt_dlp/extractor/senategov.py
View File

@ -4,43 +4,12 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_qs,
unsmuggle_url,
UnsupportedError,
make_archive_id,
remove_end,
url_or_none,
)
_COMMITTEES = {
'ag': ('76440', 'http://ag-f.akamaihd.net'),
'aging': ('76442', 'http://aging-f.akamaihd.net'),
'approps': ('76441', 'http://approps-f.akamaihd.net'),
'arch': ('', 'http://ussenate-f.akamaihd.net'),
'armed': ('76445', 'http://armed-f.akamaihd.net'),
'banking': ('76446', 'http://banking-f.akamaihd.net'),
'budget': ('76447', 'http://budget-f.akamaihd.net'),
'cecc': ('76486', 'http://srs-f.akamaihd.net'),
'commerce': ('80177', 'http://commerce1-f.akamaihd.net'),
'csce': ('75229', 'http://srs-f.akamaihd.net'),
'dpc': ('76590', 'http://dpc-f.akamaihd.net'),
'energy': ('76448', 'http://energy-f.akamaihd.net'),
'epw': ('76478', 'http://epw-f.akamaihd.net'),
'ethics': ('76449', 'http://ethics-f.akamaihd.net'),
'finance': ('76450', 'http://finance-f.akamaihd.net'),
'foreign': ('76451', 'http://foreign-f.akamaihd.net'),
'govtaff': ('76453', 'http://govtaff-f.akamaihd.net'),
'help': ('76452', 'http://help-f.akamaihd.net'),
'indian': ('76455', 'http://indian-f.akamaihd.net'),
'intel': ('76456', 'http://intel-f.akamaihd.net'),
'intlnarc': ('76457', 'http://intlnarc-f.akamaihd.net'),
'jccic': ('85180', 'http://jccic-f.akamaihd.net'),
'jec': ('76458', 'http://jec-f.akamaihd.net'),
'judiciary': ('76459', 'http://judiciary-f.akamaihd.net'),
'rpc': ('76591', 'http://rpc-f.akamaihd.net'),
'rules': ('76460', 'http://rules-f.akamaihd.net'),
'saa': ('76489', 'http://srs-f.akamaihd.net'),
'smbiz': ('76461', 'http://smbiz-f.akamaihd.net'),
'srs': ('75229', 'http://srs-f.akamaihd.net'),
'uscc': ('76487', 'http://srs-f.akamaihd.net'),
'vetaff': ('76462', 'http://vetaff-f.akamaihd.net'),
}
from ..utils.traversal import traverse_obj
class SenateISVPIE(InfoExtractor):
@ -53,31 +22,46 @@ class SenateISVPIE(InfoExtractor):
'info_dict': {
'id': 'judiciary031715',
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
'title': 'ISVP',
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'_old_archive_ids': ['senategov judiciary031715'],
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
'info_dict': {
'id': 'commerce011514',
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
'_old_archive_ids': ['senategov commerce011514'],
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'This video is not available.',
}, {
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
# checksum differs each time
'info_dict': {
'id': 'intel090613',
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
'title': 'ISVP',
'_old_archive_ids': ['senategov intel090613'],
},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'https://www.senate.gov/isvp/?auto_play=false&comm=help&filename=help090920&poster=https://www.help.senate.gov/assets/images/video-poster.png&stt=950',
'info_dict': {
'id': 'help090920',
'ext': 'mp4',
'title': 'ISVP',
'thumbnail': 'https://www.help.senate.gov/assets/images/video-poster.png',
'_old_archive_ids': ['senategov help090920'],
},
}, {
# From http://www.c-span.org/video/?96791-1
@ -85,60 +69,81 @@ class SenateISVPIE(InfoExtractor):
'only_matching': True,
}]
_COMMITTEES = {
'ag': ('76440', 'https://ag-f.akamaihd.net', '2036803', 'agriculture'),
'aging': ('76442', 'https://aging-f.akamaihd.net', '2036801', 'aging'),
'approps': ('76441', 'https://approps-f.akamaihd.net', '2036802', 'appropriations'),
'arch': ('', 'https://ussenate-f.akamaihd.net', '', 'arch'),
'armed': ('76445', 'https://armed-f.akamaihd.net', '2036800', 'armedservices'),
'banking': ('76446', 'https://banking-f.akamaihd.net', '2036799', 'banking'),
'budget': ('76447', 'https://budget-f.akamaihd.net', '2036798', 'budget'),
'cecc': ('76486', 'https://srs-f.akamaihd.net', '2036782', 'srs_cecc'),
'commerce': ('80177', 'https://commerce1-f.akamaihd.net', '2036779', 'commerce'),
'csce': ('75229', 'https://srs-f.akamaihd.net', '2036777', 'srs_srs'),
'dpc': ('76590', 'https://dpc-f.akamaihd.net', '', 'dpc'),
'energy': ('76448', 'https://energy-f.akamaihd.net', '2036797', 'energy'),
'epw': ('76478', 'https://epw-f.akamaihd.net', '2036783', 'environment'),
'ethics': ('76449', 'https://ethics-f.akamaihd.net', '2036796', 'ethics'),
'finance': ('76450', 'https://finance-f.akamaihd.net', '2036795', 'finance_finance'),
'foreign': ('76451', 'https://foreign-f.akamaihd.net', '2036794', 'foreignrelations'),
'govtaff': ('76453', 'https://govtaff-f.akamaihd.net', '2036792', 'hsgac'),
'help': ('76452', 'https://help-f.akamaihd.net', '2036793', 'help'),
'indian': ('76455', 'https://indian-f.akamaihd.net', '2036791', 'indianaffairs'),
'intel': ('76456', 'https://intel-f.akamaihd.net', '2036790', 'intelligence'),
'intlnarc': ('76457', 'https://intlnarc-f.akamaihd.net', '', 'internationalnarcoticscaucus'),
'jccic': ('85180', 'https://jccic-f.akamaihd.net', '2036778', 'jccic'),
'jec': ('76458', 'https://jec-f.akamaihd.net', '2036789', 'jointeconomic'),
'judiciary': ('76459', 'https://judiciary-f.akamaihd.net', '2036788', 'judiciary'),
'rpc': ('76591', 'https://rpc-f.akamaihd.net', '', 'rpc'),
'rules': ('76460', 'https://rules-f.akamaihd.net', '2036787', 'rules'),
'saa': ('76489', 'https://srs-f.akamaihd.net', '2036780', 'srs_saa'),
'smbiz': ('76461', 'https://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'),
'srs': ('75229', 'https://srs-f.akamaihd.net', '2031966', 'srs_srs'),
'uscc': ('76487', 'https://srs-f.akamaihd.net', '2036781', 'srs_uscc'),
'vetaff': ('76462', 'https://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'),
}
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
qs = urllib.parse.parse_qs(self._match_valid_url(url).group('qs'))
if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
if not qs.get('filename') or not qs.get('comm'):
raise ExtractorError('Invalid URL', expected=True)
video_id = re.sub(r'.mp4$', '', qs['filename'][0])
filename = qs['filename'][0]
video_id = remove_end(filename, '.mp4')
webpage = self._download_webpage(url, video_id)
committee = qs['comm'][0]
if smuggled_data.get('force_title'):
title = smuggled_data['force_title']
else:
title = self._html_extract_title(webpage)
poster = qs.get('poster')
thumbnail = poster[0] if poster else None
video_type = qs['type'][0]
committee = video_type if video_type == 'arch' else qs['comm'][0]
stream_num, domain = _COMMITTEES[committee]
stream_num, stream_domain, stream_id, msl3 = self._COMMITTEES[committee]
urls_alternatives = [f'https://www-senate-gov-media-srs.akamaized.net/hls/live/{stream_id}/{committee}/{filename}/master.m3u8',
f'https://www-senate-gov-msl3archive.akamaized.net/{msl3}/{filename}_1/master.m3u8',
f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
f'{stream_domain}/i/{filename}.mp4/master.m3u8']
formats = []
if video_type == 'arch':
filename = video_id if '.' in video_id else video_id + '.mp4'
m3u8_url = urllib.parse.urljoin(domain, 'i/' + filename + '/master.m3u8')
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8')
else:
hdcore_sign = 'hdcore=3.1.0'
url_params = (domain, video_id, stream_num)
f4m_url = f'%s/z/%s_1@%s/manifest.f4m?{hdcore_sign}' % url_params
m3u8_url = '{}/i/{}_1@{}/master.m3u8'.format(*url_params)
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
# URLs without the extra param induce an 404 error
entry.update({'extra_param_to_segment_url': hdcore_sign})
formats.append(entry)
for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
if mobj:
entry['format_id'] += mobj.group('tag')
formats.append(entry)
subtitles = {}
for video_url in urls_alternatives:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4', fatal=False)
if formats:
break
return {
'id': video_id,
'title': title,
'title': self._html_extract_title(webpage),
'formats': formats,
'thumbnail': thumbnail,
'subtitles': subtitles,
'thumbnail': traverse_obj(qs, ('poster', 0, {url_or_none})),
'_old_archive_ids': [make_archive_id(SenateGovIE, video_id)],
}
class SenateGovIE(InfoExtractor):
_IE_NAME = 'senate.gov'
_VALID_URL = r'https?:\/\/(?:www\.)?(help|appropriations|judiciary|banking|armed-services|finance)\.senate\.gov'
_SUBDOMAIN_RE = '|'.join(map(re.escape, (
'agriculture', 'aging', 'appropriations', 'armed-services', 'banking',
'budget', 'commerce', 'energy', 'epw', 'finance', 'foreign', 'help',
'intelligence', 'inaugural', 'judiciary', 'rules', 'sbc', 'veterans',
)))
_VALID_URL = rf'https?://(?:www\.)?(?:{_SUBDOMAIN_RE})\.senate\.gov'
_TESTS = [{
'url': 'https://www.help.senate.gov/hearings/vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
'info_dict': {
@ -147,6 +152,9 @@ class SenateGovIE(InfoExtractor):
'title': 'Vaccines: Saving Lives, Ensuring Confidence, and Protecting Public Health',
'description': 'The U.S. Senate Committee on Health, Education, Labor & Pensions',
'ext': 'mp4',
'age_limit': 0,
'thumbnail': 'https://www.help.senate.gov/assets/images/sharelogo.jpg',
'_old_archive_ids': ['senategov help090920'],
},
'params': {'skip_download': 'm3u8'},
}, {
@ -156,8 +164,12 @@ class SenateGovIE(InfoExtractor):
'display_id': 'watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
'title': 'Review of the FY2019 Budget Request for the U.S. Army',
'ext': 'mp4',
'age_limit': 0,
'thumbnail': 'https://www.appropriations.senate.gov/themes/appropriations/images/video-poster-flash-fit.png',
'_old_archive_ids': ['senategov appropsA051518'],
},
'params': {'skip_download': 'm3u8'},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'https://www.banking.senate.gov/hearings/21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
'info_dict': {
@ -166,32 +178,65 @@ class SenateGovIE(InfoExtractor):
'title': '21st Century Communities: Public Transportation Infrastructure Investment and FAST Act Reauthorization',
'description': 'The Official website of The United States Committee on Banking, Housing, and Urban Affairs',
'ext': 'mp4',
'thumbnail': 'https://www.banking.senate.gov/themes/banking/images/sharelogo.jpg',
'age_limit': 0,
'_old_archive_ids': ['senategov banking041521'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.agriculture.senate.gov/hearings/hemp-production-and-the-2018-farm-bill',
'only_matching': True,
}, {
'url': 'https://www.aging.senate.gov/hearings/the-older-americans-act-the-local-impact-of-the-law-and-the-upcoming-reauthorization',
'only_matching': True,
}, {
'url': 'https://www.budget.senate.gov/hearings/improving-care-lowering-costs-achieving-health-care-efficiency',
'only_matching': True,
}, {
'url': 'https://www.commerce.senate.gov/2024/12/communications-networks-safety-and-security',
'only_matching': True,
}, {
'url': 'https://www.energy.senate.gov/hearings/2024/2/full-committee-hearing-to-examine',
'only_matching': True,
}, {
'url': 'https://www.epw.senate.gov/public/index.cfm/hearings?ID=F63083EA-2C13-498C-B548-341BED68C209',
'only_matching': True,
}, {
'url': 'https://www.foreign.senate.gov/hearings/american-diplomacy-and-global-leadership-review-of-the-fy25-state-department-budget-request',
'only_matching': True,
}, {
'url': 'https://www.intelligence.senate.gov/hearings/foreign-threats-elections-2024-%E2%80%93-roles-and-responsibilities-us-tech-providers',
'only_matching': True,
}, {
'url': 'https://www.inaugural.senate.gov/52nd-inaugural-ceremonies/',
'only_matching': True,
}, {
'url': 'https://www.rules.senate.gov/hearings/02/07/2023/business-meeting',
'only_matching': True,
}, {
'url': 'https://www.sbc.senate.gov/public/index.cfm/hearings?ID=5B13AA6B-8279-45AF-B54B-94156DC7A2AB',
'only_matching': True,
}, {
'url': 'https://www.veterans.senate.gov/2024/5/frontier-health-care-ensuring-veterans-access-no-matter-where-they-live',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._generic_id(url)
webpage = self._download_webpage(url, display_id)
parse_info = parse_qs(self._search_regex(
r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)', webpage, 'hearing URL'))
stream_num, stream_domain = _COMMITTEES[parse_info['comm'][-1]]
filename = parse_info['filename'][-1]
formats = self._extract_m3u8_formats(
f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
display_id, ext='mp4')
url_info = next(SenateISVPIE.extract_from_webpage(self._downloader, url, webpage), None)
if not url_info:
raise UnsupportedError(url)
title = self._html_search_regex(
(*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title')
(*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title', fatal=False)
return {
'id': re.sub(r'.mp4$', '', filename),
**url_info,
'_type': 'url_transparent',
'display_id': display_id,
'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'age_limit': self._rta_search(webpage),
'formats': formats,
}

46
yt_dlp/extractor/soundcloud.py
View File

@ -361,6 +361,7 @@ def extract_count(key):
'uploader_url': user.get('permalink_url'),
'timestamp': unified_timestamp(info.get('created_at')),
'title': info.get('title'),
'track': info.get('title'),
'description': info.get('description'),
'thumbnails': thumbnails,
'duration': float_or_none(info.get('duration'), 1000),
@ -393,7 +394,7 @@ class SoundcloudIE(SoundcloudBaseIE):
(?:(?:(?:www\.|m\.)?soundcloud\.com/
(?!stations/track)
(?P<uploader>[\w\d-]+)/
(?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
(?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight|comments)/?(?:$|[?#]))
(?P<title>[\w\d-]+)
(?:/(?P<token>(?!(?:albums|sets|recommended))[^?]+?))?
(?:[?].*)?$)
@ -410,6 +411,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '62986583',
'ext': 'opus',
'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
'track': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
'uploader': 'E.T. ExTerrestrial Music',
'uploader_id': '1571244',
@ -432,6 +434,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '47127627',
'ext': 'opus',
'title': 'Goldrushed',
'track': 'Goldrushed',
'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
'uploader': 'The Royal Concept',
'uploader_id': '9615865',
@ -457,6 +460,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '123998367',
'ext': 'mp3',
'title': 'Youtube - Dl Test Video \'\' Ä↭',
'track': 'Youtube - Dl Test Video \'\' Ä↭',
'description': 'test chars: "\'/\\ä↭',
'uploader': 'jaimeMF',
'uploader_id': '69767071',
@ -481,6 +485,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '123998367',
'ext': 'mp3',
'title': 'Youtube - Dl Test Video \'\' Ä↭',
'track': 'Youtube - Dl Test Video \'\' Ä↭',
'description': 'test chars: "\'/\\ä↭',
'uploader': 'jaimeMF',
'uploader_id': '69767071',
@ -505,6 +510,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '343609555',
'ext': 'wav',
'title': 'The Following',
'track': 'The Following',
'description': '',
'uploader': '80M',
'uploader_id': '312384765',
@ -530,6 +536,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '340344461',
'ext': 'wav',
'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'track': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
'uploader': 'Ori Uplift Music',
'uploader_id': '12563093',
@ -555,6 +562,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '309699954',
'ext': 'mp3',
'title': 'Sideways (Prod. Mad Real)',
'track': 'Sideways (Prod. Mad Real)',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'uploader': 'garyvee',
'uploader_id': '2366352',
@ -581,6 +589,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'id': '583011102',
'ext': 'opus',
'title': 'Mezzo Valzer',
'track': 'Mezzo Valzer',
'description': 'md5:f4d5f39d52e0ccc2b4f665326428901a',
'uploader': 'Giovanni Sarani',
'uploader_id': '3352531',
@ -656,6 +665,11 @@ def _extract_set(self, playlist, token=None):
'playlistId': playlist_id,
'playlistSecretToken': token,
}, headers=self._HEADERS)
album_info = traverse_obj(playlist, {
'album': ('title', {str}),
'album_artist': ('user', 'username', {str}),
'album_type': ('set_type', {str}, {lambda x: x or 'playlist'}),
})
entries = []
for track in tracks:
track_id = str_or_none(track.get('id'))
@ -667,11 +681,17 @@ def _extract_set(self, playlist, token=None):
if token:
url += '?secret_token=' + token
entries.append(self.url_result(
url, SoundcloudIE.ie_key(), track_id))
url, SoundcloudIE.ie_key(), track_id, url_transparent=True, **album_info))
return self.playlist_result(
entries, playlist_id,
playlist.get('title'),
playlist.get('description'))
playlist.get('description'),
**album_info,
**traverse_obj(playlist, {
'uploader': ('user', 'username', {str}),
'uploader_id': ('user', 'id', {str_or_none}),
}),
)
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
@ -683,6 +703,11 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
'id': '2284613',
'title': 'The Royal Concept EP',
'description': 'md5:71d07087c7a449e8941a70a29e34671e',
'uploader': 'The Royal Concept',
'uploader_id': '9615865',
'album': 'The Royal Concept EP',
'album_artists': ['The Royal Concept'],
'album_type': 'ep',
},
'playlist_mincount': 5,
}, {
@ -776,7 +801,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
(?:(?:www|m)\.)?soundcloud\.com/
(?P<user>[^/]+)
(?:/
(?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
(?P<rsrc>tracks|albums|sets|reposts|likes|spotlight|comments)
)?
/?(?:[?#].*)?$
'''
@ -830,6 +855,13 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
'title': 'Grynpyret (Spotlight)',
},
'playlist_mincount': 1,
}, {
'url': 'https://soundcloud.com/one-thousand-and-one/comments',
'info_dict': {
'id': '992430331',
'title': '7x11x13-testing (Comments)',
},
'playlist_mincount': 1,
}]
_BASE_URL_MAP = {
@ -840,6 +872,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
'reposts': 'stream/users/%s/reposts',
'likes': 'users/%s/likes',
'spotlight': 'users/%s/spotlight',
'comments': 'users/%s/comments',
}
def _real_extract(self, url):
@ -960,6 +993,11 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
'id': '4110309',
'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
'description': 're:.*?TILT Brass - Bowery Poetry Club',
'uploader': 'Non-Site Records',
'uploader_id': '33660914',
'album_artists': ['Non-Site Records'],
'album_type': 'playlist',
'album': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
},
'playlist_count': 6,
}]

5
yt_dlp/extractor/stacommu.py
View File

@ -207,7 +207,7 @@ def _real_extract(self, url):
class TheaterComplexTownPPVIE(TheaterComplexTownBaseIE):
_VALID_URL = r'https?://(?:www\.)?theater-complex\.town/(?:(?:en|ja)/)?ppv/(?P<id>\w+)'
_VALID_URL = r'https?://(?:www\.)?theater-complex\.town/(?:(?:en|ja)/)?(?:ppv|live)/(?P<id>\w+)'
IE_NAME = 'theatercomplextown:ppv'
_TESTS = [{
'url': 'https://www.theater-complex.town/ppv/wytW3X7khrjJBUpKuV3jen',
@ -229,6 +229,9 @@ class TheaterComplexTownPPVIE(TheaterComplexTownBaseIE):
}, {
'url': 'https://www.theater-complex.town/ja/ppv/qwUVmLmGEiZ3ZW6it9uGys',
'only_matching': True,
}, {
'url': 'https://www.theater-complex.town/en/live/79akNM7bJeD5Fi9EP39aDp',
'only_matching': True,
}]
_API_PATH = 'events'

199
yt_dlp/extractor/subsplash.py Normal file
View File

@ -0,0 +1,199 @@
import functools
import math
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
int_or_none,
parse_iso8601,
try_call,
url_or_none,
)
from ..utils.traversal import traverse_obj
class SubsplashBaseIE(InfoExtractor):
def _get_headers(self, url, display_id):
token = try_call(lambda: self._get_cookies(url)['ss-token-guest'].value)
if not token:
webpage, urlh = self._download_webpage_handle(url, display_id)
token = (
try_call(lambda: self._get_cookies(url)['ss-token-guest'].value)
or urlh.get_header('x-api-token')
or self._search_json(
r'<script[^>]+\bid="shoebox-tokens"[^>]*>', webpage, 'shoebox tokens',
display_id, default={}).get('apiToken')
or self._search_regex(r'\\"tokens\\":{\\"guest\\":\\"([A-Za-z0-9._-]+)\\"', webpage, 'token', default=None))
if not token:
self.report_warning('Unable to extract auth token')
return None
return {'Authorization': f'Bearer {token}'}
def _extract_video(self, data, video_id):
formats = []
video_data = traverse_obj(data, ('_embedded', 'video', '_embedded', {dict}))
m3u8_url = traverse_obj(video_data, ('playlists', 0, '_links', 'related', 'href', {url_or_none}))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
mp4_entry = traverse_obj(video_data, ('video-outputs', lambda _, v: url_or_none(v['_links']['related']['href']), any))
if mp4_entry:
formats.append({
'url': mp4_entry['_links']['related']['href'],
'format_id': 'direct',
'quality': 1,
**traverse_obj(mp4_entry, {
'height': ('height', {int_or_none}),
'width': ('width', {int_or_none}),
'filesize': ('file_size', {int_or_none}),
}),
})
return {
'id': video_id,
'formats': formats,
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('summary_text', {str}),
'thumbnail': ('_embedded', 'images', 0, '_links', 'related', 'href', {url_or_none}),
'duration': ('_embedded', 'video', 'duration', {int_or_none(scale=1000)}),
'timestamp': ('date', {parse_iso8601}),
'release_timestamp': ('published_at', {parse_iso8601}),
'modified_timestamp': ('updated_at', {parse_iso8601}),
}),
}
class SubsplashIE(SubsplashBaseIE):
_VALID_URL = [
r'https?://(?:www\.)?subsplash\.com/(?:u/)?[^/?#]+/[^/?#]+/(?:d/|mi/\+)(?P<id>\w+)',
r'https?://(?:\w+\.)?subspla\.sh/(?P<id>\w+)',
]
_TESTS = [{
'url': 'https://subsplash.com/u/skywatchtv/media/d/5whnx5s-the-grand-delusion-taking-place-right-now',
'md5': 'd468729814e533cec86f1da505dec82d',
'info_dict': {
'id': '5whnx5s',
'ext': 'mp4',
'title': 'THE GRAND DELUSION TAKING PLACE RIGHT NOW!',
'description': 'md5:220a630865c3697b0ec9dcb3a70cbc33',
'upload_date': '20240901',
'duration': 1710,
'thumbnail': r're:https?://.*\.(?:jpg|png)$',
'modified_date': '20240901',
'release_date': '20240901',
'release_timestamp': 1725195600,
'timestamp': 1725148800,
'modified_timestamp': 1725195657,
},
}, {
'url': 'https://subsplash.com/u/prophecywatchers/media/d/n4dr8b2-the-transhumanist-plan-for-humanity-billy-crone',
'md5': '01982d58021af81c969958459bd81f13',
'info_dict': {
'id': 'n4dr8b2',
'ext': 'mp4',
'title': 'The Transhumanist Plan for Humanity | Billy Crone',
'upload_date': '20240903',
'duration': 1709,
'thumbnail': r're:https?://.*\.(?:jpg|png)$',
'timestamp': 1725321600,
'modified_date': '20241010',
'release_date': '20240903',
'release_timestamp': 1725379200,
'modified_timestamp': 1728577804,
},
}, {
'url': 'https://subsplash.com/laiglesiadelcentro/vid/mi/+ecb6a6b?autoplay=true',
'md5': '013c9b1e391dd4b34d8612439445deef',
'info_dict': {
'id': 'ecb6a6b',
'ext': 'mp4',
'thumbnail': r're:https?://.*\.(?:jpg|png)$',
'release_timestamp': 1477095852,
'title': 'En el Principio Era el Verbo | EVANGELIO DE JUAN | Ps. Gadiel Ríos',
'timestamp': 1425772800,
'upload_date': '20150308',
'description': 'md5:f368221de93176654989ba66bb564798',
'modified_timestamp': 1730258864,
'modified_date': '20241030',
'release_date': '20161022',
},
}, {
'url': 'https://prophecywatchers.subspla.sh/8gps8cx',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://core.subsplash.com/media/v1/media-items',
video_id, headers=self._get_headers(url, video_id),
query={
'filter[short_code]': video_id,
'include': 'images,audio.audio-outputs,audio.video,video.video-outputs,video.playlists,document,broadcast',
})
return self._extract_video(traverse_obj(data, ('_embedded', 'media-items', 0)), video_id)
class SubsplashPlaylistIE(SubsplashBaseIE):
IE_NAME = 'subsplash:playlist'
_VALID_URL = r'https?://(?:www\.)?subsplash\.com/[^/?#]+/(?:our-videos|media)/ms/\+(?P<id>\w+)'
_PAGE_SIZE = 15
_TESTS = [{
'url': 'https://subsplash.com/skywatchtv/our-videos/ms/+dbyjzp8',
'info_dict': {
'id': 'dbyjzp8',
'title': 'Five in Ten',
},
'playlist_mincount': 11,
}, {
'url': 'https://subsplash.com/prophecywatchers/media/ms/+n42mr48',
'info_dict': {
'id': 'n42mr48',
'title': 'Road to Zion Series',
},
'playlist_mincount': 13,
}, {
'url': 'https://subsplash.com/prophecywatchers/media/ms/+918b9f6',
'only_matching': True,
}]
def _entries(self, series_id, headers, page):
data = self._download_json(
'https://core.subsplash.com/media/v1/media-items', series_id, headers=headers,
query={
'filter[broadcast.status|broadcast.status]': 'null|on-demand',
'filter[media_series]': series_id,
'filter[status]': 'published',
'include': 'images,audio.audio-outputs,audio.video,video.video-outputs,video.playlists,document',
'page[number]': page + 1,
'page[size]': self._PAGE_SIZE,
'sort': '-position',
}, note=f'Downloading page {page + 1}')
for entry in traverse_obj(data, ('_embedded', 'media-items', lambda _, v: v['short_code'])):
entry_id = entry['short_code']
info = self._extract_video(entry, entry_id)
yield {
**info,
'webpage_url': f'https://subspla.sh/{entry_id}',
'extractor_key': SubsplashIE.ie_key(),
'extractor': SubsplashIE.IE_NAME,
}
def _real_extract(self, url):
display_id = self._match_id(url)
headers = self._get_headers(url, display_id)
data = self._download_json(
'https://core.subsplash.com/media/v1/media-series', display_id, headers=headers,
query={'filter[short_code]': display_id})
series_data = traverse_obj(data, ('_embedded', 'media-series', 0, {
'id': ('id', {str}),
'title': ('title', {str}),
'count': ('media_items_count', {int}),
}))
total_pages = math.ceil(series_data['count'] / self._PAGE_SIZE)
return self.playlist_result(
InAdvancePagedList(functools.partial(self._entries, series_data['id'], headers), total_pages, self._PAGE_SIZE),
display_id, series_data['title'])

3
yt_dlp/extractor/theplatform.py
View File

@ -118,8 +118,9 @@ def extract_site_specific_field(field):
'categories', lambda _, v: v.get('label') in ('category', None), 'name', {str})) or None,
'tags': traverse_obj(info, ('keywords', {lambda x: re.split(r'[;,]\s?', x) if x else None})),
'location': extract_site_specific_field('region'),
'series': extract_site_specific_field('show'),
'series': extract_site_specific_field('show') or extract_site_specific_field('seriesTitle'),
'season_number': int_or_none(extract_site_specific_field('seasonNumber')),
'episode_number': int_or_none(extract_site_specific_field('episodeNumber')),
'media_type': extract_site_specific_field('programmingType') or extract_site_specific_field('type'),
}

2
yt_dlp/extractor/tver.py
View File

@ -24,8 +24,6 @@ class TVerIE(InfoExtractor):
'channel': 'テレビ朝日',
'id': 'ep83nf3w4p',
'ext': 'mp4',
'onair_label': '5月3日(火)放送分',
'ext_title': '家事ヤロウ!!! 売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！ テレビ朝日 5月3日(火)放送分',
},
'add_ie': ['BrightcoveNew'],
}, {

7
yt_dlp/extractor/unsupported.py
View File

@ -50,6 +50,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
r'music\.amazon\.(?:\w{2}\.)?\w+',
r'(?:watch|front)\.njpwworld\.com',
r'qub\.ca/vrai',
r'(?:beta\.)?crunchyroll\.com',
)
_TESTS = [{
@ -153,6 +154,12 @@ class KnownDRMIE(UnsupportedInfoExtractor):
}, {
'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,
}, {
'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
'only_matching': True,
}, {
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
'only_matching': True,
}]
def _real_extract(self, url):

95
yt_dlp/extractor/videocampus_sachsen.py
View File

@ -14,59 +14,69 @@ class VideocampusSachsenIE(InfoExtractor):
'corporate.demo.vimp.com',
'dancehalldatabase.com',
'drehzahl.tv',
'educhannel.hs-gesundheit.de',
'educhannel.hs-gesundheit.de', # Hochschule für Gesundheit NRW
'emedia.ls.haw-hamburg.de',
'globale-evolution.net',
'hohu.tv',
'htvideos.hightechhigh.org',
'k210039.vimp.mivitec.net',
'media.cmslegal.com',
'media.hs-furtwangen.de',
'media.hwr-berlin.de',
'media.fh-swf.de', # Fachhochschule Südwestfalen
'media.hs-furtwangen.de', # Hochschule Furtwangen
'media.hwr-berlin.de', # Hochschule für Wirtschaft und Recht Berlin
'mediathek.dkfz.de',
'mediathek.htw-berlin.de',
'mediathek.htw-berlin.de', # Hochschule für Technik und Wirtschaft Berlin
'mediathek.polizei-bw.de',
'medien.hs-merseburg.de',
'mportal.europa-uni.de',
'medien.hs-merseburg.de', # Hochschule Merseburg
'mitmedia.manukau.ac.nz', # Manukau Institute of Technology Auckland (NZ)
'mportal.europa-uni.de', # Europa-Universität Viadrina
'pacific.demo.vimp.com',
'slctv.com',
'streaming.prairiesouth.ca',
'tube.isbonline.cn',
'univideo.uni-kassel.de',
'univideo.uni-kassel.de', # Universität Kassel
'ursula2.genetics.emory.edu',
'ursulablicklevideoarchiv.com',
'v.agrarumweltpaedagogik.at',
'video.eplay-tv.de',
'video.fh-dortmund.de',
'video.hs-offenburg.de',
'video.hs-pforzheim.de',
'video.hspv.nrw.de',
'video.fh-dortmund.de', # Fachhochschule Dortmund
'video.hs-nb.de', # Hochschule Neubrandenburg
'video.hs-offenburg.de', # Hochschule Offenburg
'video.hs-pforzheim.de', # Hochschule Pforzheim
'video.hspv.nrw.de', # Hochschule für Polizei und öffentliche Verwaltung NRW
'video.irtshdf.fr',
'video.pareygo.de',
'video.tu-freiberg.de',
'videocampus.sachsen.de',
'videoportal.uni-freiburg.de',
'videoportal.vm.uni-freiburg.de',
'video.tu-dortmund.de', # Technische Universität Dortmund
'video.tu-freiberg.de', # Technische Universität Bergakademie Freiberg
'videocampus.sachsen.de', # Video Campus Sachsen (gemeinsame Videoplattform sächsischer Universitäten, Hochschulen und der Berufsakademie Sachsen)
'videoportal.uni-freiburg.de', # Albert-Ludwigs-Universität Freiburg
'videoportal.vm.uni-freiburg.de', # Albert-Ludwigs-Universität Freiburg
'videos.duoc.cl',
'videos.uni-paderborn.de',
'videos.uni-paderborn.de', # Universität Paderborn
'vimp-bemus.udk-berlin.de',
'vimp.aekwl.de',
'vimp.hs-mittweida.de',
'vimp.oth-regensburg.de',
'vimp.ph-heidelberg.de',
'vimp.landesfilmdienste.de',
'vimp.oth-regensburg.de', # Ostbayerische Technische Hochschule Regensburg
'vimp.ph-heidelberg.de', # Pädagogische Hochschule Heidelberg
'vimp.sma-events.com',
'vimp.weka-fachmedien.de',
'vimpdesk.com',
'webtv.univ-montp3.fr',
'www.b-tu.de/media',
'www.b-tu.de/media', # Brandenburgische Technische Universität Cottbus-Senftenberg
'www.bergauf.tv',
'www.bigcitytv.de',
'www.cad-videos.de',
'www.drehzahl.tv',
'www.fh-bielefeld.de/medienportal',
'www.hohu.tv',
'www.hsbi.de/medienportal', # Hochschule Bielefeld
'www.logistic.tv',
'www.orvovideo.com',
'www.printtube.co.uk',
'www.rwe.tv',
'www.salzi.tv',
'www.signtube.co.uk',
'www.twb-power.com',
'www.wenglor-media.com',
'www2.univ-sba.dz',
)
@ -188,22 +198,23 @@ def _real_extract(self, url):
class ViMPPlaylistIE(InfoExtractor):
IE_NAME = 'ViMP:Playlist'
_VALID_URL = r'''(?x)(?P<host>https?://(?:{}))/(?:
album/view/aid/(?P<album_id>[0-9]+)|
(?P<mode>category|channel)/(?P<name>[\w-]+)/(?P<id>[0-9]+)
(?P<mode1>album)/view/aid/(?P<album_id>[0-9]+)|
(?P<mode2>category|channel)/(?P<name>[\w-]+)/(?P<channel_id>[0-9]+)|
(?P<mode3>tag)/(?P<tag_id>[0-9]+)
)'''.format('|'.join(map(re.escape, VideocampusSachsenIE._INSTANCES)))
_TESTS = [{
'url': 'https://vimp.oth-regensburg.de/channel/Designtheorie-1-SoSe-2020/3',
'info_dict': {
'id': 'channel-3',
'title': 'Designtheorie 1 SoSe 2020 :: Channels :: ViMP OTH Regensburg',
'title': 'Designtheorie 1 SoSe 2020 - Channels - ViMP OTH Regensburg',
},
'playlist_mincount': 9,
}, {
'url': 'https://www.fh-bielefeld.de/medienportal/album/view/aid/208',
'url': 'https://www.hsbi.de/medienportal/album/view/aid/208',
'info_dict': {
'id': 'album-208',
'title': 'KG Praktikum ABT/MEC :: Playlists :: FH-Medienportal',
'title': 'KG Praktikum ABT/MEC - Playlists - HSBI-Medienportal',
},
'playlist_mincount': 4,
}, {
@ -213,6 +224,13 @@ class ViMPPlaylistIE(InfoExtractor):
'title': 'Online-Seminare ONYX - BPS - Bildungseinrichtungen - VCS',
},
'playlist_mincount': 7,
}, {
'url': 'https://videocampus.sachsen.de/tag/26902',
'info_dict': {
'id': 'tag-26902',
'title': 'advanced mobile and v2x communication - Tags - VCS',
},
'playlist_mincount': 6,
}]
_PAGE_SIZE = 10
@ -220,34 +238,37 @@ def _fetch_page(self, host, url_part, playlist_id, data, page):
webpage = self._download_webpage(
f'{host}/media/ajax/component/boxList/{url_part}', playlist_id,
query={'page': page, 'page_only': 1}, data=urlencode_postdata(data))
urls = re.findall(r'"([^"]+/video/[^"]+)"', webpage)
urls = re.findall(r'"([^"]*/video/[^"]+)"', webpage)
for url in urls:
yield self.url_result(host + url, VideocampusSachsenIE)
def _real_extract(self, url):
host, album_id, mode, name, playlist_id = self._match_valid_url(url).group(
'host', 'album_id', 'mode', 'name', 'id')
host, album_id, name, channel_id, tag_id, mode1, mode2, mode3 = self._match_valid_url(url).group(
'host', 'album_id', 'name', 'channel_id', 'tag_id', 'mode1', 'mode2', 'mode3')
webpage = self._download_webpage(url, album_id or playlist_id, fatal=False) or ''
mode = mode1 or mode2 or mode3
playlist_id = album_id or channel_id or tag_id
webpage = self._download_webpage(url, playlist_id, fatal=False) or ''
title = (self._html_search_meta('title', webpage, fatal=False)
or self._html_extract_title(webpage))
url_part = (f'aid/{album_id}' if album_id
else f'category/{name}/category_id/{playlist_id}' if mode == 'category'
else f'title/{name}/channel/{playlist_id}')
else f'category/{name}/category_id/{channel_id}' if mode == 'category'
else f'title/{name}/channel/{channel_id}' if mode == 'channel'
else f'tag/{tag_id}')
mode = mode or 'album'
data = {
'vars[mode]': mode,
f'vars[{mode}]': album_id or playlist_id,
'vars[context]': '4' if album_id else '1' if mode == 'category' else '3',
'vars[context_id]': album_id or playlist_id,
f'vars[{mode}]': playlist_id,
'vars[context]': '4' if album_id else '1' if mode == 'category' else '3' if mode == 'album' else '0',
'vars[context_id]': playlist_id,
'vars[layout]': 'thumb',
'vars[per_page][thumb]': str(self._PAGE_SIZE),
}
return self.playlist_result(
OnDemandPagedList(functools.partial(
self._fetch_page, host, url_part, album_id or playlist_id, data), self._PAGE_SIZE),
playlist_title=title, id=f'{mode}-{album_id or playlist_id}')
self._fetch_page, host, url_part, playlist_id, data), self._PAGE_SIZE),
playlist_title=title, id=f'{mode}-{playlist_id}')

41
yt_dlp/extractor/vimeo.py
View File

@ -28,6 +28,7 @@
try_get,
unified_timestamp,
unsmuggle_url,
url_or_none,
urlencode_postdata,
urlhandle_detect_ext,
urljoin,
@ -211,11 +212,7 @@ def _parse_config(self, config, video_id):
'width': int_or_none(key),
'url': thumb,
})
thumbnail = video_data.get('thumbnail')
if thumbnail:
thumbnails.append({
'url': thumbnail,
})
thumbnails.extend(traverse_obj(video_data, (('thumbnail', 'thumbnail_url'), {'url': {url_or_none}})))
owner = video_data.get('owner') or {}
video_uploader_url = owner.get('url')
@ -388,7 +385,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
'uploader_id': 'businessofsoftware',
'duration': 3610,
'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d',
},
'params': {
'format': 'best[protocol=https]',
@ -413,7 +410,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'duration': 10,
'comment_count': int,
'like_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d',
},
'params': {
'format': 'best[protocol=https]',
@ -437,7 +434,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'timestamp': 1380339469,
'upload_date': '20130928',
'duration': 187,
'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d',
'view_count': int,
'comment_count': int,
'like_count': int,
@ -463,7 +460,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'duration': 62,
'comment_count': int,
'like_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/452001751-8216e0571c251a09d7a8387550942d89f7f86f6398f8ed886e639b0dd50d3c90-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/452001751-8216e0571c251a09d7a8387550942d89f7f86f6398f8ed886e639b0dd50d3c90-d',
'subtitles': {
'de': 'count:3',
'en': 'count:3',
@ -488,7 +485,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
'uploader_id': 'user28849593',
'duration': 118,
'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d',
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
},
@ -509,7 +506,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'duration': 60,
'comment_count': int,
'view_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d',
'like_count': int,
'tags': 'count:11',
},
@ -531,7 +528,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
'upload_date': '20200225',
'duration': 176,
'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d',
'uploader_url': 'https://vimeo.com/frameworkla',
},
# 'params': {'format': 'source'},
@ -556,7 +553,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'duration': 321,
'comment_count': int,
'view_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d',
'like_count': int,
'tags': ['[the shining', 'vimeohq', 'cv', 'vimeo tribute]'],
},
@ -596,7 +593,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d',
},
'params': {
'format': 'best[protocol=https]',
@ -633,7 +630,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'description': str, # FIXME: Dynamic SEO spam description
'upload_date': '20150209',
'timestamp': 1423518307,
'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
'thumbnail': 'https://i.vimeocdn.com/video/default',
'duration': 10,
'like_count': int,
'uploader_url': 'https://vimeo.com/user20132939',
@ -666,7 +663,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'license': 'by-nc',
'duration': 159,
'comment_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d',
'like_count': int,
'uploader_url': 'https://vimeo.com/aliniamedia',
'release_date': '20160329',
@ -686,7 +683,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader': 'Firework Champions',
'upload_date': '20150910',
'timestamp': 1441901895,
'thumbnail': 'https://i.vimeocdn.com/video/534715882-6ff8e4660cbf2fea68282876d8d44f318825dfe572cc4016e73b3266eac8ae3a-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/534715882-6ff8e4660cbf2fea68282876d8d44f318825dfe572cc4016e73b3266eac8ae3a-d',
'uploader_url': 'https://vimeo.com/fireworkchampions',
'tags': 'count:6',
'duration': 229,
@ -715,7 +712,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'duration': 336,
'comment_count': int,
'view_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d',
'like_count': int,
'uploader_url': 'https://vimeo.com/karimhd',
'channel_url': 'https://vimeo.com/channels/staffpicks',
@ -740,7 +737,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'release_timestamp': 1627621014,
'duration': 976,
'comment_count': int,
'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d',
'like_count': int,
'uploader_url': 'https://vimeo.com/txwestcapital',
'release_date': '20210730',
@ -764,7 +761,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'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',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d',
'duration': 2636,
'chapters': [
{'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
@ -807,7 +804,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'like_count': int,
'view_count': int,
'comment_count': int,
'thumbnail': r're:https://i\.vimeocdn\.com/video/1018638656-[\da-f]+-d_1280',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1018638656-[\da-f]+-d',
},
# 'params': {'format': 'Original'},
'expected_warnings': ['Failed to parse XML: not well-formed'],
@ -824,7 +821,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'rajavirdi',
'uploader_url': 'https://vimeo.com/rajavirdi',
'duration': 309,
'thumbnail': r're:https://i\.vimeocdn\.com/video/1716727772-[\da-f]+-d_1280',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1716727772-[\da-f]+-d',
},
# 'params': {'format': 'source'},
'expected_warnings': ['Failed to parse XML: not well-formed'],

21
yt_dlp/extractor/weibo.py
View File

@ -124,7 +124,7 @@ def _parse_video_info(self, video_info, video_id=None):
class WeiboIE(WeiboBaseIE):
_VALID_URL = r'https?://(?:m\.weibo\.cn/status|(?:www\.)?weibo\.com/\d+)/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:m\.weibo\.cn/(?:status|detail)|(?:www\.)?weibo\.com/\d+)/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://weibo.com/7827771738/N4xlMvjhI',
'info_dict': {
@ -164,6 +164,25 @@ class WeiboIE(WeiboBaseIE):
'like_count': int,
'repost_count': int,
},
}, {
'url': 'https://m.weibo.cn/detail/4189191225395228',
'info_dict': {
'id': '4189191225395228',
'ext': 'mp4',
'display_id': 'FBqgOmDxO',
'title': '柴犬柴犬的秒拍视频',
'description': '午睡当然是要甜甜蜜蜜的啦！[坏笑] Instagram：shibainu.gaku http://t.cn/RHbmjzW ',
'duration': 53,
'timestamp': 1514264429,
'upload_date': '20171226',
'thumbnail': r're:https://.*\.jpg',
'uploader': '柴犬柴犬',
'uploader_id': '5926682210',
'uploader_url': 'https://weibo.com/u/5926682210',
'view_count': int,
'like_count': int,
'repost_count': int,
},
}, {
'url': 'https://weibo.com/0/4224132150961381',
'note': 'no playback_list example',

23
yt_dlp/extractor/xhamster.py
View File

@ -20,7 +20,7 @@
class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.(?:com|desi)|xhday\.com|xhvid\.com)'
_VALID_URL = rf'''(?x)
https?://
(?:[^/?#]+\.)?{_DOMAINS}/
@ -31,7 +31,7 @@ class XHamsterIE(InfoExtractor):
'''
_TESTS = [{
'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'md5': '34e1ab926db5dc2750fed9e1f34304bb',
'md5': 'e009ea6b849b129e3bebaeb9cf0dee51',
'info_dict': {
'id': '1509445',
'display_id': 'femaleagent-shy-beauty-takes-the-bait',
@ -43,6 +43,11 @@ class XHamsterIE(InfoExtractor):
'uploader_id': 'ruseful2011',
'duration': 893,
'age_limit': 18,
'thumbnail': 'https://thumb-nss.xhcdn.com/a/u3Vr5F2vvcU3yK59_jJqVA/001/509/445/1280x720.8.jpg',
'uploader_url': 'https://xhamster.com/users/ruseful2011',
'description': '',
'view_count': int,
'comment_count': int,
},
}, {
'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
@ -56,6 +61,10 @@ class XHamsterIE(InfoExtractor):
'uploader': 'jojo747400',
'duration': 200,
'age_limit': 18,
'description': '',
'view_count': int,
'thumbnail': 'https://thumb-nss.xhcdn.com/a/kk5nio_iR-h4Z3frfVtoDw/002/221/348/1280x720.4.jpg',
'comment_count': int,
},
'params': {
'skip_download': True,
@ -73,6 +82,11 @@ class XHamsterIE(InfoExtractor):
'uploader_id': 'parejafree',
'duration': 72,
'age_limit': 18,
'comment_count': int,
'uploader_url': 'https://xhamster.com/users/parejafree',
'description': '',
'view_count': int,
'thumbnail': 'https://thumb-nss.xhcdn.com/a/xc8MSwVKcsQeRRiTT-saMQ/005/667/973/1280x720.2.jpg',
},
'params': {
'skip_download': True,
@ -122,6 +136,9 @@ class XHamsterIE(InfoExtractor):
}, {
'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
'only_matching': True,
}, {
'url': 'https://xhamster20.desi/videos/my-verification-video-scottishmistress23-11937369',
'only_matching': True,
}]
def _real_extract(self, url):
@ -267,7 +284,7 @@ def get_height(s):
video, lambda x: x['rating']['likes'], int)),
'dislike_count': int_or_none(try_get(
video, lambda x: x['rating']['dislikes'], int)),
'comment_count': int_or_none(video.get('views')),
'comment_count': int_or_none(video.get('comments')),
'age_limit': age_limit if age_limit is not None else 18,
'categories': categories,
'formats': formats,

25
yt_dlp/extractor/xiaohongshu.py
View File

@ -5,6 +5,7 @@
int_or_none,
js_to_json,
url_or_none,
urlhandle_detect_ext,
)
from ..utils.traversal import traverse_obj
@ -46,7 +47,7 @@ def _real_extract(self, url):
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', display_id, transform_source=js_to_json)
note_info = traverse_obj(initial_state, ('note', 'noteDetailMap', display_id, 'note'))
video_info = traverse_obj(note_info, ('video', 'media', 'stream', ('h264', 'av1', 'h265'), ...))
video_info = traverse_obj(note_info, ('video', 'media', 'stream', ..., ...))
formats = []
for info in video_info:
@ -56,18 +57,32 @@ def _real_extract(self, url):
'height': ('height', {int_or_none}),
'vcodec': ('videoCodec', {str}),
'acodec': ('audioCodec', {str}),
'abr': ('audioBitrate', {int_or_none}),
'vbr': ('videoBitrate', {int_or_none}),
'abr': ('audioBitrate', {int_or_none(scale=1000)}),
'vbr': ('videoBitrate', {int_or_none(scale=1000)}),
'audio_channels': ('audioChannels', {int_or_none}),
'tbr': ('avgBitrate', {int_or_none}),
'tbr': ('avgBitrate', {int_or_none(scale=1000)}),
'format': ('qualityType', {str}),
'filesize': ('size', {int_or_none}),
'duration': ('duration', {float_or_none(scale=1000)}),
})
formats.extend(traverse_obj(info, (('mediaUrl', ('backupUrls', ...)), {
formats.extend(traverse_obj(info, (('masterUrl', ('backupUrls', ...)), {
lambda u: url_or_none(u) and {'url': u, **format_info}})))
if origin_key := traverse_obj(note_info, ('video', 'consumer', 'originVideoKey', {str})):
# Not using a head request because of false negatives
urlh = self._request_webpage(
f'https://sns-video-bd.xhscdn.com/{origin_key}', display_id,
'Checking original video availability', 'Original video is not available', fatal=False)
if urlh:
formats.append({
'format_id': 'direct',
'ext': urlhandle_detect_ext(urlh, default='mp4'),
'filesize': int_or_none(urlh.get_header('Content-Length')),
'url': urlh.url,
'quality': 1,
})
thumbnails = []
for image_info in traverse_obj(note_info, ('imageList', ...)):
thumbnail_info = traverse_obj(image_info, {

265
yt_dlp/extractor/youtube.py
View File

@ -1,4 +1,5 @@
import base64
import binascii
import calendar
import collections
import copy
@ -69,7 +70,14 @@
)
STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
STREAMING_DATA_PO_TOKEN = '__yt_dlp_po_token'
STREAMING_DATA_INITIAL_PO_TOKEN = '__yt_dlp_po_token'
PO_TOKEN_GUIDE_URL = 'https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide'
class _PoTokenContext(enum.Enum):
PLAYER = 'player'
GVS = 'gvs'
# any clients starting with _ cannot be explicitly requested by the user
INNERTUBE_CLIENTS = {
@ -81,7 +89,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
},
# Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
@ -94,7 +102,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
},
'web_embedded': {
@ -116,6 +124,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
},
# This client now requires sign-in for every video
@ -127,6 +136,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_AUTH': True,
'SUPPORTS_COOKIES': True,
},
@ -143,7 +153,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
},
# This client now requires sign-in for every video
'android_music': {
@ -159,7 +169,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_AUTH': True,
},
# This client now requires sign-in for every video
@ -176,7 +186,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_AUTH': True,
},
# YouTube Kids videos aren't returned on this client for some reason
@ -202,16 +212,16 @@
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS',
'clientVersion': '19.45.4',
'clientVersion': '20.03.02',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtube/19.45.4 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
'userAgent': 'com.google.ios.youtube/20.03.02 (iPhone16,2; U; CPU iOS 18_2_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '18.1.0.22B83',
'osVersion': '18.2.1.22C161',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_JS_PLAYER': False,
},
# This client now requires sign-in for every video
@ -229,6 +239,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'REQUIRE_JS_PLAYER': False,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_AUTH': True,
},
# This client now requires sign-in for every video
@ -246,6 +257,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
'REQUIRE_JS_PLAYER': False,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'REQUIRE_AUTH': True,
},
# mweb has 'ultralow' formats
@ -260,14 +272,15 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
'REQUIRE_PO_TOKEN': True,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
},
'tv': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5',
'clientVersion': '7.20241201.18.00',
'clientVersion': '7.20250120.19.00',
'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
@ -313,7 +326,7 @@ def build_innertube_clients():
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
ytcfg.setdefault('REQUIRE_PO_TOKEN', False)
ytcfg.setdefault('PO_TOKEN_REQUIRED_CONTEXTS', [])
ytcfg.setdefault('REQUIRE_AUTH', False)
ytcfg.setdefault('SUPPORTS_COOKIES', False)
ytcfg.setdefault('PLAYER_PARAMS', None)
@ -849,11 +862,15 @@ def _download_ytcfg(self, client, video_id):
'web': 'https://www.youtube.com',
'web_music': 'https://music.youtube.com',
'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1',
'tv': 'https://www.youtube.com/tv',
}.get(client)
if not url:
return {}
webpage = self._download_webpage(
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config',
headers=traverse_obj(self._get_default_ytcfg(client), {
'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}),
}))
return self.extract_ytcfg(video_id, webpage) or {}
@staticmethod
@ -1423,8 +1440,8 @@ 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')
_DEFAULT_CLIENTS = ('ios', 'tv')
_DEFAULT_AUTHED_CLIENTS = ('web_creator', 'tv')
_DEFAULT_CLIENTS = ('tv', 'ios', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv', 'web')
_GEO_BYPASS = False
@ -2629,16 +2646,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'timestamp': 1657627949,
'release_date': '20220712',
'channel_url': 'https://www.youtube.com/channel/UCSJ4gkVC6NrvII8umztf0Ow',
'description': 'md5:13a6f76df898f5674f9127139f3df6f7',
'description': 'md5:452d5c82f72bb7e62a4e0297c3f01c23',
'age_limit': 0,
'thumbnail': 'https://i.ytimg.com/vi/jfKfPfyJRdk/maxresdefault.jpg',
'release_timestamp': 1657641570,
'uploader_url': 'https://www.youtube.com/@LofiGirl',
'channel_follower_count': int,
'channel_is_verified': True,
'title': r're:^lofi hip hop radio 📚 - beats to relax/study to',
'title': r're:^lofi hip hop radio 📚 beats to relax/study to',
'view_count': int,
'live_status': 'is_live',
'media_type': 'livestream',
'tags': 'count:32',
'channel': 'Lofi Girl',
'availability': 'public',
@ -2799,6 +2817,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'skip': 'Age-restricted; requires authentication',
},
{
'note': 'Support /live/ URL + media type for post-live content',
'url': 'https://www.youtube.com/live/qVv6vCqciTM',
'info_dict': {
'id': 'qVv6vCqciTM',
@ -2821,6 +2840,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
'categories': ['Entertainment'],
'live_status': 'was_live',
'media_type': 'livestream',
'release_timestamp': 1671793345,
'channel': 'さなちゃんねる',
'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
@ -3833,53 +3853,105 @@ def _generate_player_context(cls, sts=None):
**cls._get_checkok_params(),
}
def _get_config_po_token(self, client):
def _get_config_po_token(self, client: str, context: _PoTokenContext):
po_token_strs = self._configuration_arg('po_token', [], ie_key=YoutubeIE, casesense=True)
for token_str in po_token_strs:
po_token_client, sep, po_token = token_str.partition('+')
po_token_meta, sep, po_token = token_str.partition('+')
if not sep:
self.report_warning(
f'Invalid po_token configuration format. Expected "client+po_token", got "{token_str}"', only_once=True)
f'Invalid po_token configuration format. '
f'Expected "CLIENT.CONTEXT+PO_TOKEN", got "{token_str}"', only_once=True)
continue
if po_token_client == client:
return po_token
def fetch_po_token(self, client='web', visitor_data=None, data_sync_id=None, player_url=None, **kwargs):
# PO Token is bound to visitor_data / Visitor ID when logged out. Must have visitor_data for it to function.
if not visitor_data and not self.is_authenticated and player_url:
po_token_client, sep, po_token_context = po_token_meta.partition('.')
if po_token_client.lower() != client:
continue
if not sep:
# TODO(future): deprecate the old format?
self.write_debug(
f'po_token configuration for {client} client is missing a context; assuming GVS. '
'You can provide a context with the format "CLIENT.CONTEXT+PO_TOKEN"',
only_once=True)
po_token_context = _PoTokenContext.GVS.value
if po_token_context.lower() != context.value:
continue
# Clean and validate the PO Token. This will strip invalid characters off
# (e.g. additional url params the user may accidentally include)
try:
return base64.urlsafe_b64encode(base64.urlsafe_b64decode(urllib.parse.unquote(po_token))).decode()
except (binascii.Error, ValueError):
self.report_warning(
f'Invalid po_token configuration for {client} client: '
f'{po_token_context} PO Token should be a base64url-encoded string.',
only_once=True)
continue
def fetch_po_token(self, client='web', context=_PoTokenContext.GVS, ytcfg=None, visitor_data=None,
data_sync_id=None, session_index=None, player_url=None, video_id=None, **kwargs):
"""
Fetch a PO Token for a given client and context. This function will validate required parameters for a given context and client.
EXPERIMENTAL: This method is unstable and may change or be removed without notice.
@param client: The client to fetch the PO Token for.
@param context: The context in which the PO Token is used.
@param ytcfg: The ytcfg for the client.
@param visitor_data: visitor data.
@param data_sync_id: data sync ID.
@param session_index: session index.
@param player_url: player URL.
@param video_id: video ID.
@param kwargs: Additional arguments to pass down. May be more added in the future.
@return: The fetched PO Token. None if it could not be fetched.
"""
# GVS WebPO Token is bound to visitor_data / Visitor ID when logged out.
# Must have visitor_data for it to function.
if player_url and context == _PoTokenContext.GVS and not visitor_data and not self.is_authenticated:
self.report_warning(
f'Unable to fetch PO Token for {client} client: Missing required Visitor Data. '
f'Unable to fetch GVS PO Token for {client} client: Missing required Visitor Data. '
f'You may need to pass Visitor Data with --extractor-args "youtube:visitor_data=XXX"')
return
config_po_token = self._get_config_po_token(client)
if context == _PoTokenContext.PLAYER and not video_id:
self.report_warning(
f'Unable to fetch Player PO Token for {client} client: Missing required Video ID')
return
config_po_token = self._get_config_po_token(client, context)
if config_po_token:
# PO token is bound to data_sync_id / account Session ID when logged in. However, for the config po_token,
# if using first channel in an account then we don't need the data_sync_id anymore...
if not data_sync_id and self.is_authenticated and player_url:
# GVS WebPO token is bound to data_sync_id / account Session ID when logged in.
if player_url and context == _PoTokenContext.GVS and not data_sync_id and self.is_authenticated:
self.report_warning(
f'Got a PO Token for {client} client, but missing Data Sync ID for account. Formats may not work.'
f'Got a GVS PO Token for {client} client, but missing Data Sync ID for account. Formats may not work.'
f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"')
return config_po_token
# Require PO Token if logged in for external fetching
if not data_sync_id and self.is_authenticated and player_url:
# Require GVS WebPO Token if logged in for external fetching
if player_url and context == _PoTokenContext.GVS and not data_sync_id and self.is_authenticated:
self.report_warning(
f'Unable to fetch PO Token for {client} client: Missing required Data Sync ID for account. '
f'Unable to fetch GVS PO Token for {client} client: Missing required Data Sync ID for account. '
f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"')
return
return self._fetch_po_token(
client=client,
context=context.value,
ytcfg=ytcfg,
visitor_data=visitor_data,
data_sync_id=data_sync_id,
session_index=session_index,
player_url=player_url,
video_id=video_id,
**kwargs,
)
def _fetch_po_token(self, client, visitor_data=None, data_sync_id=None, player_url=None, **kwargs):
"""External PO Token fetch stub"""
def _fetch_po_token(self, client, **kwargs):
"""(Unstable) External PO Token fetch stub"""
@staticmethod
def _is_agegated(player_response):
@ -3960,16 +4032,10 @@ def _get_requested_clients(self, url, smuggled_data):
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):
for requested_client in requested_clients:
_, base_client, variant = _split_innertube_client(requested_client)
music_client = f'{base_client}_music' if base_client != 'mweb' else 'web_music'
if variant != 'music' and music_client in INNERTUBE_CLIENTS:
client_info = INNERTUBE_CLIENTS[music_client]
if not client_info['REQUIRE_AUTH'] or (self.is_authenticated and client_info['SUPPORTS_COOKIES']):
requested_clients.append(music_client)
if self.is_authenticated:
if (smuggled_data.get('is_music_url') or self.is_music_url(url)) and 'web_music' not in requested_clients:
requested_clients.append('web_music')
unsupported_clients = [
client for client in requested_clients if not INNERTUBE_CLIENTS[client]['SUPPORTS_COOKIES']
]
@ -4036,17 +4102,47 @@ def append_client(*client_names):
visitor_data = visitor_data or self._extract_visitor_data(master_ytcfg, initial_pr, player_ytcfg)
data_sync_id = data_sync_id or self._extract_data_sync_id(master_ytcfg, initial_pr, player_ytcfg)
po_token = self.fetch_po_token(
client=client, visitor_data=visitor_data,
data_sync_id=data_sync_id if self.is_authenticated else None,
player_url=player_url if require_js_player else None,
)
require_po_token = self._get_default_ytcfg(client).get('REQUIRE_PO_TOKEN')
if not po_token and require_po_token and 'missing_pot' in self._configuration_arg('formats'):
fetch_po_token_args = {
'client': client,
'visitor_data': visitor_data,
'video_id': video_id,
'data_sync_id': data_sync_id if self.is_authenticated else None,
'player_url': player_url if require_js_player else None,
'session_index': self._extract_session_index(master_ytcfg, player_ytcfg),
'ytcfg': player_ytcfg,
}
player_po_token = self.fetch_po_token(
context=_PoTokenContext.PLAYER, **fetch_po_token_args)
gvs_po_token = self.fetch_po_token(
context=_PoTokenContext.GVS, **fetch_po_token_args)
required_pot_contexts = self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
if (
not player_po_token
and _PoTokenContext.PLAYER in required_pot_contexts
):
# TODO: may need to skip player response request. Unsure yet..
self.report_warning(
f'No PO Token provided for {client} client, '
f'which may be required for working {client} formats. This client will be deprioritized', only_once=True)
f'No Player PO Token provided for {client} client, '
f'which may be required for working {client} formats. This client will be deprioritized'
f'You can manually pass a Player PO Token for this client with --extractor-args "youtube:po_token={client}.player+XXX". '
f'For more information, refer to {PO_TOKEN_GUIDE_URL} .', only_once=True)
deprioritize_pr = True
if (
not gvs_po_token
and _PoTokenContext.GVS in required_pot_contexts
and 'missing_pot' in self._configuration_arg('formats')
):
# note: warning with help message is provided later during format processing
self.report_warning(
f'No GVS PO Token provided for {client} client, '
f'which may be required for working {client} formats. This client will be deprioritized',
only_once=True)
deprioritize_pr = True
pr = initial_pr if client == 'web' else None
@ -4059,7 +4155,7 @@ def append_client(*client_names):
initial_pr=initial_pr,
visitor_data=visitor_data,
data_sync_id=data_sync_id,
po_token=po_token)
po_token=player_po_token)
except ExtractorError as e:
self.report_warning(e)
continue
@ -4070,36 +4166,24 @@ def append_client(*client_names):
# Save client name for introspection later
sd = traverse_obj(pr, ('streamingData', {dict})) or {}
sd[STREAMING_DATA_CLIENT_NAME] = client
sd[STREAMING_DATA_PO_TOKEN] = po_token
sd[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
f[STREAMING_DATA_CLIENT_NAME] = client
f[STREAMING_DATA_PO_TOKEN] = po_token
f[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
if deprioritize_pr:
deprioritized_prs.append(pr)
else:
prs.append(pr)
# web_embedded can work around age-gate and age-verification for some embeddable videos
if self._is_agegated(pr) and variant != 'web_embedded':
append_client(f'web_embedded.{base_client}')
# Unauthenticated users will only get web_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)
''' This code is pointless while web_creator is in _DEFAULT_AUTHED_CLIENTS
# 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
embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr)
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
if self.is_authenticated and self._is_agegated(pr):
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 can work around the age-verification requirement
# tv_embedded may(?) still work around age-verification if the video is embeddable
append_client('web_creator')
'''
# tv_embedded can work around the age-verification requirement for embeddable videos
# web_creator may work around age-verification for all videos but requires PO token
append_client('tv_embedded', 'web_creator')
prs.extend(deprioritized_prs)
@ -4121,10 +4205,10 @@ def _needs_live_processing(self, live_status, duration):
def _report_pot_format_skipped(self, video_id, client_name, proto):
msg = (
f'{video_id}: {client_name} client {proto} formats require a PO Token which was not provided. '
f'{video_id}: {client_name} client {proto} formats require a GVS PO Token which was not provided. '
'They will be skipped as they may yield HTTP Error 403. '
f'You can manually pass a PO Token for this client with --extractor-args "youtube:po_token={client_name}+XXX". '
'For more information, refer to https://github.com/yt-dlp/yt-dlp/wiki/Extractors#po-token-guide . '
f'You can manually pass a GVS PO Token for this client with --extractor-args "youtube:po_token={client_name}.gvs+XXX". '
f'For more information, refer to {PO_TOKEN_GUIDE_URL} . '
'To enable these broken formats anyway, pass --extractor-args "youtube:formats=missing_pot"')
# Only raise a warning for non-default clients, to not confuse users.
@ -4254,13 +4338,17 @@ def build_fragments(f):
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt[STREAMING_DATA_CLIENT_NAME]
po_token = fmt.get(STREAMING_DATA_PO_TOKEN)
po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)
if po_token:
fmt_url = update_url_query(fmt_url, {'pot': po_token})
# Clients that require PO Token return videoplayback URLs that may return 403
require_po_token = (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN'))
require_po_token = (
not po_token
and _PoTokenContext.GVS in self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
and itag not in ['18']) # these formats do not require PO Token
if require_po_token and 'missing_pot' not in self._configuration_arg('formats'):
self._report_pot_format_skipped(video_id, client_name, 'https')
continue
@ -4349,7 +4437,11 @@ def process_manifest_format(f, proto, client_name, itag, po_token):
# Clients that require PO Token return videoplayback URLs that may return 403
# hls does not currently require PO Token
if (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN')) and proto != 'hls':
if (
not po_token
and _PoTokenContext.GVS in self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
and proto != 'hls'
):
if 'missing_pot' not in self._configuration_arg('formats'):
self._report_pot_format_skipped(video_id, client_name, proto)
return False
@ -4390,7 +4482,7 @@ def process_manifest_format(f, proto, client_name, itag, po_token):
subtitles = {}
for sd in streaming_data:
client_name = sd[STREAMING_DATA_CLIENT_NAME]
po_token = sd.get(STREAMING_DATA_PO_TOKEN)
po_token = sd.get(STREAMING_DATA_INITIAL_PO_TOKEN)
hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
if hls_manifest_url:
if po_token:
@ -4717,6 +4809,7 @@ def is_bad_format(fmt):
'tags': keywords,
'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
'live_status': live_status,
'media_type': 'livestream' if get_first(video_details, 'isLiveContent') else None,
'release_timestamp': live_start_time,
'_format_sort_fields': ( # source_preference is lower for potentially damaged formats
'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang', 'proto'),
@ -5281,10 +5374,12 @@ def _rich_entries(self, rich_grid_renderer):
yield self.url_result(
f'https://www.youtube.com/shorts/{video_id}',
ie=YoutubeIE, video_id=video_id,
**traverse_obj(renderer, ('overlayMetadata', {
'title': ('primaryText', 'content', {str}),
'view_count': ('secondaryText', 'content', {parse_count}),
})),
**traverse_obj(renderer, {
'title': ((
('overlayMetadata', 'primaryText', 'content', {str}),
('accessibilityText', {lambda x: re.fullmatch(r'(.+), (?:[\d,.]+(?:[KM]| million)?|No) views? - play Short', x)}, 1)), any),
'view_count': ('overlayMetadata', 'secondaryText', 'content', {parse_count}),
}),
thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources'))
return

76
yt_dlp/extractor/zdf.py
View File

@ -5,7 +5,6 @@
NO_DEFAULT,
ExtractorError,
determine_ext,
extract_attributes,
float_or_none,
int_or_none,
join_nonempty,
@ -25,6 +24,11 @@ class ZDFBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['DE']
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd', 'fhd', 'uhd')
def _download_v2_doc(self, document_id):
return self._download_json(
f'https://zdf-prod-futura.zdf.de/mediathekV2/document/{document_id}',
document_id)
def _call_api(self, url, video_id, item, api_token=None, referrer=None):
headers = {}
if api_token:
@ -320,9 +324,7 @@ def _extract_regular(self, url, player, video_id):
return self._extract_entry(player['content'], player, content, video_id)
def _extract_mobile(self, video_id):
video = self._download_json(
f'https://zdf-cdn.live.cellular.de/mediathekV2/document/{video_id}',
video_id)
video = self._download_v2_doc(video_id)
formats = []
formitaeten = try_get(video, lambda x: x['document']['formitaeten'], list)
@ -374,7 +376,7 @@ def _real_extract(self, url):
class ZDFChannelIE(ZDFBaseIE):
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/?#]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
'info_dict': {
@ -387,18 +389,19 @@ class ZDFChannelIE(ZDFBaseIE):
'info_dict': {
'id': 'planet-e',
'title': 'planet e.',
'description': 'md5:87e3b9c66a63cf1407ee443d2c4eb88e',
},
'playlist_mincount': 50,
}, {
'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
'info_dict': {
'id': 'aktenzeichen-xy-ungeloest',
'title': 'Aktenzeichen XY... ungelöst',
'entries': "lambda x: not any('xy580-fall1-kindermoerder-gesucht-100' in e['url'] for e in x)",
'title': 'Aktenzeichen XY... Ungelöst',
'description': 'md5:623ede5819c400c6d04943fa8100e6e7',
},
'playlist_mincount': 2,
}, {
'url': 'https://www.zdf.de/filme/taunuskrimi/',
'url': 'https://www.zdf.de/serien/taunuskrimi/',
'only_matching': True,
}]
@ -406,36 +409,41 @@ class ZDFChannelIE(ZDFBaseIE):
def suitable(cls, url):
return False if ZDFIE.suitable(url) else super().suitable(url)
def _og_search_title(self, webpage, fatal=False):
title = super()._og_search_title(webpage, fatal=fatal)
return re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', title or '')[0] or None
def _extract_entry(self, entry):
return self.url_result(
entry['sharingUrl'], ZDFIE, **traverse_obj(entry, {
'id': ('basename', {str}),
'title': ('titel', {str}),
'description': ('beschreibung', {str}),
'duration': ('length', {float_or_none}),
# TODO: seasonNumber and episodeNumber can be extracted but need to also be in ZDFIE
}))
def _entries(self, data, document_id):
for entry in traverse_obj(data, (
'cluster', lambda _, v: v['type'] == 'teaser',
# If 'brandId' differs, it is a 'You might also like' video. Filter these out
'teaser', lambda _, v: v['type'] == 'video' and v['brandId'] == document_id and v['sharingUrl'],
)):
yield self._extract_entry(entry)
def _real_extract(self, url):
channel_id = self._match_id(url)
webpage = self._download_webpage(url, channel_id)
document_id = self._search_regex(
r'docId\s*:\s*(["\'])(?P<doc_id>(?:(?!\1).)+)\1', webpage, 'document id', group='doc_id')
data = self._download_v2_doc(document_id)
matches = re.finditer(
rf'''<div\b[^>]*?\sdata-plusbar-id\s*=\s*(["'])(?P<p_id>[\w-]+)\1[^>]*?\sdata-plusbar-url=\1(?P<url>{ZDFIE._VALID_URL})\1''',
webpage)
main_video = traverse_obj(data, (
'cluster', lambda _, v: v['type'] == 'teaserContent',
'teaser', lambda _, v: v['type'] == 'video' and v['basename'] and v['sharingUrl'], any)) or {}
if self._downloader.params.get('noplaylist', False):
entry = next(
(self.url_result(m.group('url'), ie=ZDFIE.ie_key()) for m in matches),
None)
self.to_screen('Downloading just the main video because of --no-playlist')
if entry:
return entry
else:
self.to_screen(f'Downloading playlist {channel_id} - add --no-playlist to download just the main video')
if not self._yes_playlist(channel_id, main_video.get('basename')):
return self._extract_entry(main_video)
def check_video(m):
v_ref = self._search_regex(
r'''(<a\b[^>]*?\shref\s*=[^>]+?\sdata-target-id\s*=\s*(["']){}\2[^>]*>)'''.format(m.group('p_id')),
webpage, 'check id', default='')
v_ref = extract_attributes(v_ref)
return v_ref.get('data-target-video-type') != 'novideo'
return self.playlist_from_matches(
(m.group('url') for m in matches if check_video(m)),
channel_id, self._og_search_title(webpage, fatal=False))
return self.playlist_result(
self._entries(data, document_id), channel_id,
re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', self._og_search_title(webpage) or '')[0] or None,
join_nonempty(
'headline', 'text', delim='\n\n',
from_dict=traverse_obj(data, ('shortText', {dict}), default={})) or None)

11
yt_dlp/utils/_utils.py
View File

@ -685,7 +685,8 @@ def _sanitize_path_parts(parts):
elif part == '..':
if sanitized_parts and sanitized_parts[-1] != '..':
sanitized_parts.pop()
sanitized_parts.append('..')
else:
sanitized_parts.append('..')
continue
# Replace invalid segments with `#`
# - trailing dots and spaces (`asdf...` => `asdf..#`)
@ -702,7 +703,8 @@ def sanitize_path(s, force=False):
if not force:
return s
root = '/' if s.startswith('/') else ''
return root + '/'.join(_sanitize_path_parts(s.split('/')))
path = '/'.join(_sanitize_path_parts(s.split('/')))
return root + path if root or path else '.'
normed = s.replace('/', '\\')
@ -721,7 +723,8 @@ def sanitize_path(s, force=False):
root = '\\' if normed[:1] == '\\' else ''
parts = normed.split('\\')
return root + '\\'.join(_sanitize_path_parts(parts))
path = '\\'.join(_sanitize_path_parts(parts))
return root + path if root or path else '.'
def sanitize_url(url, *, scheme='http'):
@ -5330,7 +5333,7 @@ class FormatSorter:
settings = {
'vcodec': {'type': 'ordered', 'regex': True,
'order': ['av0?1', 'vp0?9.0?2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']},
'order': ['av0?1', r'vp0?9\.0?2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']},
'acodec': {'type': 'ordered', 'regex': True,
'order': ['[af]lac', 'wav|aiff', 'opus', 'vorbis|ogg', 'aac', 'mp?4a?', 'mp3', 'ac-?4', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']},
'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range',

6
yt_dlp/version.py
View File

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2025.01.12'
__version__ = '2025.01.26'
RELEASE_GIT_HEAD = 'dade5e35c89adaad04408bfef766820dbca06ebe'
RELEASE_GIT_HEAD = '3b4531934465580be22937fecbb6e1a3a9e2334f'
VARIANT = None
@ -12,4 +12,4 @@
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2025.01.12'
_pkg_version = '2025.01.26'