diff --git a/.gitignore b/.gitignore index fdd904f7fe..8fcd0de641 100644 --- a/.gitignore +++ b/.gitignore @@ -92,6 +92,7 @@ updates_key.pem *.class *.isorted *.stackdump +uv.lock # Generated AUTHORS diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 0102264180..7376b18015 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -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 diff --git a/Changelog.md b/Changelog.md index cf9806ea11..3232c158b5 100644 --- a/Changelog.md +++ b/Changelog.md @@ -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 diff --git a/README.md b/README.md index 2f848bd132..45c56434ab 100644 --- a/README.md +++ b/README.md @@ -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` diff --git a/devscripts/changelog_override.json b/devscripts/changelog_override.json index 079e2f7296..8aa7b7e2bc 100644 --- a/devscripts/changelog_override.json +++ b/devscripts/changelog_override.json @@ -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"] } ] diff --git a/supportedsites.md b/supportedsites.md index 1420742d17..70909ef002 100644 --- a/supportedsites.md +++ b/supportedsites.md @@ -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** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 6b022a7eaa..17e081bc6e 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -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({}) diff --git a/test/test_utils.py b/test/test_utils.py index b3de14198e..8f81d0b1b7 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -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') diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index f6155dd2e9..b7b19cf6e0 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -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: diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 84723bff51..711ddc1a13 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -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 ( diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py index b1343eed39..8c7131b10a 100644 --- a/yt_dlp/extractor/abematv.py +++ b/yt_dlp/extractor/abematv.py @@ -421,14 +421,15 @@ def _real_extract(self, url): class AbemaTVTitleIE(AbemaTVBaseIE): - _VALID_URL = r'https?://abema\.tv/video/title/(?P[^?/]+)' + _VALID_URL = r'https?://abema\.tv/video/title/(?P[^?/#]+)/?(?:\?(?:[^#]+&)?s=(?P[^&#]+))?' _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')) diff --git a/yt_dlp/extractor/acast.py b/yt_dlp/extractor/acast.py index 8f4a2cf0f8..eb467cb754 100644 --- a/yt_dlp/extractor/acast.py +++ b/yt_dlp/extractor/acast.py @@ -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[^/]+)/(?P[^/#?"]+) + (?P[^/?#]+)/(?:episodes/)?(?P[^/#?"]+) )''' _EMBED_REGEX = [rf'(?x)]+\bsrc=[\'"](?P{_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[^/#?]+) @@ -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 diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 2db951a608..42b4e2d3c2 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -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\d+)(?P