mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-05-12 16:25:42 -05:00
Code Activity

Merge branch 'master' into handle-infinite-redirects

Browse source
This commit is contained in:
Adam Miller 2025-01-22 16:19:35 -08:00
commit 4c4f2aa81b
27 changed files with 993 additions and 414 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
CONTRIBUTORS
View file

@ -713,3 +713,5 @@ xiaomac
wesson09
Crypto90
MutantPiggieGolem1
Sanceilaks
Strkmn

24
Changelog.md
View file

@ -4,6 +4,30 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 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
- [Fix filename sanitization with `--no-windows-filenames`](https://github.com/yt-dlp/yt-dlp/commit/8346b549150003df988538e54c9d8bc4de568979) ([#11988](https://github.com/yt-dlp/yt-dlp/issues/11988)) by [bashonly](https://github.com/bashonly)
- [Validate retries values are non-negative](https://github.com/yt-dlp/yt-dlp/commit/1f4e1e85a27c5b43e34d7706cfd88ffce1b56a4a) ([#11927](https://github.com/yt-dlp/yt-dlp/issues/11927)) by [Strkmn](https://github.com/Strkmn)
#### Extractor changes
- **drtalks**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1f489f4a45691cac3f9e787d22a3a8a086229ba6) ([#10831](https://github.com/yt-dlp/yt-dlp/issues/10831)) by [pzhlkj6612](https://github.com/pzhlkj6612), [seproDev](https://github.com/seproDev)
- **plvideo**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3c14e9191f3035b9a729d1d87bc0381f42de57cf) ([#10657](https://github.com/yt-dlp/yt-dlp/issues/10657)) by [Sanceilaks](https://github.com/Sanceilaks), [seproDev](https://github.com/seproDev)
- **vine**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/e2ef4fece6c9742d1733e3bae408c4787765f78c) ([#11700](https://github.com/yt-dlp/yt-dlp/issues/11700)) by [allendema](https://github.com/allendema)
- **xiaohongshu**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/763ed06ee69f13949397897bd42ff2ec3dc3d384) ([#11806](https://github.com/yt-dlp/yt-dlp/issues/11806)) by [HobbyistDev](https://github.com/HobbyistDev)
- **youtube**
- [Fix DASH formats incorrectly skipped in some situations](https://github.com/yt-dlp/yt-dlp/commit/0b6b7742c2e7f2a1fcb0b54ef3dd484bab404b3f) ([#11910](https://github.com/yt-dlp/yt-dlp/issues/11910)) by [coletdjnz](https://github.com/coletdjnz)
- [Refactor cookie auth](https://github.com/yt-dlp/yt-dlp/commit/75079f4e3f7dce49b61ef01da7adcd9876a0ca3b) ([#11989](https://github.com/yt-dlp/yt-dlp/issues/11989)) by [coletdjnz](https://github.com/coletdjnz)
- [Use `tv` instead of `mweb` client by default](https://github.com/yt-dlp/yt-dlp/commit/712d2abb32f59b2d246be2901255f84f1a4c30b3) ([#12059](https://github.com/yt-dlp/yt-dlp/issues/12059)) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- **cleanup**: Miscellaneous: [dade5e3](https://github.com/yt-dlp/yt-dlp/commit/dade5e35c89adaad04408bfef766820dbca06ebe) by [grqz](https://github.com/grqz), [Grub4K](https://github.com/Grub4K), [seproDev](https://github.com/seproDev)
### 2024.12.23
#### Core changes

2
README.md
View file

@ -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,mweb` is used, or `web_creator,mweb` 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 `_music` variants may be 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 `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)

3
pyproject.toml
View file

@ -76,7 +76,7 @@ dev = [
]
static-analysis = [
"autopep8~=2.0",
"ruff~=0.8.0",
"ruff~=0.9.0",
]
test = [
"pytest~=8.1",
@ -195,6 +195,7 @@ ignore = [
"B023", # function-uses-loop-variable (false positives)
"B028", # no-explicit-stacklevel
"B904", # raise-without-from-inside-except
"A005", # stdlib-module-shadowing
"C401", # unnecessary-generator-set
"C402", # unnecessary-generator-dict
"PIE790", # unnecessary-placeholder

4
supportedsites.md
View file

@ -374,6 +374,7 @@ # Supported sites
- **Dropbox**
- **Dropout**: [*dropout*](## "netrc machine")
- **DropoutSeason**
- **DrTalks**
- **DrTuber**
- **drtv**
- **drtv:live**
@ -1086,6 +1087,7 @@ # Supported sites
- **pluralsight**: [*pluralsight*](## "netrc machine")
- **pluralsight:course**
- **PlutoTV**: (**Currently broken**)
- **PlVideo**: Платформа
- **PodbayFM**
- **PodbayFMChannel**
- **Podchaser**
@ -1641,8 +1643,6 @@ # Supported sites
- **Vimm:stream**
- **ViMP**
- **ViMP:Playlist**
- **Vine**
- **vine:user**
- **Viously**
- **Viqeo**: (**Currently broken**)
- **Viu**

7
yt_dlp/YoutubeDL.py
View file

@ -283,7 +283,10 @@ class YoutubeDL:
lazy_playlist: Process playlist entries as they are received.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
logger: Log messages to a logging.Logger instance.
logger: A class having a `debug`, `warning` and `error` function where
each has a single string parameter, the message to be logged.
For compatibility reasons, both debug and info messages are passed to `debug`.
A debug message will have a prefix of `[debug] ` to discern it from info messages.
logtostderr: Print everything to stderr instead of stdout.
consoletitle: Display progress in the console window's titlebar.
writedescription: Write the video description to a .description file
@ -1323,7 +1326,7 @@ def filename_sanitizer(key, value, restricted):
elif (sys.platform != 'win32' and not self.params.get('restrictfilenames')
and self.params.get('windowsfilenames') is False):
def sanitize(key, value):
return value.replace('/', '\u29F8').replace('\0', '')
return str(value).replace('/', '\u29F8').replace('\0', '')
else:
def sanitize(key, value):
return filename_sanitizer(key, value, restricted=self.params.get('restrictfilenames'))

4
yt_dlp/__init__.py
View file

@ -261,9 +261,11 @@ def parse_retries(name, value):
elif value in ('inf', 'infinite'):
return float('inf')
try:
return int(value)
int_value = int(value)
except (TypeError, ValueError):
validate(False, f'{name} retry count', value)
validate_positive(f'{name} retry count', int_value)
return int_value
opts.retries = parse_retries('download', opts.retries)
opts.fragment_retries = parse_retries('fragment', opts.fragment_retries)

19
yt_dlp/extractor/_extractors.py
View file

@ -256,6 +256,7 @@
BilibiliCheeseIE,
BilibiliCheeseSeasonIE,
BilibiliCollectionListIE,
BiliBiliDynamicIE,
BilibiliFavoritesListIE,
BiliBiliIE,
BiliBiliPlayerIE,
@ -555,6 +556,7 @@
DropoutIE,
DropoutSeasonIE,
)
from .drtalks import DrTalksIE
from .drtuber import DrTuberIE
from .drtv import (
DRTVIE,
@ -584,6 +586,10 @@
EggheadCourseIE,
EggheadLessonIE,
)
from .eggs import (
EggsArtistIE,
EggsIE,
)
from .eighttracks import EightTracksIE
from .eitb import EitbIE
from .elementorembed import ElementorEmbedIE
@ -1278,6 +1284,10 @@
)
from .nekohacker import NekoHackerIE
from .nerdcubed import NerdCubedFeedIE
from .nest import (
NestClipIE,
NestIE,
)
from .neteasemusic import (
NetEaseMusicAlbumIE,
NetEaseMusicDjRadioIE,
@ -1532,6 +1542,10 @@
PinterestCollectionIE,
PinterestIE,
)
from .piramidetv import (
PiramideTVChannelIE,
PiramideTVIE,
)
from .pixivsketch import (
PixivSketchIE,
PixivSketchUserIE,
@ -1551,6 +1565,7 @@
PluralsightIE,
)
from .plutotv import PlutoTVIE
from .plvideo import PlVideoIE
from .podbayfm import (
PodbayFMChannelIE,
PodbayFMIE,
@ -2354,10 +2369,6 @@
VimmIE,
VimmRecordingIE,
)
from .vine import (
VineIE,
VineUserIE,
)
from .viously import ViouslyIE
from .viqeo import ViqeoIE
from .viu import (

42
yt_dlp/extractor/bilibili.py
View file

@ -32,6 +32,7 @@
parse_qs,
parse_resolution,
qualities,
sanitize_url,
smuggle_url,
srt_subtitles_timecode,
str_or_none,
@ -1861,6 +1862,47 @@ 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, {sanitize_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'

11
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$',
@ -341,6 +343,7 @@ 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', {

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 ''

51
yt_dlp/extractor/drtalks.py Normal file
View file

@ -0,0 +1,51 @@
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import url_or_none
from ..utils.traversal import traverse_obj
class DrTalksIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?drtalks\.com/videos/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://drtalks.com/videos/six-pillars-of-resilience-tools-for-managing-stress-and-flourishing/',
'info_dict': {
'id': '6366193757112',
'ext': 'mp4',
'uploader_id': '6314452011001',
'tags': ['resilience'],
'description': 'md5:9c6805aee237ee6de8052461855b9dda',
'timestamp': 1734546659,
'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/12/Episode-82-Eva-Selhub-DrTalks-Thumbs.jpg',
'title': 'Six Pillars of Resilience: Tools for Managing Stress and Flourishing',
'duration': 2800.682,
'upload_date': '20241218',
},
}, {
'url': 'https://drtalks.com/videos/the-pcos-puzzle-mastering-metabolic-health-with-marcelle-pick/',
'info_dict': {
'id': '6364699891112',
'ext': 'mp4',
'title': 'The PCOS Puzzle: Mastering Metabolic Health with Marcelle Pick',
'description': 'md5:e87cbe00ca50135d5702787fc4043aaa',
'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/11/Episode-34-Marcelle-Pick-OBGYN-NP-DrTalks.jpg',
'duration': 3515.2,
'tags': ['pcos'],
'upload_date': '20241114',
'timestamp': 1731592119,
'uploader_id': '6314452011001',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
next_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']['video']
return self.url_result(
next_data['videos']['brightcoveVideoLink'], BrightcoveNewIE, video_id,
url_transparent=True,
**traverse_obj(next_data, {
'title': ('title', {str}),
'description': ('videos', 'summury', {str}),
'thumbnail': ('featuredImage', 'node', 'sourceUrl', {url_or_none}),
}))

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}),
}))

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)

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}),
})),
}

3
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,
)
@ -171,6 +172,8 @@ def call_playback_api(item, query=None):
format_url = url_or_none(asset.get('url'))
if not format_url:
continue
# Remove the 'adap' query parameter
format_url = update_url_query(format_url, {'adap': []})
asset_format = (asset.get('format') or '').lower()
if asset_format == 'hls' or determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_nrk_formats(format_url, video_id))

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)

130
yt_dlp/extractor/plvideo.py Normal file
View file

@ -0,0 +1,130 @@
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
parse_resolution,
url_or_none,
)
from ..utils.traversal import traverse_obj
class PlVideoIE(InfoExtractor):
IE_DESC = 'Платформа'
_VALID_URL = r'https?://(?:www\.)?plvideo\.ru/(?:watch\?(?:[^#]+&)?v=|shorts/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://plvideo.ru/watch?v=Y5JzUzkcQTMK',
'md5': 'fe8e18aca892b3b31f3bf492169f8a26',
'info_dict': {
'id': 'Y5JzUzkcQTMK',
'ext': 'mp4',
'thumbnail': 'https://img.plvideo.ru/images/fp-2024-images/v/cover/37/dd/37dd00a4c96c77436ab737e85947abd7/original663a4a3bb713e5.33151959.jpg',
'title': 'Presidente de Cuba llega a Moscú en una visita de trabajo',
'channel': 'RT en Español',
'channel_id': 'ZH4EKqunVDvo',
'media_type': 'video',
'comment_count': int,
'tags': ['rusia', 'cuba', 'russia', 'miguel díaz-canel'],
'description': 'md5:a1a395d900d77a86542a91ee0826c115',
'released_timestamp': 1715096124,
'channel_is_verified': True,
'like_count': int,
'timestamp': 1715095911,
'duration': 44320,
'view_count': int,
'dislike_count': int,
'upload_date': '20240507',
'modified_date': '20240701',
'channel_follower_count': int,
'modified_timestamp': 1719824073,
},
}, {
'url': 'https://plvideo.ru/shorts/S3Uo9c-VLwFX',
'md5': '7d8fa2279406c69d2fd2a6fc548a9805',
'info_dict': {
'id': 'S3Uo9c-VLwFX',
'ext': 'mp4',
'channel': 'Romaatom',
'tags': 'count:22',
'dislike_count': int,
'upload_date': '20241130',
'description': 'md5:452e6de219bf2f32bb95806c51c3b364',
'duration': 58433,
'modified_date': '20241130',
'thumbnail': 'https://img.plvideo.ru/images/fp-2024-11-cover/S3Uo9c-VLwFX/f9318999-a941-482b-b700-2102a7049366.jpg',
'media_type': 'shorts',
'like_count': int,
'modified_timestamp': 1732961458,
'channel_is_verified': True,
'channel_id': 'erJyyTIbmUd1',
'timestamp': 1732961355,
'comment_count': int,
'title': 'Белоусов отменил приказы о кадровом резерве на гражданской службе',
'channel_follower_count': int,
'view_count': int,
'released_timestamp': 1732961458,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
f'https://api.g1.plvideo.ru/v1/videos/{video_id}?Aud=18', video_id)
is_live = False
formats = []
subtitles = {}
automatic_captions = {}
for quality, data in traverse_obj(video_data, ('item', 'profiles', {dict.items}, lambda _, v: url_or_none(v[1]['hls']))):
formats.append({
'format_id': quality,
'ext': 'mp4',
'protocol': 'm3u8_native',
**traverse_obj(data, {
'url': 'hls',
'fps': ('fps', {float_or_none}),
'aspect_ratio': ('aspectRatio', {float_or_none}),
}),
**parse_resolution(quality),
})
if livestream_url := traverse_obj(video_data, ('item', 'livestream', 'url', {url_or_none})):
is_live = True
formats.extend(self._extract_m3u8_formats(livestream_url, video_id, 'mp4', live=True))
for lang, url in traverse_obj(video_data, ('item', 'subtitles', {dict.items}, lambda _, v: url_or_none(v[1]))):
if lang.endswith('-auto'):
automatic_captions.setdefault(lang[:-5], []).append({
'url': url,
})
else:
subtitles.setdefault(lang, []).append({
'url': url,
})
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'automatic_captions': automatic_captions,
'is_live': is_live,
**traverse_obj(video_data, ('item', {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('cover', 'paths', 'original', 'src', {url_or_none}),
'duration': ('uploadFile', 'videoDuration', {int_or_none}),
'channel': ('channel', 'name', {str}),
'channel_id': ('channel', 'id', {str}),
'channel_follower_count': ('channel', 'stats', 'subscribers', {int_or_none}),
'channel_is_verified': ('channel', 'verified', {bool}),
'tags': ('tags', ..., {str}),
'timestamp': ('createdAt', {parse_iso8601}),
'released_timestamp': ('publishedAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
'view_count': ('stats', 'viewTotalCount', {int_or_none}),
'like_count': ('stats', 'likeCount', {int_or_none}),
'dislike_count': ('stats', 'dislikeCount', {int_or_none}),
'comment_count': ('stats', 'commentCount', {int_or_none}),
'media_type': ('type', {str}),
})),
}

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,
}

21
yt_dlp/extractor/tumblr.py
View file

@ -189,26 +189,6 @@ class TumblrIE(InfoExtractor):
'release_date': '20140227',
},
'add_ie': ['Vimeo'],
}, {
'url': 'http://sutiblr.tumblr.com/post/139638707273',
'md5': '2dd184b3669e049ba40563a7d423f95c',
'info_dict': {
'id': 'ir7qBEIKqvq',
'ext': 'mp4',
'title': 'Vine by sutiblr',
'alt_title': 'Vine by sutiblr',
'uploader': 'sutiblr',
'uploader_id': '1198993975374495744',
'upload_date': '20160220',
'like_count': int,
'comment_count': int,
'repost_count': int,
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1455940159,
'view_count': int,
},
'add_ie': ['Vine'],
'skip': 'Vine is unavailable',
}, {
'url': 'https://silami.tumblr.com/post/84250043974/my-bad-river-flows-in-you-impression-on-maschine',
'md5': '3c92d7c3d867f14ccbeefa2119022277',
@ -366,7 +346,6 @@ class TumblrIE(InfoExtractor):
_providers = {
'instagram': 'Instagram',
'vimeo': 'Vimeo',
'vine': 'Vine',
'youtube': 'Youtube',
'dailymotion': 'Dailymotion',
'tiktok': 'TikTok',

39
yt_dlp/extractor/twitter.py
View file

@ -409,26 +409,6 @@ class TwitterCardIE(InfoExtractor):
},
'add_ie': ['Youtube'],
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
'info_dict': {
'id': 'iBb2x00UVlv',
'ext': 'mp4',
'upload_date': '20151113',
'uploader_id': '1189339351084113920',
'uploader': 'ArsenalTerje',
'title': 'Vine by ArsenalTerje',
'timestamp': 1447451307,
'alt_title': 'Vine by ArsenalTerje',
'comment_count': int,
'like_count': int,
'thumbnail': r're:^https?://[^?#]+\.jpg',
'view_count': int,
'repost_count': int,
},
'add_ie': ['Vine'],
'params': {'skip_download': 'm3u8'},
},
{
'url': 'https://twitter.com/i/videos/tweet/705235433198714880',
'md5': '884812a2adc8aaf6fe52b15ccbfa3b88',
@ -567,25 +547,6 @@ class TwitterIE(TwitterBaseIE):
'age_limit': 0,
'_old_archive_ids': ['twitter 700207533655363584'],
},
}, {
'url': 'https://twitter.com/Filmdrunk/status/713801302971588609',
'md5': '89a15ed345d13b86e9a5a5e051fa308a',
'info_dict': {
'id': 'MIOxnrUteUd',
'ext': 'mp4',
'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン',
'uploader': 'TAKUMA',
'uploader_id': '1004126642786242560',
'timestamp': 1402826626,
'upload_date': '20140615',
'thumbnail': r're:^https?://.*\.jpg',
'alt_title': 'Vine by TAKUMA',
'comment_count': int,
'repost_count': int,
'like_count': int,
'view_count': int,
},
'add_ie': ['Vine'],
}, {
'url': 'https://twitter.com/captainamerica/status/719944021058060289',
'info_dict': {

150
yt_dlp/extractor/vine.py
View file

@ -1,150 +0,0 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
format_field,
int_or_none,
unified_timestamp,
)
class VineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))']
_TESTS = [{
'url': 'https://vine.co/v/b9KOOWX7HUx',
'md5': '2f36fed6235b16da96ce9b4dc890940d',
'info_dict': {
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'title': 'Chicken.',
'alt_title': 'Vine by Jack',
'timestamp': 1368997951,
'upload_date': '20130519',
'uploader': 'Jack',
'uploader_id': '76',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/e192BnZnZ9V',
'info_dict': {
'id': 'e192BnZnZ9V',
'ext': 'mp4',
'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2',
'alt_title': 'Vine by Pimry_zaa',
'timestamp': 1436057405,
'upload_date': '20150705',
'uploader': 'Pimry_zaa',
'uploader_id': '1135760698325307392',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
'only_matching': True,
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
'only_matching': True,
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
f'https://archive.vine.co/posts/{video_id}.json', video_id)
def video_url(kind):
for url_suffix in ('Url', 'URL'):
format_url = data.get(f'video{kind}{url_suffix}')
if format_url:
return format_url
formats = []
for quality, format_id in enumerate(('low', '', 'dash')):
format_url = video_url(format_id.capitalize())
if not format_url:
continue
# DASH link returns plain mp4
if format_id == 'dash' and determine_ext(format_url) == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
else:
formats.append({
'url': format_url,
'format_id': format_id or 'standard',
'quality': quality,
})
self._check_formats(formats, video_id)
username = data.get('username')
alt_title = format_field(username, None, 'Vine by %s')
return {
'id': video_id,
'title': data.get('description') or alt_title or 'Vine video',
'alt_title': alt_title,
'thumbnail': data.get('thumbnailUrl'),
'timestamp': unified_timestamp(data.get('created')),
'uploader': username,
'uploader_id': data.get('userIdStr'),
'view_count': int_or_none(data.get('loops')),
'like_count': int_or_none(data.get('likes')),
'comment_count': int_or_none(data.get('comments')),
'repost_count': int_or_none(data.get('reposts')),
'formats': formats,
}
class VineUserIE(InfoExtractor):
IE_NAME = 'vine:user'
_VALID_URL = r'https?://vine\.co/(?P<u>u/)?(?P<user>[^/]+)'
_VINE_BASE_URL = 'https://vine.co/'
_TESTS = [{
'url': 'https://vine.co/itsruthb',
'info_dict': {
'id': 'itsruthb',
'title': 'Ruth B',
'description': '| Instagram/Twitter: itsruthb | still a lost boy from neverland',
},
'playlist_mincount': 611,
}, {
'url': 'https://vine.co/u/942914934646415360',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if VineIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
user = mobj.group('user')
u = mobj.group('u')
profile_url = '{}api/users/profiles/{}{}'.format(
self._VINE_BASE_URL, 'vanity/' if not u else '', user)
profile_data = self._download_json(
profile_url, user, note='Downloading user profile data')
data = profile_data['data']
user_id = data.get('userId') or data['userIdStr']
profile = self._download_json(
f'https://archive.vine.co/profiles/{user_id}.json', user_id)
entries = [
self.url_result(
f'https://vine.co/v/{post_id}', ie='Vine', video_id=post_id)
for post_id in profile['posts']
if post_id and isinstance(post_id, str)]
return self.playlist_result(
entries, user, profile.get('username'), profile.get('description'))

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',

39
yt_dlp/extractor/xiaohongshu.py
View file

@ -5,12 +5,13 @@
int_or_none,
js_to_json,
url_or_none,
urlhandle_detect_ext,
)
from ..utils.traversal import traverse_obj
class XiaoHongShuIE(InfoExtractor):
_VALID_URL = r'https?://www\.xiaohongshu\.com/explore/(?P<id>[\da-f]+)'
_VALID_URL = r'https?://www\.xiaohongshu\.com/(?:explore|discovery/item)/(?P<id>[\da-f]+)'
IE_DESC = '小红书'
_TESTS = [{
'url': 'https://www.xiaohongshu.com/explore/6411cf99000000001300b6d9',
@ -25,6 +26,18 @@ class XiaoHongShuIE(InfoExtractor):
'duration': 101.726,
'thumbnail': r're:https?://sns-webpic-qc\.xhscdn\.com/\d+/[a-z0-9]+/[\w]+',
},
}, {
'url': 'https://www.xiaohongshu.com/discovery/item/674051740000000007027a15?xsec_token=CBgeL8Dxd1ZWBhwqRd568gAZ_iwG-9JIf9tnApNmteU2E=',
'info_dict': {
'id': '674051740000000007027a15',
'ext': 'mp4',
'title': '相互喜欢就可以了',
'uploader_id': '63439913000000001901f49a',
'duration': 28.073,
'description': '#广州[话题]# #深圳[话题]# #香港[话题]# #街头采访[话题]# #是你喜欢的类型[话题]#',
'thumbnail': r're:https?://sns-webpic-qc\.xhscdn\.com/\d+/[\da-f]+/[^/]+',
'tags': ['广州', '深圳', '香港', '街头采访', '是你喜欢的类型'],
},
}]
def _real_extract(self, url):
@ -34,7 +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:
@ -44,18 +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, {

216
yt_dlp/extractor/youtube.py
View file

@ -32,7 +32,6 @@
classproperty,
clean_html,
datetime_from_str,
dict_get,
filesize_from_tbr,
filter_dict,
float_or_none,
@ -117,6 +116,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
'REQUIRE_PO_TOKEN': True,
'SUPPORTS_COOKIES': True,
},
# This client now requires sign-in for every video
@ -128,6 +128,7 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
'SUPPORTS_COOKIES': True,
},
@ -212,8 +213,8 @@
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
},
# This client now requires sign-in for every video
'ios_music': {
@ -230,6 +231,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
},
# This client now requires sign-in for every video
@ -247,6 +249,7 @@
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
},
# mweb has 'ultralow' formats
@ -256,11 +259,12 @@
'client': {
'clientName': 'MWEB',
'clientVersion': '2.20241202.07.00',
# mweb does not require PO Token with this UA
# mweb previously did not require PO Token with this UA
'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
'REQUIRE_PO_TOKEN': True,
'SUPPORTS_COOKIES': True,
},
'tv': {
@ -567,9 +571,15 @@ def _initialize_pref(self):
pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
def _initialize_cookie_auth(self):
yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies()
if yt_sapisid or yt_1psapisid or yt_3psapisid:
self.write_debug('Found YouTube account cookies')
def _real_initialize(self):
self._initialize_pref()
self._initialize_consent()
self._initialize_cookie_auth()
self._check_login_required()
def _perform_login(self, username, password):
@ -627,32 +637,63 @@ def _extract_context(self, ytcfg=None, default_client='web'):
client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
return context
_SAPISID = None
@staticmethod
def _make_sid_authorization(scheme, sid, origin, additional_parts):
timestamp = str(round(time.time()))
def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
time_now = round(time.time())
if self._SAPISID is None:
hash_parts = []
if additional_parts:
hash_parts.append(':'.join(additional_parts.values()))
hash_parts.extend([timestamp, sid, origin])
sidhash = hashlib.sha1(' '.join(hash_parts).encode()).hexdigest()
parts = [timestamp, sidhash]
if additional_parts:
parts.append(''.join(additional_parts))
return f'{scheme} {"_".join(parts)}'
def _get_sid_cookies(self):
"""
Get SAPISID, 1PSAPISID, 3PSAPISID cookie values
@returns sapisid, 1psapisid, 3psapisid
"""
yt_cookies = self._get_cookies('https://www.youtube.com')
yt_sapisid = try_call(lambda: yt_cookies['SAPISID'].value)
yt_3papisid = try_call(lambda: yt_cookies['__Secure-3PAPISID'].value)
yt_1papisid = try_call(lambda: yt_cookies['__Secure-1PAPISID'].value)
# Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
# YouTube also falls back to __Secure-3PAPISID if SAPISID is missing.
# See: https://github.com/yt-dlp/yt-dlp/issues/393
sapisid_cookie = dict_get(
yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
if sapisid_cookie and sapisid_cookie.value:
self._SAPISID = sapisid_cookie.value
self.write_debug('Extracted SAPISID cookie')
# SAPISID cookie is required if not already present
if not yt_cookies.get('SAPISID'):
self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
self._set_cookie(
'.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
else:
self._SAPISID = False
if not self._SAPISID:
return yt_sapisid or yt_3papisid, yt_1papisid, yt_3papisid
def _get_sid_authorization_header(self, origin='https://www.youtube.com', user_session_id=None):
"""
Generate API Session ID Authorization for Innertube requests. Assumes all requests are secure (https).
@param origin: Origin URL
@param user_session_id: Optional User Session ID
@return: Authorization header value
"""
authorizations = []
additional_parts = {}
if user_session_id:
additional_parts['u'] = user_session_id
yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies()
for scheme, sid in (('SAPISIDHASH', yt_sapisid),
('SAPISID1PHASH', yt_1psapisid),
('SAPISID3PHASH', yt_3psapisid)):
if sid:
authorizations.append(self._make_sid_authorization(scheme, sid, origin, additional_parts))
if not authorizations:
return None
# SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
sapisidhash = hashlib.sha1(
f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
return f'SAPISIDHASH {time_now}_{sapisidhash}'
return ' '.join(authorizations)
def _call_api(self, ep, query, video_id, fatal=True, headers=None,
note='Downloading API JSON', errnote='Unable to download API page',
@ -688,26 +729,48 @@ def _extract_session_index(*data):
if session_index is not None:
return session_index
def _data_sync_id_to_delegated_session_id(self, data_sync_id):
if not data_sync_id:
return
# datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
# and just "user_syncid||" for primary channel. We only want the channel_syncid
channel_syncid, _, user_syncid = data_sync_id.partition('||')
if user_syncid:
return channel_syncid
def _extract_account_syncid(self, *args):
@staticmethod
def _parse_data_sync_id(data_sync_id):
"""
Extract current session ID required to download private playlists of secondary channels
Parse data_sync_id into delegated_session_id and user_session_id.
data_sync_id is of the form "delegated_session_id||user_session_id" for secondary channel
and just "user_session_id||" for primary channel.
@param data_sync_id: data_sync_id string
@return: Tuple of (delegated_session_id, user_session_id)
"""
if not data_sync_id:
return None, None
first, _, second = data_sync_id.partition('||')
if second:
return first, second
return None, first
def _extract_delegated_session_id(self, *args):
"""
Extract current delegated session ID required to download private playlists of secondary channels
@params response and/or ytcfg
@return: delegated session ID
"""
# ytcfg includes channel_syncid if on secondary channel
if delegated_sid := traverse_obj(args, (..., 'DELEGATED_SESSION_ID', {str}, any)):
return delegated_sid
data_sync_id = self._extract_data_sync_id(*args)
return self._data_sync_id_to_delegated_session_id(data_sync_id)
return self._parse_data_sync_id(data_sync_id)[0]
def _extract_user_session_id(self, *args):
"""
Extract current user session ID
@params response and/or ytcfg
@return: user session ID
"""
if user_sid := traverse_obj(args, (..., 'USER_SESSION_ID', {str}, any)):
return user_sid
data_sync_id = self._extract_data_sync_id(*args)
return self._parse_data_sync_id(data_sync_id)[1]
def _extract_data_sync_id(self, *args):
"""
@ -734,7 +797,7 @@ def _extract_visitor_data(self, *args):
@functools.cached_property
def is_authenticated(self):
return bool(self._generate_sapisidhash_header())
return bool(self._get_sid_authorization_header())
def extract_ytcfg(self, video_id, webpage):
if not webpage:
@ -744,25 +807,28 @@ def extract_ytcfg(self, video_id, webpage):
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), video_id, fatal=False) or {}
def _generate_cookie_auth_headers(self, *, ytcfg=None, account_syncid=None, session_index=None, origin=None, **kwargs):
def _generate_cookie_auth_headers(self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, origin=None, **kwargs):
headers = {}
account_syncid = account_syncid or self._extract_account_syncid(ytcfg)
if account_syncid:
headers['X-Goog-PageId'] = account_syncid
delegated_session_id = delegated_session_id or self._extract_delegated_session_id(ytcfg)
if delegated_session_id:
headers['X-Goog-PageId'] = delegated_session_id
if session_index is None:
session_index = self._extract_session_index(ytcfg)
if account_syncid or session_index is not None:
if delegated_session_id or session_index is not None:
headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
auth = self._generate_sapisidhash_header(origin)
auth = self._get_sid_authorization_header(origin, user_session_id=user_session_id or self._extract_user_session_id(ytcfg))
if auth is not None:
headers['Authorization'] = auth
headers['X-Origin'] = origin
if traverse_obj(ytcfg, 'LOGGED_IN', expected_type=bool):
headers['X-Youtube-Bootstrap-Logged-In'] = 'true'
return headers
def generate_api_headers(
self, *, ytcfg=None, account_syncid=None, session_index=None,
self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None,
visitor_data=None, api_hostname=None, default_client='web', **kwargs):
origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
@ -773,7 +839,12 @@ def generate_api_headers(
'Origin': origin,
'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client),
**self._generate_cookie_auth_headers(ytcfg=ytcfg, account_syncid=account_syncid, session_index=session_index, origin=origin),
**self._generate_cookie_auth_headers(
ytcfg=ytcfg,
delegated_session_id=delegated_session_id,
user_session_id=user_session_id,
session_index=session_index,
origin=origin),
}
return filter_dict(headers)
@ -1356,8 +1427,8 @@ 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', 'mweb')
_DEFAULT_AUTHED_CLIENTS = ('web_creator', 'mweb')
_DEFAULT_CLIENTS = ('tv', 'ios', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv', 'web')
_GEO_BYPASS = False
@ -3836,9 +3907,13 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg,
default_client=client,
visitor_data=visitor_data,
session_index=self._extract_session_index(master_ytcfg, player_ytcfg),
account_syncid=(
self._data_sync_id_to_delegated_session_id(data_sync_id)
or self._extract_account_syncid(master_ytcfg, initial_pr, player_ytcfg)
delegated_session_id=(
self._parse_data_sync_id(data_sync_id)[0]
or self._extract_delegated_session_id(master_ytcfg, initial_pr, player_ytcfg)
),
user_session_id=(
self._parse_data_sync_id(data_sync_id)[1]
or self._extract_user_session_id(master_ytcfg, initial_pr, player_ytcfg)
),
)
@ -3889,15 +3964,6 @@ 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:
unsupported_clients = [
client for client in requested_clients if not INNERTUBE_CLIENTS[client]['SUPPORTS_COOKIES']
@ -4008,28 +4074,6 @@ def append_client(*client_names):
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):
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')
'''
prs.extend(deprioritized_prs)
if skipped_clients:
@ -5350,7 +5394,7 @@ def _extract_entries(self, parent_renderer, continuation_list):
if not continuation_list[0]:
continuation_list[0] = self._extract_continuation(parent_renderer)
def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
def _entries(self, tab, item_id, ytcfg, delegated_session_id, visitor_data):
continuation_list = [None]
extract_entries = lambda x: self._extract_entries(x, continuation_list)
tab_content = try_get(tab, lambda x: x['content'], dict)
@ -5371,7 +5415,7 @@ def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
break
seen_continuations.add(continuation_token)
headers = self.generate_api_headers(
ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
ytcfg=ytcfg, delegated_session_id=delegated_session_id, visitor_data=visitor_data)
response = self._extract_response(
item_id=f'{item_id} page {page_num}',
query=continuation, headers=headers, ytcfg=ytcfg,
@ -5441,7 +5485,7 @@ def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
return self.playlist_result(
self._entries(
selected_tab, metadata['id'], ytcfg,
self._extract_account_syncid(ytcfg, data),
self._extract_delegated_session_id(ytcfg, data),
self._extract_visitor_data(data, ytcfg)),
**metadata)
@ -5593,7 +5637,7 @@ def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
watch_endpoint = try_get(
playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
headers = self.generate_api_headers(
ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data),
visitor_data=self._extract_visitor_data(response, data, ytcfg))
query = {
'playlistId': playlist_id,
@ -5691,7 +5735,7 @@ def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
if not is_playlist:
return
headers = self.generate_api_headers(
ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data),
visitor_data=self._extract_visitor_data(data, ytcfg))
query = {
'params': 'wgYCCAA=',

6
yt_dlp/version.py
View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.12.23'
__version__ = '2025.01.15'
RELEASE_GIT_HEAD = '65cf46cddd873fd229dbb0fc0689bca4c201c6b6'
RELEASE_GIT_HEAD = 'c8541f8b13e743fcfa06667530d13fee8686e22a'
VARIANT = None
@ -12,4 +12,4 @@
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.12.23'
_pkg_version = '2025.01.15'