mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-02-27 02:40:02 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into extract-common-_is_jwt_token_expired-to-InfoExtractor

Browse Source
This commit is contained in:
Michaël De Boey
2025-04-06 09:01:45 +02:00
parent ff1786e158 425017531f
commit 5e1507c39a
74 changed files with 2427 additions and 1202 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/_extractors.py
View File

@@ -336,6 +336,7 @@ from .canal1 import Canal1IE
from .canalalpha import CanalAlphaIE
from .canalc2 import Canalc2IE
from .canalplus import CanalplusIE
from .canalsurmas import CanalsurmasIE
from .caracoltv import CaracolTvPlayIE
from .cartoonnetwork import CartoonNetworkIE
from .cbc import (
@@ -495,10 +496,6 @@ from .daum import (
from .daystar import DaystarClipIE
from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import (
DeezerAlbumIE,
DeezerPlaylistIE,
)
from .democracynow import DemocracynowIE
from .detik import DetikEmbedIE
from .deuxm import (
@@ -686,6 +683,7 @@ from .foxnews import (
)
from .foxsports import FoxSportsIE
from .fptplay import FptplayIE
from .francaisfacile import FrancaisFacileIE
from .franceinter import FranceInterIE
from .francetv import (
FranceTVIE,
@@ -842,6 +840,7 @@ from .icareus import IcareusIE
from .ichinanalive import (
IchinanaLiveClipIE,
IchinanaLiveIE,
IchinanaLiveVODIE,
)
from .idolplus import IdolPlusIE
from .ign import (
@@ -1054,6 +1053,7 @@ from .livestream import (
)
from .livestreamfails import LivestreamfailsIE
from .lnk import LnkIE
from .loco import LocoIE
from .loom import (
LoomFolderIE,
LoomIE,
@@ -1493,6 +1493,10 @@ from .paramountplus import (
)
from .parler import ParlerIE
from .parlview import ParlviewIE
from .parti import (
PartiLivestreamIE,
PartiVideoIE,
)
from .patreon import (
PatreonCampaignIE,
PatreonIE,
@@ -1739,6 +1743,7 @@ from .roosterteeth import (
RoosterTeethSeriesIE,
)
from .rottentomatoes import RottenTomatoesIE
from .roya import RoyaLiveIE
from .rozhlas import (
MujRozhlasIE,
RozhlasIE,
@@ -1882,6 +1887,8 @@ from .skyit import (
SkyItVideoIE,
SkyItVideoLiveIE,
TV8ItIE,
TV8ItLiveIE,
TV8ItPlaylistIE,
)
from .skylinewebcams import SkylineWebcamsIE
from .skynewsarabia import (
@@ -1985,6 +1992,7 @@ from .storyfire import (
StoryFireSeriesIE,
StoryFireUserIE,
)
from .streaks import StreaksIE
from .streamable import StreamableIE
from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
@@ -2348,10 +2356,6 @@ from .viewlift import (
ViewLiftIE,
)
from .viidea import ViideaIE
from .viki import (
VikiChannelIE,
VikiIE,
)
from .vimeo import (
VHXEmbedIE,
VimeoAlbumIE,
@@ -2396,10 +2400,15 @@ from .voxmedia import (
VoxMediaIE,
VoxMediaVolumeIE,
)
from .vrsquare import (
VrSquareChannelIE,
VrSquareIE,
VrSquareSearchIE,
VrSquareSectionIE,
)
from .vrt import (
VRTIE,
DagelijkseKostIE,
KetnetIE,
Radio1BeIE,
VrtNUIE,
)

15
yt_dlp/extractor/afreecatv.py
View File

@@ -1,3 +1,4 @@
import datetime as dt
import functools
from .common import InfoExtractor
@@ -10,7 +11,7 @@ from ..utils import (
filter_dict,
int_or_none,
orderedSet,
unified_timestamp,
parse_iso8601,
url_or_none,
urlencode_postdata,
urljoin,
@@ -87,9 +88,9 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'thumbnail': r're:https?://videoimg\.sooplive\.co/.kr/.+',
'thumbnail': r're:https?://videoimg\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
'upload_date': '20230108',
'timestamp': 1673218805,
'timestamp': 1673186405,
'title': '젠지 페이즈',
},
'params': {
@@ -102,7 +103,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4',
'title': '혼자사는여자집',
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'thumbnail': r're:https?://(?:video|st)img\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
@@ -119,7 +120,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)',
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'thumbnail': r're:https?://(?:video|st)img\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu',
'upload_date': '20180327',
@@ -187,7 +188,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'formats': formats,
**traverse_obj(file_element, {
'duration': ('duration', {int_or_none(scale=1000)}),
'timestamp': ('file_start', {unified_timestamp}),
'timestamp': ('file_start', {parse_iso8601(delimiter=' ', timezone=dt.timedelta(hours=9))}),
}),
})
@@ -370,7 +371,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
'title': channel_info.get('TITLE') or station_info.get('station_title'),
'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
'uploader_id': broadcaster_id,
'timestamp': unified_timestamp(station_info.get('broad_start')),
'timestamp': parse_iso8601(station_info.get('broad_start'), delimiter=' ', timezone=dt.timedelta(hours=9)),
'formats': formats,
'is_live': True,
'http_headers': {'Referer': url},

16
yt_dlp/extractor/bandlab.py
View File

@@ -86,7 +86,7 @@ class BandlabBaseIE(InfoExtractor):
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
'url': ('video', 'url', {url_or_none}),
'title': ('caption', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
'title': ('caption', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=72)}),
'description': ('caption', {str}),
'thumbnail': ('video', 'picture', 'url', {url_or_none}),
'view_count': ('video', 'counters', 'plays', {int_or_none}),
@@ -120,7 +120,7 @@ class BandlabIE(BandlabBaseIE):
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
@@ -142,7 +142,7 @@ class BandlabIE(BandlabBaseIE):
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
@@ -158,7 +158,7 @@ class BandlabIE(BandlabBaseIE):
'comment_count': int,
'genres': ['Other'],
'uploader_id': 'user8353034818103753',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/51b18363-da23-4b9b-a29c-2933a3e561ca/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/songs/51b18363-da23-4b9b-a29c-2933a3e561ca/',
'timestamp': 1709625771,
'track': 'PodcastMaerchen4b',
'duration': 468.14,
@@ -178,7 +178,7 @@ class BandlabIE(BandlabBaseIE):
'id': '110343fc-148b-ea11-96d2-0003ffd1fc09',
'ext': 'm4a',
'timestamp': 1588273294,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/b612e533-e4f7-4542-9f50-3fcfd8dd822c/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/users/b612e533-e4f7-4542-9f50-3fcfd8dd822c/',
'description': 'Final Revision.',
'title': 'Replay ( Instrumental)',
'uploader': 'David R Sparks',
@@ -200,7 +200,7 @@ class BandlabIE(BandlabBaseIE):
'id': '5cdf9036-3857-ef11-991a-6045bd36e0d9',
'ext': 'mp4',
'duration': 44.705,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/videos/67c6cef1-cef6-40d3-831e-a55bc1dcb972/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/videos/67c6cef1-cef6-40d3-831e-a55bc1dcb972/',
'comment_count': int,
'title': 'backing vocals',
'uploader_id': 'marliashya',
@@ -224,7 +224,7 @@ class BandlabIE(BandlabBaseIE):
'view_count': int,
'track': 'Positronic Meltdown',
'duration': 318.55,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/87165bc3-5439-496e-b1f7-a9f13b541ff2/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/songs/87165bc3-5439-496e-b1f7-a9f13b541ff2/',
'description': 'Checkout my tracks at AOMX http://aomxsounds.com/',
'uploader_id': 'microfreaks',
'title': 'Positronic Meltdown',
@@ -246,7 +246,7 @@ class BandlabIE(BandlabBaseIE):
'comment_count': int,
'uploader': 'Sorakime',
'uploader_id': 'sorakime',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/572a351a-0f3a-4c6a-ac39-1a5defdeeb1c/',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.0/users/572a351a-0f3a-4c6a-ac39-1a5defdeeb1c/',
'timestamp': 1691162128,
'upload_date': '20230804',
'media_type': 'track',

8
yt_dlp/extractor/bilibili.py
View File

@@ -1596,16 +1596,16 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
webpage = self._download_webpage(url, list_id)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', list_id)
if traverse_obj(initial_state, ('error', 'code', {int_or_none})) != 200:
error_code = traverse_obj(initial_state, ('error', 'trueCode', {int_or_none}))
error_message = traverse_obj(initial_state, ('error', 'message', {str_or_none}))
error = traverse_obj(initial_state, (('error', 'listError'), all, lambda _, v: v['code'], any))
if error and error['code'] != 200:
error_code = error.get('trueCode')
if error_code == -400 and list_id == 'watchlater':
self.raise_login_required('You need to login to access your watchlater playlist')
elif error_code == -403:
self.raise_login_required('This is a private playlist. You need to login as its owner')
elif error_code == 11010:
raise ExtractorError('Playlist is no longer available', expected=True)
raise ExtractorError(f'Could not access playlist: {error_code} {error_message}')
raise ExtractorError(f'Could not access playlist: {error_code} {error.get("message")}')
query = {
'ps': 20,

10
yt_dlp/extractor/bluesky.py
View File

@@ -53,7 +53,7 @@ class BlueskyIE(InfoExtractor):
'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky now has video! Update your app to versi...',
'title': 'Bluesky now has video! Update your app to version 1.91 or refresh on ...',
'alt_title': 'Bluesky video feature announcement',
'description': r're:(?s)Bluesky now has video! .{239}',
'upload_date': '20240911',
@@ -172,7 +172,7 @@ class BlueskyIE(InfoExtractor):
'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky now has video! Update your app to versi...',
'title': 'Bluesky now has video! Update your app to version 1.91 or refresh on ...',
'alt_title': 'Bluesky video feature announcement',
'description': r're:(?s)Bluesky now has video! .{239}',
'upload_date': '20240911',
@@ -191,7 +191,7 @@ class BlueskyIE(InfoExtractor):
'info_dict': {
'id': '3l7rdfxhyds2f',
'ext': 'mp4',
'uploader': 'cinnamon',
'uploader': 'cinnamon 🐇 🏳️‍⚧️',
'uploader_id': 'cinny.bun.how',
'uploader_url': 'https://bsky.app/profile/cinny.bun.how',
'channel_id': 'did:plc:7x6rtuenkuvxq3zsvffp2ide',
@@ -255,7 +255,7 @@ class BlueskyIE(InfoExtractor):
'info_dict': {
'id': '3l77u64l7le2e',
'ext': 'mp4',
'title': 'hearing people on twitter say that bluesky isn\'...',
'title': "hearing people on twitter say that bluesky isn't funny yet so post t...",
'like_count': int,
'uploader_id': 'thafnine.net',
'uploader_url': 'https://bsky.app/profile/thafnine.net',
@@ -387,7 +387,7 @@ class BlueskyIE(InfoExtractor):
'age_limit': (
'labels', ..., 'val', {lambda x: 18 if x in ('sexual', 'porn', 'graphic-media') else None}, any),
'description': (*record_path, 'text', {str}, filter),
'title': (*record_path, 'text', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
'title': (*record_path, 'text', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=72)}),
}),
})
return entries

2
yt_dlp/extractor/bokecc.py
View File

@@ -24,7 +24,7 @@ class BokeCCBaseIE(InfoExtractor):
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{

84
yt_dlp/extractor/canalsurmas.py Normal file
View File

@@ -0,0 +1,84 @@
import json
import time
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
jwt_decode_hs256,
parse_iso8601,
url_or_none,
variadic,
)
from ..utils.traversal import traverse_obj
class CanalsurmasIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?canalsurmas\.es/videos/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.canalsurmas.es/videos/44006-el-gran-queo-1-lora-del-rio-sevilla-20072014',
'md5': '861f86fdc1221175e15523047d0087ef',
'info_dict': {
'id': '44006',
'ext': 'mp4',
'title': 'Lora del Río (Sevilla)',
'description': 'md5:3d9ee40a9b1b26ed8259e6b71ed27b8b',
'thumbnail': 'https://cdn2.rtva.interactvty.com/content_cards/00f3e8f67b0a4f3b90a4a14618a48b0d.jpg',
'timestamp': 1648123182,
'upload_date': '20220324',
},
}]
_API_BASE = 'https://api-rtva.interactvty.com'
_access_token = None
@staticmethod
def _is_jwt_expired(token):
return jwt_decode_hs256(token)['exp'] - time.time() < 300
def _call_api(self, endpoint, video_id, fields=None):
if not self._access_token or self._is_jwt_expired(self._access_token):
self._access_token = self._download_json(
f'{self._API_BASE}/jwt/token/', None,
'Downloading access token', 'Failed to download access token',
headers={'Content-Type': 'application/json'},
data=json.dumps({
'username': 'canalsur_demo',
'password': 'dsUBXUcI',
}).encode())['access']
return self._download_json(
f'{self._API_BASE}/api/2.0/contents/{endpoint}/{video_id}/', video_id,
f'Downloading {endpoint} API JSON', f'Failed to download {endpoint} API JSON',
headers={'Authorization': f'jwtok {self._access_token}'},
query={'optional_fields': ','.join(variadic(fields))} if fields else None)
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._call_api('content', video_id, fields=[
'description', 'image', 'duration', 'created_at', 'tags',
])
stream_info = self._call_api('content_resources', video_id, 'media_url')
formats, subtitles = [], {}
for stream_url in traverse_obj(stream_info, ('results', ..., 'media_url', {url_or_none})):
if determine_ext(stream_url) == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
stream_url, video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.append({'url': stream_url})
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(video_info, {
'title': ('name', {str.strip}),
'description': ('description', {str}),
'thumbnail': ('image', {url_or_none}),
'duration': ('duration', {float_or_none}),
'timestamp': ('created_at', {parse_iso8601}),
'tags': ('tags', ..., {str}),
}),
}

47
yt_dlp/extractor/chzzk.py
View File

@@ -21,7 +21,7 @@ class CHZZKLiveIE(InfoExtractor):
'channel': '진짜도현',
'channel_id': 'c68b8ef525fb3d2fa146344d84991753',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1705510344,
'upload_date': '20240117',
'live_status': 'is_live',
@@ -98,7 +98,7 @@ class CHZZKVideoIE(InfoExtractor):
'channel': '침착맨',
'channel_id': 'bb382c2c0cc9fa7c86ab3b037fb5799c',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 15577,
'timestamp': 1702970505.417,
'upload_date': '20231219',
@@ -115,7 +115,7 @@ class CHZZKVideoIE(InfoExtractor):
'channel': '라디유radiyu',
'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 95,
'timestamp': 1703102631.722,
'upload_date': '20231220',
@@ -131,12 +131,30 @@ class CHZZKVideoIE(InfoExtractor):
'channel': '강지',
'channel_id': 'b5ed5db484d04faf4d150aedd362f34b',
'channel_is_verified': True,
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 4433,
'timestamp': 1703307460.214,
'upload_date': '20231223',
'view_count': int,
},
}, {
# video_status == 'NONE' but is downloadable
'url': 'https://chzzk.naver.com/video/6325166',
'info_dict': {
'id': '6325166',
'ext': 'mp4',
'title': '와이프 숙제빼주기',
'channel': '이 다',
'channel_id': '0076a519f147ee9fd0959bf02f9571ca',
'channel_is_verified': False,
'view_count': int,
'duration': 28167,
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1742139216.86,
'upload_date': '20250316',
'live_status': 'was_live',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
@@ -147,11 +165,7 @@ class CHZZKVideoIE(InfoExtractor):
live_status = 'was_live' if video_meta.get('liveOpenDate') else 'not_live'
video_status = video_meta.get('vodStatus')
if video_status == 'UPLOAD':
playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
playback['media'][0]['path'], video_id, 'mp4', m3u8_id='hls')
elif video_status == 'ABR_HLS':
if video_status == 'ABR_HLS':
formats, subtitles = self._extract_mpd_formats_and_subtitles(
f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}',
video_id, query={
@@ -161,10 +175,17 @@ class CHZZKVideoIE(InfoExtractor):
'cpl': 'en_US',
})
else:
self.raise_no_formats(
f'Unknown video status detected: "{video_status}"', expected=True, video_id=video_id)
formats, subtitles = [], {}
live_status = 'post_live' if live_status == 'was_live' else None
fatal = video_status == 'UPLOAD'
playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id, fatal=fatal)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
traverse_obj(playback, ('media', 0, 'path')), video_id, 'mp4', m3u8_id='hls', fatal=fatal)
if formats and video_status != 'UPLOAD':
self.write_debug(f'Video found with status: "{video_status}"')
elif not formats:
self.raise_no_formats(
f'Unknown video status detected: "{video_status}"', expected=True, video_id=video_id)
formats, subtitles = [], {}
live_status = 'post_live' if live_status == 'was_live' else None
return {
'id': video_id,

36
yt_dlp/extractor/common.py
View File

@@ -78,6 +78,7 @@ from ..utils import (
parse_iso8601,
parse_m3u8_attributes,
parse_resolution,
qualities,
sanitize_url,
smuggle_url,
str_or_none,
@@ -2177,6 +2178,8 @@ class InfoExtractor:
media_url = media.get('URI')
if media_url:
manifest_url = format_url(media_url)
is_audio = media_type == 'AUDIO'
is_alternate = media.get('DEFAULT') == 'NO' or media.get('AUTOSELECT') == 'NO'
formats.extend({
'format_id': join_nonempty(m3u8_id, group_id, name, idx),
'format_note': name,
@@ -2189,7 +2192,11 @@ class InfoExtractor:
'preference': preference,
'quality': quality,
'has_drm': has_drm,
'vcodec': 'none' if media_type == 'AUDIO' else None,
'vcodec': 'none' if is_audio else None,
# Alternate audio formats (e.g. audio description) should be deprioritized
'source_preference': -2 if is_audio and is_alternate else None,
# Save this to assign source_preference based on associated video stream
'_audio_group_id': group_id if is_audio and not is_alternate else None,
} for idx in _extract_m3u8_playlist_indices(manifest_url))
def build_stream_name():
@@ -2284,6 +2291,8 @@ class InfoExtractor:
# ignore references to rendition groups and treat them
# as complete formats.
if audio_group_id and codecs and f.get('vcodec') != 'none':
# Save this to determine quality of audio formats that only have a GROUP-ID
f['_audio_group_id'] = audio_group_id
audio_group = groups.get(audio_group_id)
if audio_group and audio_group[0].get('URI'):
# TODO: update acodec for audio only formats with
@@ -2306,6 +2315,28 @@ class InfoExtractor:
formats.append(http_f)
last_stream_inf = {}
# Some audio-only formats only have a GROUP-ID without any other quality/bitrate/codec info
# Each audio GROUP-ID corresponds with one or more video formats' AUDIO attribute
# For sorting purposes, set source_preference based on the quality of the video formats they are grouped with
# See https://github.com/yt-dlp/yt-dlp/issues/11178
audio_groups_by_quality = orderedSet(f['_audio_group_id'] for f in sorted(
traverse_obj(formats, lambda _, v: v.get('vcodec') != 'none' and v['_audio_group_id']),
key=lambda x: (x.get('tbr') or 0, x.get('width') or 0)))
audio_quality_map = {
audio_groups_by_quality[0]: 'low',
audio_groups_by_quality[-1]: 'high',
} if len(audio_groups_by_quality) > 1 else None
audio_preference = qualities(audio_groups_by_quality)
for fmt in formats:
audio_group_id = fmt.pop('_audio_group_id', None)
if not audio_quality_map or not audio_group_id or fmt.get('vcodec') != 'none':
continue
# Use source_preference since quality and preference are set by params
fmt['source_preference'] = audio_preference(audio_group_id)
fmt['format_note'] = join_nonempty(
fmt.get('format_note'), audio_quality_map.get(audio_group_id), delim=', ')
return formats, subtitles
def _extract_m3u8_vod_duration(
@@ -2935,8 +2966,7 @@ class InfoExtractor:
segment_duration = None
if 'total_number' not in representation_ms_info and 'segment_duration' in representation_ms_info:
segment_duration = float_or_none(representation_ms_info['segment_duration'], representation_ms_info['timescale'])
representation_ms_info['total_number'] = int(math.ceil(
float_or_none(period_duration, segment_duration, default=0)))
representation_ms_info['total_number'] = math.ceil(float_or_none(period_duration, segment_duration, default=0))
representation_ms_info['fragments'] = [{
media_location_key: media_template % {
'Number': segment_number,

17
yt_dlp/extractor/crowdbunker.py
View File

@@ -5,7 +5,9 @@ from ..utils import (
int_or_none,
try_get,
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj
class CrowdBunkerIE(InfoExtractor):
@@ -44,16 +46,15 @@ class CrowdBunkerIE(InfoExtractor):
'url': sub_url,
})
mpd_url = try_get(video_json, lambda x: x['dashManifest']['url'])
if mpd_url:
fmts, subs = self._extract_mpd_formats_and_subtitles(mpd_url, video_id)
if mpd_url := traverse_obj(video_json, ('dashManifest', 'url', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(mpd_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
m3u8_url = try_get(video_json, lambda x: x['hlsManifest']['url'])
if m3u8_url:
fmts, subs = self._extract_m3u8_formats_and_subtitles(mpd_url, video_id)
self._merge_subtitles(subs, target=subtitles)
if m3u8_url := traverse_obj(video_json, ('hlsManifest', 'url', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
self._merge_subtitles(subs, target=subtitles)
thumbnails = [{
'url': image['url'],

142
yt_dlp/extractor/deezer.py
View File

@@ -1,142 +0,0 @@
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
orderedSet,
)
class DeezerBaseInfoExtractor(InfoExtractor):
def get_data(self, url):
if not self.get_param('test'):
self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
mobj = self._match_valid_url(url)
data_id = mobj.group('id')
webpage = self._download_webpage(url, data_id)
geoblocking_msg = self._html_search_regex(
r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
default=None)
if geoblocking_msg is not None:
raise ExtractorError(
f'Deezer said: {geoblocking_msg}', expected=True)
data_json = self._search_regex(
(r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
webpage, 'data JSON')
data = json.loads(data_json)
return data_id, webpage, data
class DeezerPlaylistIE(DeezerBaseInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.deezer.com/playlist/176747451',
'info_dict': {
'id': '176747451',
'title': 'Best!',
'uploader': 'anonymous',
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
},
'playlist_count': 29,
}
def _real_extract(self, url):
playlist_id, webpage, data = self.get_data(url)
playlist_title = data.get('DATA', {}).get('TITLE')
playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
playlist_thumbnail = self._search_regex(
r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
'playlist thumbnail')
entries = []
for s in data.get('SONGS', {}).get('data'):
formats = [{
'format_id': 'preview',
'url': s.get('MEDIA', [{}])[0].get('HREF'),
'preference': -100, # Only the first 30 seconds
'ext': 'mp3',
}]
artists = ', '.join(
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
entries.append({
'id': s.get('SNG_ID'),
'duration': int_or_none(s.get('DURATION')),
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
'uploader': s.get('ART_NAME'),
'uploader_id': s.get('ART_ID'),
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
'formats': formats,
})
return {
'_type': 'playlist',
'id': playlist_id,
'title': playlist_title,
'uploader': playlist_uploader,
'thumbnail': playlist_thumbnail,
'entries': entries,
}
class DeezerAlbumIE(DeezerBaseInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.deezer.com/fr/album/67505622',
'info_dict': {
'id': '67505622',
'title': 'Last Week',
'uploader': 'Home Brew',
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
},
'playlist_count': 7,
}
def _real_extract(self, url):
album_id, webpage, data = self.get_data(url)
album_title = data.get('DATA', {}).get('ALB_TITLE')
album_uploader = data.get('DATA', {}).get('ART_NAME')
album_thumbnail = self._search_regex(
r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
'album thumbnail')
entries = []
for s in data.get('SONGS', {}).get('data'):
formats = [{
'format_id': 'preview',
'url': s.get('MEDIA', [{}])[0].get('HREF'),
'preference': -100, # Only the first 30 seconds
'ext': 'mp3',
}]
artists = ', '.join(
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
entries.append({
'id': s.get('SNG_ID'),
'duration': int_or_none(s.get('DURATION')),
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
'uploader': s.get('ART_NAME'),
'uploader_id': s.get('ART_ID'),
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
'formats': formats,
'track': s.get('SNG_TITLE'),
'track_number': int_or_none(s.get('TRACK_NUMBER')),
'track_id': s.get('SNG_ID'),
'artist': album_uploader,
'album': album_title,
'album_artist': album_uploader,
})
return {
'_type': 'playlist',
'id': album_id,
'title': album_title,
'uploader': album_uploader,
'thumbnail': album_thumbnail,
'entries': entries,
}

87
yt_dlp/extractor/francaisfacile.py Normal file
View File

@@ -0,0 +1,87 @@
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class FrancaisFacileIE(InfoExtractor):
_VALID_URL = r'https?://francaisfacile\.rfi\.fr/[a-z]{2}/(?:actualit%C3%A9|podcasts/[^/#?]+)/(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250305-r%C3%A9concilier-les-jeunes-avec-la-lecture-gr%C3%A2ce-aux-r%C3%A9seaux-sociaux',
'md5': '4f33674cb205744345cc835991100afa',
'info_dict': {
'id': 'WBMZ58952-FLE-FR-20250305',
'display_id': '20250305-réconcilier-les-jeunes-avec-la-lecture-grâce-aux-réseaux-sociaux',
'title': 'Réconcilier les jeunes avec la lecture grâce aux réseaux sociaux',
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/05/6b6af52a-f9ba-11ef-a1f8-005056a97652.mp3',
'ext': 'mp3',
'description': 'md5:b903c63d8585bd59e8cc4d5f80c4272d',
'duration': 103.15,
'timestamp': 1741177984,
'upload_date': '20250305',
},
}, {
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250307-argentine-le-sac-d-un-alpiniste-retrouv%C3%A9-40-ans-apr%C3%A8s-sa-mort',
'md5': 'b8c3a63652d4ae8e8092dda5700c1cd9',
'info_dict': {
'id': 'WBMZ59102-FLE-FR-20250307',
'display_id': '20250307-argentine-le-sac-d-un-alpiniste-retrouvé-40-ans-après-sa-mort',
'title': 'Argentine: le sac d\'un alpiniste retrouvé 40 ans après sa mort',
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/07/8edf4082-fb46-11ef-8a37-005056bf762b.mp3',
'ext': 'mp3',
'description': 'md5:7fd088fbdf4a943bb68cf82462160dca',
'duration': 117.74,
'timestamp': 1741352789,
'upload_date': '20250307',
},
}, {
'url': 'https://francaisfacile.rfi.fr/fr/podcasts/un-mot-une-histoire/20250317-le-mot-de-david-foenkinos-peut-%C3%AAtre',
'md5': 'db83c2cc2589b4c24571c6b6cf14f5f1',
'info_dict': {
'id': 'WBMZ59441-FLE-FR-20250317',
'display_id': '20250317-le-mot-de-david-foenkinos-peut-être',
'title': 'Le mot de David Foenkinos: «peut-être» - Un mot, une histoire',
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/17/4ca6cbbe-0315-11f0-a85b-005056a97652.mp3',
'ext': 'mp3',
'description': 'md5:3fe35fae035803df696bfa7af2496e49',
'duration': 198.96,
'timestamp': 1742210897,
'upload_date': '20250317',
},
}]
def _real_extract(self, url):
display_id = urllib.parse.unquote(self._match_id(url))
try: # yt-dlp's default user-agents are too old and blocked by the site
webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient
webpage = self._download_webpage(url, display_id, impersonate=True)
data = self._search_json(
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
webpage, 'audio data', display_id)
return {
'id': data['mediaId'],
'display_id': display_id,
'vcodec': 'none',
'title': self._html_extract_title(webpage),
**self._search_json_ld(webpage, display_id, fatal=False),
**traverse_obj(data, {
'title': ('title', {str}),
'url': ('sources', ..., 'url', {url_or_none}, any),
'duration': ('sources', ..., 'duration', {float_or_none}, any),
}),
}

22
yt_dlp/extractor/generic.py
View File

@@ -16,6 +16,7 @@ from ..utils import (
MEDIA_EXTENSIONS,
ExtractorError,
UnsupportedError,
base_url,
determine_ext,
determine_protocol,
dict_get,
@@ -2213,10 +2214,21 @@ class GenericIE(InfoExtractor):
if is_live is not None:
info['live_status'] = 'not_live' if is_live == 'false' else 'is_live'
return
headers = m3u8_format.get('http_headers') or info.get('http_headers')
duration = self._extract_m3u8_vod_duration(
m3u8_format['url'], info.get('id'), note='Checking m3u8 live status',
errnote='Failed to download m3u8 media playlist', headers=headers)
headers = m3u8_format.get('http_headers') or info.get('http_headers') or {}
display_id = info.get('id')
urlh = self._request_webpage(
m3u8_format['url'], display_id, 'Checking m3u8 live status', errnote=False,
headers={**headers, 'Accept-Encoding': 'identity'}, fatal=False)
if urlh is False:
return
first_bytes = urlh.read(512)
if not first_bytes.startswith(b'#EXTM3U'):
return
m3u8_doc = self._webpage_read_content(
urlh, urlh.url, display_id, prefix=first_bytes, fatal=False, errnote=False)
if not m3u8_doc:
return
duration = self._parse_m3u8_vod_duration(m3u8_doc, display_id)
if not duration:
info['live_status'] = 'is_live'
info['duration'] = info.get('duration') or duration
@@ -2531,7 +2543,7 @@ class GenericIE(InfoExtractor):
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
doc,
mpd_base_url=full_response.url.rpartition('/')[0],
mpd_base_url=base_url(full_response.url),
mpd_url=url)
info_dict['live_status'] = 'is_live' if doc.get('type') == 'dynamic' else None
self._extra_manifest_info(info_dict, url)

6
yt_dlp/extractor/hse.py
View File

@@ -6,7 +6,7 @@ from ..utils import (
)
class HSEShowBaseInfoExtractor(InfoExtractor):
class HSEShowBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['DE']
def _extract_redux_data(self, url, video_id):
@@ -28,7 +28,7 @@ class HSEShowBaseInfoExtractor(InfoExtractor):
return formats, subtitles
class HSEShowIE(HSEShowBaseInfoExtractor):
class HSEShowIE(HSEShowBaseIE):
_VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/c/tv-shows/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.hse.de/dpl/c/tv-shows/505350',
@@ -64,7 +64,7 @@ class HSEShowIE(HSEShowBaseInfoExtractor):
}
class HSEProductIE(HSEShowBaseInfoExtractor):
class HSEProductIE(HSEShowBaseIE):
_VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/p/product/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.hse.de/dpl/p/product/408630',

58
yt_dlp/extractor/ichinanalive.py
View File

@@ -1,5 +1,13 @@
from .common import InfoExtractor
from ..utils import ExtractorError, str_or_none, traverse_obj, unified_strdate
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
traverse_obj,
unified_strdate,
url_or_none,
)
class IchinanaLiveIE(InfoExtractor):
@@ -157,3 +165,51 @@ class IchinanaLiveClipIE(InfoExtractor):
'description': view_data.get('caption'),
'upload_date': unified_strdate(str_or_none(view_data.get('createdAt'))),
}
class IchinanaLiveVODIE(InfoExtractor):
IE_NAME = '17live:vod'
_VALID_URL = r'https?://(?:www\.)?17\.live/ja/vod/[^/?#]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://17.live/ja/vod/27323042/2cf84520-e65e-4b22-891e-1d3a00b0f068',
'md5': '3299b930d7457b069639486998a89580',
'info_dict': {
'id': '2cf84520-e65e-4b22-891e-1d3a00b0f068',
'ext': 'mp4',
'title': 'md5:b5f8cbf497d54cc6a60eb3b480182f01',
'uploader': 'md5:29fb12122ab94b5a8495586e7c3085a5',
'uploader_id': '27323042',
'channel': '🌟オールナイトニッポン アーカイブ🌟',
'channel_id': '2b4f85f1-d61e-429d-a901-68d32bdd8645',
'like_count': int,
'view_count': int,
'thumbnail': r're:https?://.+/.+\.(?:jpe?g|png)',
'duration': 549,
'description': 'md5:116f326579700f00eaaf5581aae1192e',
'timestamp': 1741058645,
'upload_date': '20250304',
},
}, {
'url': 'https://17.live/ja/vod/27323042/0de11bac-9bea-40b8-9eab-0239a7d88079',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(f'https://wap-api.17app.co/api/v1/vods/{video_id}', video_id)
return traverse_obj(json_data, {
'id': ('vodID', {str}),
'title': ('title', {str}),
'formats': ('vodURL', {lambda x: self._extract_m3u8_formats(x, video_id)}),
'uploader': ('userInfo', 'displayName', {str}),
'uploader_id': ('userInfo', 'roomID', {int}, {str_or_none}),
'channel': ('userInfo', 'name', {str}),
'channel_id': ('userInfo', 'userID', {str}),
'like_count': ('likeCount', {int_or_none}),
'view_count': ('viewCount', {int_or_none}),
'thumbnail': ('imageURL', {url_or_none}),
'duration': ('duration', {int_or_none}),
'description': ('description', {str}),
'timestamp': ('createdAt', {int_or_none}),
})

10
yt_dlp/extractor/jamendo.py
View File

@@ -2,10 +2,12 @@ import hashlib
import random
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
clean_html,
int_or_none,
try_get,
urlhandle_detect_ext,
)
@@ -27,7 +29,7 @@ class JamendoIE(InfoExtractor):
'ext': 'flac',
# 'title': 'Maya Filipič - Stories from Emona I',
'title': 'Stories from Emona I',
'artist': 'Maya Filipič',
'artists': ['Maya Filipič'],
'album': 'Between two worlds',
'track': 'Stories from Emona I',
'duration': 210,
@@ -93,9 +95,15 @@ class JamendoIE(InfoExtractor):
if not cover_url or cover_url in urls:
continue
urls.append(cover_url)
urlh = self._request_webpage(
HEADRequest(cover_url), track_id, 'Checking thumbnail extension',
errnote=False, fatal=False)
if not urlh:
continue
size = int_or_none(cover_id.lstrip('size'))
thumbnails.append({
'id': cover_id,
'ext': urlhandle_detect_ext(urlh, default='jpg'),
'url': cover_url,
'width': size,
'height': size,

87
yt_dlp/extractor/loco.py Normal file
View File

@@ -0,0 +1,87 @@
from .common import InfoExtractor
from ..utils import int_or_none, url_or_none
from ..utils.traversal import require, traverse_obj
class LocoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?loco\.com/(?P<type>streamers|stream)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://loco.com/streamers/teuzinfps',
'info_dict': {
'id': 'teuzinfps',
'ext': 'mp4',
'title': r're:MS BOLADAO, RESENHA & GAMEPLAY ALTO NIVEL',
'description': 'bom e novo',
'uploader_id': 'RLUVE3S9JU',
'channel': 'teuzinfps',
'channel_follower_count': int,
'comment_count': int,
'view_count': int,
'concurrent_view_count': int,
'like_count': int,
'thumbnail': 'https://static.ivory.getloconow.com/default_thumb/743701a9-98ca-41ae-9a8b-70bd5da070ad.jpg',
'tags': ['MMORPG', 'Gameplay'],
'series': 'Tibia',
'timestamp': int,
'modified_timestamp': int,
'live_status': 'is_live',
'upload_date': str,
'modified_date': str,
},
'params': {
'skip_download': 'Livestream',
},
}, {
'url': 'https://loco.com/stream/c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
'md5': '45ebc8a47ee1c2240178757caf8881b5',
'info_dict': {
'id': 'c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
'ext': 'mp4',
'title': 'PAULINHO LOKO NA LOCO!',
'description': 'live on na loco',
'uploader_id': '2MDO7Z1DPM',
'channel': 'paulinholokobr',
'channel_follower_count': int,
'comment_count': int,
'view_count': int,
'concurrent_view_count': int,
'like_count': int,
'duration': 14491,
'thumbnail': 'https://static.ivory.getloconow.com/default_thumb/59b5970b-23c1-4518-9e96-17ce341299fe.jpg',
'tags': ['Gameplay'],
'series': 'GTA 5',
'timestamp': 1740612872,
'modified_timestamp': 1740613037,
'upload_date': '20250226',
'modified_date': '20250226',
},
}]
def _real_extract(self, url):
video_type, video_id = self._match_valid_url(url).group('type', 'id')
webpage = self._download_webpage(url, video_id)
stream = traverse_obj(self._search_nextjs_data(webpage, video_id), (
'props', 'pageProps', ('liveStreamData', 'stream'), {dict}, any, {require('stream info')}))
return {
'formats': self._extract_m3u8_formats(stream['conf']['hls'], video_id),
'id': video_id,
'is_live': video_type == 'streamers',
**traverse_obj(stream, {
'title': ('title', {str}),
'series': ('game_name', {str}),
'uploader_id': ('user_uid', {str}),
'channel': ('alias', {str}),
'description': ('description', {str}),
'concurrent_view_count': ('viewersCurrent', {int_or_none}),
'view_count': ('total_views', {int_or_none}),
'thumbnail': ('thumbnail_url_small', {url_or_none}),
'like_count': ('likes', {int_or_none}),
'tags': ('tags', ..., {str}),
'timestamp': ('started_at', {int_or_none(scale=1000)}),
'modified_timestamp': ('updated_at', {int_or_none(scale=1000)}),
'comment_count': ('comments_count', {int_or_none}),
'channel_follower_count': ('followers_count', {int_or_none}),
'duration': ('duration', {int_or_none}),
}),
}

3
yt_dlp/extractor/medaltv.py
View File

@@ -102,11 +102,10 @@ class MedalTVIE(InfoExtractor):
item_id = item_id or '%dp' % height
if item_id not in item_url:
return
width = int(round(aspect_ratio * height))
container.append({
'url': item_url,
id_key: item_id,
'width': width,
'width': round(aspect_ratio * height),
'height': height,
})

44
yt_dlp/extractor/microsoftembed.py
View File

@@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
parse_resolution,
traverse_obj,
unified_timestamp,
url_basename,
@@ -83,8 +84,8 @@ class MicrosoftMediusBaseIE(InfoExtractor):
subtitles.setdefault(sub.pop('tag', 'und'), []).append(sub)
return subtitles
def _extract_ism(self, ism_url, video_id):
formats = self._extract_ism_formats(ism_url, video_id)
def _extract_ism(self, ism_url, video_id, fatal=True):
formats = self._extract_ism_formats(ism_url, video_id, fatal=fatal)
for fmt in formats:
if fmt['language'] != 'eng' and 'English' not in fmt['format_id']:
fmt['language_preference'] = -10
@@ -218,9 +219,21 @@ class MicrosoftLearnEpisodeIE(MicrosoftMediusBaseIE):
'description': 'md5:7bbbfb593d21c2cf2babc3715ade6b88',
'timestamp': 1676339547,
'upload_date': '20230214',
'thumbnail': r're:https://learn\.microsoft\.com/video/media/.*\.png',
'thumbnail': r're:https://learn\.microsoft\.com/video/media/.+\.png',
'subtitles': 'count:14',
},
}, {
'url': 'https://learn.microsoft.com/en-gb/shows/on-demand-instructor-led-training-series/az-900-module-1',
'info_dict': {
'id': '4fe10f7c-d83c-463b-ac0e-c30a8195e01b',
'ext': 'mp4',
'title': 'AZ-900 Cloud fundamentals (1 of 6)',
'description': 'md5:3c2212ce865e9142f402c766441bd5c9',
'thumbnail': r're:https://.+/.+\.jpg',
'timestamp': 1706605184,
'upload_date': '20240130',
},
'params': {'format': 'bv[protocol=https]'},
}]
def _real_extract(self, url):
@@ -230,9 +243,32 @@ class MicrosoftLearnEpisodeIE(MicrosoftMediusBaseIE):
entry_id = self._html_search_meta('entryId', webpage, 'entryId', fatal=True)
video_info = self._download_json(
f'https://learn.microsoft.com/api/video/public/v1/entries/{entry_id}', video_id)
formats = []
if ism_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoUrl', {url_or_none})):
formats.extend(self._extract_ism(ism_url, video_id, fatal=False))
if hls_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoHLSUrl', {url_or_none})):
formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
if mpd_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoDashUrl', {url_or_none})):
formats.extend(self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False))
for key in ('low', 'medium', 'high'):
if video_url := traverse_obj(video_info, ('publicVideo', f'{key}QualityVideoUrl', {url_or_none})):
formats.append({
'url': video_url,
'format_id': f'video-http-{key}',
'acodec': 'none',
**parse_resolution(video_url),
})
if audio_url := traverse_obj(video_info, ('publicVideo', 'audioUrl', {url_or_none})):
formats.append({
'url': audio_url,
'format_id': 'audio-http',
'vcodec': 'none',
})
return {
'id': entry_id,
'formats': self._extract_ism(video_info['publicVideo']['adaptiveVideoUrl'], video_id),
'formats': formats,
'subtitles': self._sub_to_dict(traverse_obj(video_info, (
'publicVideo', 'captions', lambda _, v: url_or_none(v['url']), {
'tag': ('language', {str}),

14
yt_dlp/extractor/mitele.py
View File

@@ -1,5 +1,7 @@
from .telecinco import TelecincoBaseIE
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
)
@@ -79,7 +81,17 @@ class MiTeleIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
try: # yt-dlp's default user-agents are too old and blocked by akamai
webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient to bypass akamai
webpage = self._download_webpage(url, display_id, impersonate=True)
pre_player = self._search_json(
r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
webpage, 'Pre Player', display_id)['prePlayer']

4
yt_dlp/extractor/mlb.py
View File

@@ -446,9 +446,7 @@ mutation initPlaybackSession(
if not (m3u8_url and token):
errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
if 'not entitled' in errors:
raise ExtractorError(errors, expected=True)
elif errors: # Only warn when 'blacked out' since radio formats are available
if errors: # Only warn when 'blacked out' or 'not entitled'; radio formats may be available
self.report_warning(f'API returned errors for {format_id}: {errors}')
else:
self.report_warning(f'No formats available for {format_id} broadcast; skipping')

4
yt_dlp/extractor/moviepilot.py
View File

@@ -3,8 +3,8 @@ from .dailymotion import DailymotionIE
class MoviepilotIE(InfoExtractor):
_IE_NAME = 'moviepilot'
_IE_DESC = 'Moviepilot trailer'
IE_NAME = 'moviepilot'
IE_DESC = 'Moviepilot trailer'
_VALID_URL = r'https?://(?:www\.)?moviepilot\.de/movies/(?P<id>[^/]+)'
_TESTS = [{

314
yt_dlp/extractor/msn.py
View File

@@ -1,167 +1,215 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
determine_ext,
int_or_none,
unescapeHTML,
parse_iso8601,
url_or_none,
)
from ..utils.traversal import traverse_obj
class MSNIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:(?:www|preview)\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_VALID_URL = r'https?://(?:(?:www|preview)\.)?msn\.com/(?P<locale>[a-z]{2}-[a-z]{2})/(?:[^/?#]+/)+(?P<display_id>[^/?#]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://www.msn.com/en-in/money/video/7-ways-to-get-rid-of-chest-congestion/vi-BBPxU6d',
'md5': '087548191d273c5c55d05028f8d2cbcd',
'url': 'https://www.msn.com/en-gb/video/news/president-macron-interrupts-trump-over-ukraine-funding/vi-AA1zMcD7',
'info_dict': {
'id': 'BBPxU6d',
'display_id': '7-ways-to-get-rid-of-chest-congestion',
'id': 'AA1zMcD7',
'ext': 'mp4',
'title': 'Seven ways to get rid of chest congestion',
'description': '7 Ways to Get Rid of Chest Congestion',
'duration': 88,
'uploader': 'Health',
'uploader_id': 'BBPrMqa',
'display_id': 'president-macron-interrupts-trump-over-ukraine-funding',
'title': 'President Macron interrupts Trump over Ukraine funding',
'description': 'md5:5fd3857ac25849e7a56cb25fbe1a2a8b',
'uploader': 'k! News UK',
'uploader_id': 'BB1hz5Rj',
'duration': 59,
'thumbnail': 'https://img-s-msn-com.akamaized.net/tenant/amp/entityid/AA1zMagX.img',
'tags': 'count:14',
'timestamp': 1740510914,
'upload_date': '20250225',
'release_timestamp': 1740513600,
'release_date': '20250225',
'modified_timestamp': 1741413241,
'modified_date': '20250308',
},
}, {
# Article, multiple Dailymotion Embeds
'url': 'https://www.msn.com/en-in/money/sports/hottest-football-wags-greatest-footballers-turned-managers-and-more/ar-BBpc7Nl',
'url': 'https://www.msn.com/en-gb/video/watch/films-success-saved-adam-pearsons-acting-career/vi-AA1znZGE?ocid=hpmsn',
'info_dict': {
'id': 'BBpc7Nl',
'id': 'AA1znZGE',
'ext': 'mp4',
'display_id': 'films-success-saved-adam-pearsons-acting-career',
'title': "Films' success saved Adam Pearson's acting career",
'description': 'md5:98c05f7bd9ab4f9c423400f62f2d3da5',
'uploader': 'Sky News',
'uploader_id': 'AA2eki',
'duration': 52,
'thumbnail': 'https://img-s-msn-com.akamaized.net/tenant/amp/entityid/AA1zo7nU.img',
'timestamp': 1739993965,
'upload_date': '20250219',
'release_timestamp': 1739977753,
'release_date': '20250219',
'modified_timestamp': 1742076259,
'modified_date': '20250315',
},
'playlist_mincount': 4,
}, {
'url': 'http://www.msn.com/en-ae/news/offbeat/meet-the-nine-year-old-self-made-millionaire/ar-BBt6ZKf',
'only_matching': True,
}, {
'url': 'http://www.msn.com/en-ae/video/watch/obama-a-lot-of-people-will-be-disappointed/vi-AAhxUMH',
'only_matching': True,
}, {
# geo restricted
'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/the-first-fart-makes-you-laugh-the-last-fart-makes-you-cry/vp-AAhzIBU',
'only_matching': True,
}, {
'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6',
'only_matching': True,
}, {
# Vidible(AOL) Embed
'url': 'https://www.msn.com/en-us/money/other/jupiter-is-about-to-come-so-close-you-can-see-its-moons-with-binoculars/vi-AACqsHR',
'only_matching': True,
'url': 'https://www.msn.com/en-us/entertainment/news/rock-frontman-replacements-you-might-not-know-happened/vi-AA1yLVcD',
'info_dict': {
'id': 'AA1yLVcD',
'ext': 'mp4',
'display_id': 'rock-frontman-replacements-you-might-not-know-happened',
'title': 'Rock Frontman Replacements You Might Not Know Happened',
'description': 'md5:451a125496ff0c9f6816055bb1808da9',
'uploader': 'Grunge (Video)',
'uploader_id': 'BB1oveoV',
'duration': 596,
'thumbnail': 'https://img-s-msn-com.akamaized.net/tenant/amp/entityid/AA1yM4OJ.img',
'timestamp': 1739223456,
'upload_date': '20250210',
'release_timestamp': 1739219731,
'release_date': '20250210',
'modified_timestamp': 1741427272,
'modified_date': '20250308',
},
}, {
# Dailymotion Embed
'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L',
'only_matching': True,
'url': 'https://www.msn.com/de-de/nachrichten/other/the-first-descendant-gameplay-trailer-zu-serena-der-neuen-gefl%C3%BCgelten-nachfahrin/vi-AA1B1d06',
'info_dict': {
'id': 'x9g6oli',
'ext': 'mp4',
'title': 'The First Descendant: Gameplay-Trailer zu Serena, der neuen geflügelten Nachfahrin',
'description': '',
'uploader': 'MeinMMO',
'uploader_id': 'x2mvqi4',
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 60,
'thumbnail': 'https://s1.dmcdn.net/v/Y3fO61drj56vPB9SS/x1080',
'tags': ['MeinMMO', 'The First Descendant'],
'timestamp': 1742124877,
'upload_date': '20250316',
},
}, {
# YouTube Embed
'url': 'https://www.msn.com/en-in/money/news/meet-vikram-%E2%80%94-chandrayaan-2s-lander/vi-AAGUr0v',
'only_matching': True,
# Youtube Embed
'url': 'https://www.msn.com/en-gb/video/webcontent/web-content/vi-AA1ybFaJ',
'info_dict': {
'id': 'kQSChWu95nE',
'ext': 'mp4',
'title': '7 Daily Habits to Nurture Your Personal Growth',
'description': 'md5:6f233c68341b74dee30c8c121924e827',
'uploader': 'TopThink',
'uploader_id': '@TopThink',
'uploader_url': 'https://www.youtube.com/@TopThink',
'channel': 'TopThink',
'channel_id': 'UCMlGmHokrQRp-RaNO7aq4Uw',
'channel_url': 'https://www.youtube.com/channel/UCMlGmHokrQRp-RaNO7aq4Uw',
'channel_is_verified': True,
'channel_follower_count': int,
'comment_count': int,
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 705,
'thumbnail': 'https://i.ytimg.com/vi/kQSChWu95nE/maxresdefault.jpg',
'categories': ['Howto & Style'],
'tags': ['topthink', 'top think', 'personal growth'],
'timestamp': 1722711620,
'upload_date': '20240803',
'playable_in_embed': True,
'availability': 'public',
'live_status': 'not_live',
},
}, {
# NBCSports Embed
'url': 'https://www.msn.com/en-us/money/football_nfl/week-13-preview-redskins-vs-panthers/vi-BBXsCDb',
'only_matching': True,
# Article with social embed
'url': 'https://www.msn.com/en-in/news/techandscience/watch-earth-sets-and-rises-behind-moon-in-breathtaking-blue-ghost-video/ar-AA1zKoAc',
'info_dict': {
'id': 'AA1zKoAc',
'title': 'Watch: Earth sets and rises behind Moon in breathtaking Blue Ghost video',
'description': 'md5:0ad51cfa77e42e7f0c46cf98a619dbbf',
'uploader': 'India Today',
'uploader_id': 'AAyFWG',
'tags': 'count:11',
'timestamp': 1740485034,
'upload_date': '20250225',
'release_timestamp': 1740484875,
'release_date': '20250225',
'modified_timestamp': 1740488561,
'modified_date': '20250225',
},
'playlist_count': 1,
}]
def _real_extract(self, url):
display_id, page_id = self._match_valid_url(url).groups()
locale, display_id, page_id = self._match_valid_url(url).group('locale', 'display_id', 'id')
webpage = self._download_webpage(url, display_id)
json_data = self._download_json(
f'https://assets.msn.com/content/view/v2/Detail/{locale}/{page_id}', page_id)
entries = []
for _, metadata in re.findall(r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1', webpage):
video = self._parse_json(unescapeHTML(metadata), display_id)
provider_id = video.get('providerId')
player_name = video.get('playerName')
if player_name and provider_id:
entry = None
if player_name == 'AOL':
if provider_id.startswith('http'):
provider_id = self._search_regex(
r'https?://delivery\.vidible\.tv/video/redirect/([0-9a-f]{24})',
provider_id, 'vidible id')
entry = self.url_result(
'aol-video:' + provider_id, 'Aol', provider_id)
elif player_name == 'Dailymotion':
entry = self.url_result(
'https://www.dailymotion.com/video/' + provider_id,
'Dailymotion', provider_id)
elif player_name == 'YouTube':
entry = self.url_result(
provider_id, 'Youtube', provider_id)
elif player_name == 'NBCSports':
entry = self.url_result(
'http://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/' + provider_id,
'NBCSportsVPlayer', provider_id)
if entry:
entries.append(entry)
continue
video_id = video['uuid']
title = video['title']
common_metadata = traverse_obj(json_data, {
'title': ('title', {str}),
'description': (('abstract', ('body', {clean_html})), {str}, filter, any),
'timestamp': ('createdDateTime', {parse_iso8601}),
'release_timestamp': ('publishedDateTime', {parse_iso8601}),
'modified_timestamp': ('updatedDateTime', {parse_iso8601}),
'thumbnail': ('thumbnail', 'image', 'url', {url_or_none}),
'duration': ('videoMetadata', 'playTime', {int_or_none}),
'tags': ('keywords', ..., {str}),
'uploader': ('provider', 'name', {str}),
'uploader_id': ('provider', 'id', {str}),
})
page_type = json_data['type']
source_url = traverse_obj(json_data, ('sourceHref', {url_or_none}))
if page_type == 'video':
if traverse_obj(json_data, ('thirdPartyVideoPlayer', 'enabled')) and source_url:
return self.url_result(source_url)
formats = []
for file_ in video.get('videoFiles', []):
format_url = file_.get('url')
if not format_url:
continue
if 'format=m3u8-aapl' in format_url:
# m3u8_native should not be used here until
# https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed
formats.extend(self._extract_m3u8_formats(
format_url, display_id, 'mp4',
m3u8_id='hls', fatal=False))
elif 'format=mpd-time-csf' in format_url:
formats.extend(self._extract_mpd_formats(
format_url, display_id, 'dash', fatal=False))
elif '.ism' in format_url:
if format_url.endswith('.ism'):
format_url += '/manifest'
formats.extend(self._extract_ism_formats(
format_url, display_id, 'mss', fatal=False))
else:
format_id = file_.get('formatCode')
formats.append({
'url': format_url,
'ext': 'mp4',
'format_id': format_id,
'width': int_or_none(file_.get('width')),
'height': int_or_none(file_.get('height')),
'vbr': int_or_none(self._search_regex(r'_(\d+)\.mp4', format_url, 'vbr', default=None)),
'quality': 1 if format_id == '1001' else None,
})
subtitles = {}
for file_ in video.get('files', []):
format_url = file_.get('url')
format_code = file_.get('formatCode')
if not format_url or not format_code:
continue
if str(format_code) == '3100':
subtitles.setdefault(file_.get('culture', 'en'), []).append({
'ext': determine_ext(format_url, 'ttml'),
'url': format_url,
})
for file in traverse_obj(json_data, ('videoMetadata', 'externalVideoFiles', lambda _, v: url_or_none(v['url']))):
file_url = file['url']
ext = determine_ext(file_url)
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
file_url, page_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(
file_url, page_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.append(
traverse_obj(file, {
'url': 'url',
'format_id': ('format', {str}),
'filesize': ('fileSize', {int_or_none}),
'height': ('height', {int_or_none}),
'width': ('width', {int_or_none}),
}))
for caption in traverse_obj(json_data, ('videoMetadata', 'closedCaptions', lambda _, v: url_or_none(v['href']))):
lang = caption.get('locale') or 'en-us'
subtitles.setdefault(lang, []).append({
'url': caption['href'],
'ext': 'ttml',
})
entries.append({
'id': video_id,
return {
'id': page_id,
'display_id': display_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('headlineImage', {}).get('url'),
'duration': int_or_none(video.get('durationSecs')),
'uploader': video.get('sourceFriendly'),
'uploader_id': video.get('providerId'),
'creator': video.get('creator'),
'subtitles': subtitles,
'formats': formats,
})
'subtitles': subtitles,
**common_metadata,
}
elif page_type == 'webcontent':
if not source_url:
raise ExtractorError('Could not find source URL')
return self.url_result(source_url)
elif page_type == 'article':
entries = []
for embed_url in traverse_obj(json_data, ('socialEmbeds', ..., 'postUrl', {url_or_none})):
entries.append(self.url_result(embed_url))
if not entries:
error = unescapeHTML(self._search_regex(
r'data-error=(["\'])(?P<error>.+?)\1',
webpage, 'error', group='error'))
raise ExtractorError(f'{self.IE_NAME} said: {error}', expected=True)
return self.playlist_result(entries, page_id, **common_metadata)
return self.playlist_result(entries, page_id)
raise ExtractorError(f'Unsupported page type: {page_type}')

2
yt_dlp/extractor/nbc.py
View File

@@ -736,7 +736,7 @@ class NBCStationsIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
nbc_data = self._search_json(
r'<script>\s*var\s+nbc\s*=', webpage, 'NBC JSON data', video_id)
r'(?:<script>\s*var\s+nbc\s*=|Object\.assign\(nbc,)', webpage, 'NBC JSON data', video_id)
pdk_acct = nbc_data.get('pdkAcct') or 'Yh1nAC'
fw_ssid = traverse_obj(nbc_data, ('video', 'fwSSID'))

169
yt_dlp/extractor/ninenow.py
View File

@@ -1,34 +1,46 @@
import json
import re
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
smuggle_url,
parse_iso8601,
parse_resolution,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import require, traverse_obj, value
class NineNowIE(InfoExtractor):
IE_NAME = '9now.com.au'
_VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/]+/){2}(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU']
_VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/?#]+/){2}(?P<id>(?P<type>clip|episode)-[^/?#]+)'
_GEO_BYPASS = False
_TESTS = [{
# clip
'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
'md5': '17cf47d63ec9323e562c9957a968b565',
'url': 'https://www.9now.com.au/today/season-2025/clip-cm8hw9h5z00080hquqa5hszq7',
'info_dict': {
'id': '16801',
'id': '6370295582112',
'ext': 'mp4',
'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
'description': 'Is a boycott of the NAB Cup "on the table"?',
'title': 'Would Karl Stefanovic be able to land a plane?',
'description': 'The Today host\'s skills are put to the test with the latest simulation tech.',
'uploader_id': '4460760524001',
'upload_date': '20160713',
'timestamp': 1468421266,
'duration': 197.376,
'tags': ['flights', 'technology', 'Karl Stefanovic'],
'season': 'Season 2025',
'season_number': 2025,
'series': 'TODAY',
'timestamp': 1742507988,
'upload_date': '20250320',
'release_timestamp': 1742507983,
'release_date': '20250320',
'thumbnail': r're:https?://.+/1920x0/.+\.jpg',
},
'params': {
'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
},
'skip': 'Only available in Australia',
}, {
# episode
'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
@@ -41,7 +53,7 @@ class NineNowIE(InfoExtractor):
# episode of series
'url': 'https://www.9now.com.au/lego-masters/season-3/episode-3',
'info_dict': {
'id': '6249614030001',
'id': '6308830406112',
'title': 'Episode 3',
'ext': 'mp4',
'season_number': 3,
@@ -50,72 +62,87 @@ class NineNowIE(InfoExtractor):
'uploader_id': '4460760524001',
'timestamp': 1619002200,
'upload_date': '20210421',
'duration': 3574.085,
'thumbnail': r're:https?://.+/1920x0/.+\.jpg',
'tags': ['episode'],
'series': 'Lego Masters',
'season': 'Season 3',
'episode': 'Episode 3',
'release_timestamp': 1619002200,
'release_date': '20210421',
},
'expected_warnings': ['Ignoring subtitle tracks'],
'params': {
'skip_download': True,
'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
},
}, {
'url': 'https://www.9now.com.au/married-at-first-sight/season-12/episode-1',
'info_dict': {
'id': '6367798770112',
'ext': 'mp4',
'title': 'Episode 1',
'description': r're:The cultural sensation of Married At First Sight returns with our first weddings! .{90}$',
'uploader_id': '4460760524001',
'duration': 5415.079,
'thumbnail': r're:https?://.+/1920x0/.+\.png',
'tags': ['episode'],
'season': 'Season 12',
'season_number': 12,
'episode': 'Episode 1',
'episode_number': 1,
'series': 'Married at First Sight',
'timestamp': 1737973800,
'upload_date': '20250127',
'release_timestamp': 1737973800,
'release_date': '20250127',
},
'params': {
'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId=%s'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId={}'
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.francetv and yt_dlp.extractor.goplay
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url):
display_id = self._match_id(url)
display_id, video_type = self._match_valid_url(url).group('id', 'type')
webpage = self._download_webpage(url, display_id)
page_data = self._parse_json(self._search_regex(
r'window\.__data\s*=\s*({.*?});', webpage,
'page data', default='{}'), display_id, fatal=False)
if not page_data:
page_data = self._parse_json(self._parse_json(self._search_regex(
r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
webpage, 'page data'), display_id), display_id)
for kind in ('episode', 'clip'):
current_key = page_data.get(kind, {}).get(
f'current{kind.capitalize()}Key')
if not current_key:
continue
cache = page_data.get(kind, {}).get(f'{kind}Cache', {})
if not cache:
continue
common_data = {
'episode': (cache.get(current_key) or next(iter(cache.values())))[kind],
'season': (cache.get(current_key) or next(iter(cache.values()))).get('season', None),
}
break
else:
raise ExtractorError('Unable to find video data')
common_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {json.loads}, ..., {self._find_json},
lambda _, v: v['payload'][video_type]['slug'] == display_id,
'payload', any, {require('video data')}))
if not self.get_param('allow_unplayable_formats') and try_get(common_data, lambda x: x['episode']['video']['drm'], bool):
if traverse_obj(common_data, (video_type, 'video', 'drm', {bool})):
self.report_drm(display_id)
brightcove_id = try_get(
common_data, lambda x: x['episode']['video']['brightcoveId'], str) or 'ref:{}'.format(common_data['episode']['video']['referenceId'])
video_id = str_or_none(try_get(common_data, lambda x: x['episode']['video']['id'])) or brightcove_id
title = try_get(common_data, lambda x: x['episode']['name'], str)
season_number = try_get(common_data, lambda x: x['season']['seasonNumber'], int)
episode_number = try_get(common_data, lambda x: x['episode']['episodeNumber'], int)
timestamp = unified_timestamp(try_get(common_data, lambda x: x['episode']['airDate'], str))
release_date = unified_strdate(try_get(common_data, lambda x: x['episode']['availability'], str))
thumbnails_data = try_get(common_data, lambda x: x['episode']['image']['sizes'], dict) or {}
thumbnails = [{
'id': thumbnail_id,
'url': thumbnail_url,
'width': int_or_none(thumbnail_id[1:]),
} for thumbnail_id, thumbnail_url in thumbnails_data.items()]
brightcove_id = traverse_obj(common_data, (
video_type, 'video', (
('brightcoveId', {str}),
('referenceId', {str}, {lambda x: f'ref:{x}' if x else None}),
), any, {require('brightcove ID')}))
return {
'_type': 'url_transparent',
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
{'geo_countries': self._GEO_COUNTRIES}),
'id': video_id,
'title': title,
'description': try_get(common_data, lambda x: x['episode']['description'], str),
'duration': float_or_none(try_get(common_data, lambda x: x['episode']['video']['duration'], float), 1000),
'thumbnails': thumbnails,
'ie_key': 'BrightcoveNew',
'season_number': season_number,
'episode_number': episode_number,
'timestamp': timestamp,
'release_date': release_date,
'ie_key': BrightcoveNewIE.ie_key(),
'url': self.BRIGHTCOVE_URL_TEMPLATE.format(brightcove_id),
**traverse_obj(common_data, {
'id': (video_type, 'video', 'id', {int}, ({str_or_none}, {value(brightcove_id)}), any),
'title': (video_type, 'name', {str}),
'description': (video_type, 'description', {str}),
'duration': (video_type, 'video', 'duration', {float_or_none(scale=1000)}),
'tags': (video_type, 'tags', ..., 'name', {str}, all, filter),
'series': ('tvSeries', 'name', {str}),
'season_number': ('season', 'seasonNumber', {int_or_none}),
'episode_number': ('episode', 'episodeNumber', {int_or_none}),
'timestamp': ('episode', 'airDate', {parse_iso8601}),
'release_timestamp': (video_type, 'availability', {parse_iso8601}),
'thumbnails': (video_type, 'image', 'sizes', {dict.items}, lambda _, v: url_or_none(v[1]), {
'id': 0,
'url': 1,
'width': (1, {parse_resolution}, 'width'),
}),
}),
}

25
yt_dlp/extractor/on24.py
View File

@@ -11,12 +11,15 @@ class On24IE(InfoExtractor):
IE_NAME = 'on24'
IE_DESC = 'ON24'
_VALID_URL = r'''(?x)
https?://event\.on24\.com/(?:
wcc/r/(?P<id_1>\d{7})/(?P<key_1>[0-9A-F]{32})|
eventRegistration/(?:console/EventConsoleApollo|EventLobbyServlet\?target=lobby30)
\.jsp\?(?:[^/#?]*&)?eventid=(?P<id_2>\d{7})[^/#?]*&key=(?P<key_2>[0-9A-F]{32})
)'''
_ID_RE = r'(?P<id>\d{7})'
_KEY_RE = r'(?P<key>[0-9A-F]{32})'
_URL_BASE_RE = r'https?://event\.on24\.com'
_URL_QUERY_RE = rf'(?:[^#]*&)?eventid={_ID_RE}&(?:[^#]+&)?key={_KEY_RE}'
_VALID_URL = [
rf'{_URL_BASE_RE}/wcc/r/{_ID_RE}/{_KEY_RE}',
rf'{_URL_BASE_RE}/eventRegistration/console/(?:EventConsoleApollo\.jsp|apollox/mainEvent/?)\?{_URL_QUERY_RE}',
rf'{_URL_BASE_RE}/eventRegistration/EventLobbyServlet/?\?{_URL_QUERY_RE}',
]
_TESTS = [{
'url': 'https://event.on24.com/eventRegistration/console/EventConsoleApollo.jsp?uimode=nextgeneration&eventid=2197467&sessionid=1&key=5DF57BE53237F36A43B478DD36277A84&contenttype=A&eventuserid=305999&playerwidth=1000&playerheight=650&caller=previewLobby&text_language_id=en&format=fhaudio&newConsole=false',
@@ -34,12 +37,16 @@ class On24IE(InfoExtractor):
}, {
'url': 'https://event.on24.com/eventRegistration/console/EventConsoleApollo.jsp?&eventid=2639291&sessionid=1&username=&partnerref=&format=fhvideo1&mobile=&flashsupportedmobiledevice=&helpcenter=&key=82829018E813065A122363877975752E&newConsole=true&nxChe=true&newTabCon=true&text_language_id=en&playerwidth=748&playerheight=526&eventuserid=338788762&contenttype=A&mediametricsessionid=384764716&mediametricid=3558192&usercd=369267058&mode=launch',
'only_matching': True,
}, {
'url': 'https://event.on24.com/eventRegistration/EventLobbyServlet?target=reg20.jsp&eventid=3543176&key=BC0F6B968B67C34B50D461D40FDB3E18&groupId=3143628',
'only_matching': True,
}, {
'url': 'https://event.on24.com/eventRegistration/console/apollox/mainEvent?&eventid=4843671&sessionid=1&username=&partnerref=&format=fhvideo1&mobile=&flashsupportedmobiledevice=&helpcenter=&key=4EAC9B5C564CC98FF29E619B06A2F743&newConsole=true&nxChe=true&newTabCon=true&consoleEarEventConsole=false&consoleEarCloudApi=false&text_language_id=en&playerwidth=748&playerheight=526&referrer=https%3A%2F%2Fevent.on24.com%2Finterface%2Fregistration%2Fautoreg%2Findex.html%3Fsessionid%3D1%26eventid%3D4843671%26key%3D4EAC9B5C564CC98FF29E619B06A2F743%26email%3D000a3e42-7952-4dd6-8f8a-34c38ea3cf02%2540platform%26firstname%3Ds%26lastname%3Ds%26deletecookie%3Dtrue%26event_email%3DN%26marketing_email%3DN%26std1%3D0642572014177%26std2%3D0642572014179%26std3%3D550165f7-a44e-4725-9fe6-716f89908c2b%26std4%3D0&eventuserid=745776448&contenttype=A&mediametricsessionid=640613707&mediametricid=6810717&usercd=745776448&mode=launch',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
event_id = mobj.group('id_1') or mobj.group('id_2')
event_key = mobj.group('key_1') or mobj.group('key_2')
event_id, event_key = self._match_valid_url(url).group('id', 'key')
event_data = self._download_json(
'https://event.on24.com/apic/utilApp/EventConsoleCachedServlet',

101
yt_dlp/extractor/parti.py Normal file
View File

@@ -0,0 +1,101 @@
from .common import InfoExtractor
from ..utils import UserNotLive, int_or_none, parse_iso8601, url_or_none, urljoin
from ..utils.traversal import traverse_obj
class PartiBaseIE(InfoExtractor):
def _call_api(self, path, video_id, note=None):
return self._download_json(
f'https://api-backend.parti.com/parti_v2/profile/{path}', video_id, note)
class PartiVideoIE(PartiBaseIE):
IE_NAME = 'parti:video'
_VALID_URL = r'https?://(?:www\.)?parti\.com/video/(?P<id>\d+)'
_TESTS = [{
'url': 'https://parti.com/video/66284',
'info_dict': {
'id': '66284',
'ext': 'mp4',
'title': 'NOW LIVE ',
'upload_date': '20250327',
'categories': ['Gaming'],
'thumbnail': 'https://assets.parti.com/351424_eb9e5250-2821-484a-9c5f-ca99aa666c87.png',
'channel': 'ItZTMGG',
'timestamp': 1743044379,
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._call_api(f'get_livestream_channel_info/recent/{video_id}', video_id)
return {
'id': video_id,
'formats': self._extract_m3u8_formats(
urljoin('https://watch.parti.com', data['livestream_recording']), video_id, 'mp4'),
**traverse_obj(data, {
'title': ('event_title', {str}),
'channel': ('user_name', {str}),
'thumbnail': ('event_file', {url_or_none}),
'categories': ('category_name', {str}, filter, all),
'timestamp': ('event_start_ts', {int_or_none}),
}),
}
class PartiLivestreamIE(PartiBaseIE):
IE_NAME = 'parti:livestream'
_VALID_URL = r'https?://(?:www\.)?parti\.com/creator/(?P<service>[\w]+)/(?P<id>[\w/-]+)'
_TESTS = [{
'url': 'https://parti.com/creator/parti/Capt_Robs_Adventures',
'info_dict': {
'id': 'Capt_Robs_Adventures',
'ext': 'mp4',
'title': r"re:I'm Live on Parti \d{4}-\d{2}-\d{2} \d{2}:\d{2}",
'view_count': int,
'thumbnail': r're:https://assets\.parti\.com/.+\.png',
'timestamp': 1743879776,
'upload_date': '20250405',
'live_status': 'is_live',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://parti.com/creator/discord/sazboxgaming/0',
'only_matching': True,
}]
def _real_extract(self, url):
service, creator_slug = self._match_valid_url(url).group('service', 'id')
encoded_creator_slug = creator_slug.replace('/', '%23')
creator_id = self._call_api(
f'get_user_by_social_media/{service}/{encoded_creator_slug}',
creator_slug, note='Fetching user ID')
data = self._call_api(
f'get_livestream_channel_info/{creator_id}', creator_id,
note='Fetching user profile feed')['channel_info']
if not traverse_obj(data, ('channel', 'is_live', {bool})):
raise UserNotLive(video_id=creator_id)
channel_info = data['channel']
return {
'id': creator_slug,
'formats': self._extract_m3u8_formats(
channel_info['playback_url'], creator_slug, live=True, query={
'token': channel_info['playback_auth_token'],
'player_version': '1.17.0',
}),
'is_live': True,
**traverse_obj(data, {
'title': ('livestream_event_info', 'event_name', {str}),
'description': ('livestream_event_info', 'event_description', {str}),
'thumbnail': ('livestream_event_info', 'livestream_preview_file', {url_or_none}),
'timestamp': ('stream', 'start_time', {parse_iso8601}),
'view_count': ('stream', 'viewer_count', {int_or_none}),
}),
}

12
yt_dlp/extractor/polskieradio.py
View File

@@ -22,7 +22,7 @@ from ..utils import (
)
class PolskieRadioBaseExtractor(InfoExtractor):
class PolskieRadioBaseIE(InfoExtractor):
def _extract_webpage_player_entries(self, webpage, playlist_id, base_data):
media_urls = set()
@@ -47,7 +47,7 @@ class PolskieRadioBaseExtractor(InfoExtractor):
yield entry
class PolskieRadioLegacyIE(PolskieRadioBaseExtractor):
class PolskieRadioLegacyIE(PolskieRadioBaseIE):
# legacy sites
IE_NAME = 'polskieradio:legacy'
_VALID_URL = r'https?://(?:www\.)?polskieradio(?:24)?\.pl/\d+/\d+/[Aa]rtykul/(?P<id>\d+)'
@@ -127,7 +127,7 @@ class PolskieRadioLegacyIE(PolskieRadioBaseExtractor):
return self.playlist_result(entries, playlist_id, title, description)
class PolskieRadioIE(PolskieRadioBaseExtractor):
class PolskieRadioIE(PolskieRadioBaseIE):
# new next.js sites
_VALID_URL = r'https?://(?:[^/]+\.)?(?:polskieradio(?:24)?|radiokierowcow)\.pl/artykul/(?P<id>\d+)'
_TESTS = [{
@@ -519,7 +519,7 @@ class PolskieRadioPlayerIE(InfoExtractor):
}
class PolskieRadioPodcastBaseExtractor(InfoExtractor):
class PolskieRadioPodcastBaseIE(InfoExtractor):
_API_BASE = 'https://apipodcasts.polskieradio.pl/api'
def _parse_episode(self, data):
@@ -539,7 +539,7 @@ class PolskieRadioPodcastBaseExtractor(InfoExtractor):
}
class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseExtractor):
class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseIE):
IE_NAME = 'polskieradio:podcast:list'
_VALID_URL = r'https?://podcasty\.polskieradio\.pl/podcast/(?P<id>\d+)'
_TESTS = [{
@@ -578,7 +578,7 @@ class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseExtractor):
}
class PolskieRadioPodcastIE(PolskieRadioPodcastBaseExtractor):
class PolskieRadioPodcastIE(PolskieRadioPodcastBaseIE):
IE_NAME = 'polskieradio:podcast'
_VALID_URL = r'https?://podcasty\.polskieradio\.pl/track/(?P<id>[a-f\d]{8}(?:-[a-f\d]{4}){4}[a-f\d]{8})'
_TESTS = [{

8
yt_dlp/extractor/redgifs.py
View File

@@ -12,7 +12,7 @@ from ..utils import (
)
class RedGifsBaseInfoExtractor(InfoExtractor):
class RedGifsBaseIE(InfoExtractor):
_FORMATS = {
'gif': 250,
'sd': 480,
@@ -113,7 +113,7 @@ class RedGifsBaseInfoExtractor(InfoExtractor):
return page_fetcher(page) if page else OnDemandPagedList(page_fetcher, self._PAGE_SIZE)
class RedGifsIE(RedGifsBaseInfoExtractor):
class RedGifsIE(RedGifsBaseIE):
_VALID_URL = r'https?://(?:(?:www\.)?redgifs\.com/(?:watch|ifr)/|thumbs2\.redgifs\.com/)(?P<id>[^-/?#\.]+)'
_TESTS = [{
'url': 'https://www.redgifs.com/watch/squeakyhelplesswisent',
@@ -172,7 +172,7 @@ class RedGifsIE(RedGifsBaseInfoExtractor):
return self._parse_gif_data(video_info['gif'])
class RedGifsSearchIE(RedGifsBaseInfoExtractor):
class RedGifsSearchIE(RedGifsBaseIE):
IE_DESC = 'Redgifs search'
_VALID_URL = r'https?://(?:www\.)?redgifs\.com/browse\?(?P<query>[^#]+)'
_PAGE_SIZE = 80
@@ -226,7 +226,7 @@ class RedGifsSearchIE(RedGifsBaseInfoExtractor):
entries, query_str, tags, f'RedGifs search for {tags}, ordered by {order}')
class RedGifsUserIE(RedGifsBaseInfoExtractor):
class RedGifsUserIE(RedGifsBaseIE):
IE_DESC = 'Redgifs user'
_VALID_URL = r'https?://(?:www\.)?redgifs\.com/users/(?P<username>[^/?#]+)(?:\?(?P<query>[^#]+))?'
_PAGE_SIZE = 80

43
yt_dlp/extractor/roya.py Normal file
View File

@@ -0,0 +1,43 @@
from .common import InfoExtractor
from ..utils.traversal import traverse_obj
class RoyaLiveIE(InfoExtractor):
_VALID_URL = r'https?://roya\.tv/live-stream/(?P<id>\d+)'
_TESTS = [{
'url': 'https://roya.tv/live-stream/1',
'info_dict': {
'id': '1',
'title': r're:Roya TV \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'ext': 'mp4',
'live_status': 'is_live',
},
}, {
'url': 'https://roya.tv/live-stream/21',
'info_dict': {
'id': '21',
'title': r're:Roya News \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'ext': 'mp4',
'live_status': 'is_live',
},
}, {
'url': 'https://roya.tv/live-stream/10000',
'only_matching': True,
}]
def _real_extract(self, url):
media_id = self._match_id(url)
stream_url = self._download_json(
f'https://ticket.roya-tv.com/api/v5/fastchannel/{media_id}', media_id)['data']['secured_url']
title = traverse_obj(
self._download_json('https://backend.roya.tv/api/v01/channels/schedule-pagination', media_id, fatal=False),
('data', 0, 'channel', lambda _, v: str(v['id']) == media_id, 'title', {str}, any))
return {
'id': media_id,
'formats': self._extract_m3u8_formats(stream_url, media_id, 'mp4', m3u8_id='hls', live=True),
'title': title,
'is_live': True,
}

13
yt_dlp/extractor/rtvs.py
View File

@@ -9,7 +9,9 @@ from ..utils import (
class RTVSIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
IE_NAME = 'stvr'
IE_DESC = 'Slovak Television and Radio (formerly RTVS)'
_VALID_URL = r'https?://(?:www\.)?(?:rtvs|stvr)\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
_TESTS = [{
# radio archive
'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
@@ -19,7 +21,7 @@ class RTVSIE(InfoExtractor):
'ext': 'mp3',
'title': 'Ostrov pokladov 1 časť.mp3',
'duration': 2854,
'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0000/b1R8.rtvs.jpg',
'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0000/rtvs-00009383.png',
'display_id': '135331',
},
}, {
@@ -30,7 +32,7 @@ class RTVSIE(InfoExtractor):
'ext': 'mp4',
'title': 'Amaro Džives - Náš deň',
'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.',
'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
'timestamp': 1428555900,
'upload_date': '20150409',
'duration': 4986,
@@ -47,8 +49,11 @@ class RTVSIE(InfoExtractor):
'display_id': '307655',
'duration': 831,
'upload_date': '20211111',
'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0916/robin.jpg',
'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0916/robin.jpg',
},
}, {
'url': 'https://www.stvr.sk/radio/archiv/11224/414872',
'only_matching': True,
}]
def _real_extract(self, url):

61
yt_dlp/extractor/rumble.py
View File

@@ -7,7 +7,6 @@ from ..utils import (
ExtractorError,
UnsupportedError,
clean_html,
determine_ext,
extract_attributes,
format_field,
get_element_by_class,
@@ -36,7 +35,7 @@ class RumbleEmbedIE(InfoExtractor):
'upload_date': '20191020',
'channel_url': 'https://rumble.com/c/WMAR',
'channel': 'WMAR',
'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.qR4e-small-WMAR-2-News-Latest-Headline.jpg',
'thumbnail': r're:https://.+\.jpg',
'duration': 234,
'uploader': 'WMAR',
'live_status': 'not_live',
@@ -52,7 +51,7 @@ class RumbleEmbedIE(InfoExtractor):
'upload_date': '20220217',
'channel_url': 'https://rumble.com/c/CyberTechNews',
'channel': 'CTNews',
'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
'thumbnail': r're:https://.+\.jpg',
'duration': 901,
'uploader': 'CTNews',
'live_status': 'not_live',
@@ -114,6 +113,22 @@ class RumbleEmbedIE(InfoExtractor):
'live_status': 'was_live',
},
'params': {'skip_download': True},
}, {
'url': 'https://rumble.com/embed/v6pezdb',
'info_dict': {
'id': 'v6pezdb',
'ext': 'mp4',
'title': '"Es war einmal ein Mädchen" – Ein filmisches Zeitzeugnis aus Leningrad 1944',
'uploader': 'RT DE',
'channel': 'RT DE',
'channel_url': 'https://rumble.com/c/RTDE',
'duration': 309,
'thumbnail': 'https://1a-1791.com/video/fww1/dc/s8/1/n/z/2/y/nz2yy.qR4e-small-Es-war-einmal-ein-Mdchen-Ei.jpg',
'timestamp': 1743703500,
'upload_date': '20250403',
'live_status': 'not_live',
},
'params': {'skip_download': True},
}, {
'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
'only_matching': True,
@@ -168,40 +183,42 @@ class RumbleEmbedIE(InfoExtractor):
live_status = None
formats = []
for ext, ext_info in (video.get('ua') or {}).items():
if isinstance(ext_info, dict):
for height, video_info in ext_info.items():
for format_type, format_info in (video.get('ua') or {}).items():
if isinstance(format_info, dict):
for height, video_info in format_info.items():
if not traverse_obj(video_info, ('meta', 'h', {int_or_none})):
video_info.setdefault('meta', {})['h'] = height
ext_info = ext_info.values()
format_info = format_info.values()
for video_info in ext_info:
for video_info in format_info:
meta = video_info.get('meta') or {}
if not video_info.get('url'):
continue
if ext == 'hls':
# With default query params returns m3u8 variants which are duplicates, without returns tar files
if format_type == 'tar':
continue
if format_type == 'hls':
if meta.get('live') is True and video.get('live') == 1:
live_status = 'post_live'
formats.extend(self._extract_m3u8_formats(
video_info['url'], video_id,
ext='mp4', m3u8_id='hls', fatal=False, live=live_status == 'is_live'))
continue
timeline = ext == 'timeline'
if timeline:
ext = determine_ext(video_info['url'])
is_timeline = format_type == 'timeline'
is_audio = format_type == 'audio'
formats.append({
'ext': ext,
'acodec': 'none' if timeline else None,
'acodec': 'none' if is_timeline else None,
'vcodec': 'none' if is_audio else None,
'url': video_info['url'],
'format_id': join_nonempty(ext, format_field(meta, 'h', '%sp')),
'format_note': 'Timeline' if timeline else None,
'fps': None if timeline else video.get('fps'),
'format_id': join_nonempty(format_type, format_field(meta, 'h', '%sp')),
'format_note': 'Timeline' if is_timeline else None,
'fps': None if is_timeline or is_audio else video.get('fps'),
**traverse_obj(meta, {
'tbr': 'bitrate',
'filesize': 'size',
'width': 'w',
'height': 'h',
}, expected_type=lambda x: int(x) or None),
'tbr': ('bitrate', {int_or_none}),
'filesize': ('size', {int_or_none}),
'width': ('w', {int_or_none}),
'height': ('h', {int_or_none}),
}),
})
subtitles = {

11
yt_dlp/extractor/sbs.py
View File

@@ -122,6 +122,15 @@ class SBSIE(InfoExtractor):
if traverse_obj(media, ('partOfSeries', {dict})):
media['epName'] = traverse_obj(media, ('title', {str}))
# Need to set different language for forced subs or else they have priority over full subs
fixed_subtitles = {}
for lang, subs in subtitles.items():
for sub in subs:
fixed_lang = lang
if sub['url'].lower().endswith('_fe.vtt'):
fixed_lang += '-forced'
fixed_subtitles.setdefault(fixed_lang, []).append(sub)
return {
'id': video_id,
**traverse_obj(media, {
@@ -151,6 +160,6 @@ class SBSIE(InfoExtractor):
}),
}),
'formats': formats,
'subtitles': subtitles,
'subtitles': fixed_subtitles,
'uploader': 'SBSC',
}

4
yt_dlp/extractor/senategov.py
View File

@@ -13,7 +13,7 @@ from ..utils.traversal import traverse_obj
class SenateISVPIE(InfoExtractor):
_IE_NAME = 'senate.gov:isvp'
IE_NAME = 'senate.gov:isvp'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_EMBED_REGEX = [r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]"]
@@ -137,7 +137,7 @@ class SenateISVPIE(InfoExtractor):
class SenateGovIE(InfoExtractor):
_IE_NAME = 'senate.gov'
IE_NAME = 'senate.gov'
_SUBDOMAIN_RE = '|'.join(map(re.escape, (
'agriculture', 'aging', 'appropriations', 'armed-services', 'banking',
'budget', 'commerce', 'energy', 'epw', 'finance', 'foreign', 'help',

99
yt_dlp/extractor/skyit.py
View File

@@ -2,16 +2,18 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
int_or_none,
parse_duration,
unified_timestamp,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class SkyItPlayerIE(InfoExtractor):
IE_NAME = 'player.sky.it'
_VALID_URL = r'https?://player\.sky\.it/player/(?:external|social)\.html\?.*?\bid=(?P<id>\d+)'
class SkyItBaseIE(InfoExtractor):
_GEO_BYPASS = False
_DOMAIN = 'sky'
_PLAYER_TMPL = 'https://player.sky.it/player/external.html?id=%s&domain=%s'
@@ -33,7 +35,6 @@ class SkyItPlayerIE(InfoExtractor):
SkyItPlayerIE.ie_key(), video_id)
def _parse_video(self, video, video_id):
title = video['title']
is_live = video.get('type') == 'live'
hls_url = video.get(('streaming' if is_live else 'hls') + '_url')
if not hls_url and video.get('geoblock' if is_live else 'geob'):
@@ -43,7 +44,7 @@ class SkyItPlayerIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'title': video.get('title'),
'formats': formats,
'thumbnail': dict_get(video, ('video_still', 'video_still_medium', 'thumb')),
'description': video.get('short_desc') or None,
@@ -52,6 +53,11 @@ class SkyItPlayerIE(InfoExtractor):
'is_live': is_live,
}
class SkyItPlayerIE(SkyItBaseIE):
IE_NAME = 'player.sky.it'
_VALID_URL = r'https?://player\.sky\.it/player/(?:external|social)\.html\?.*?\bid=(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
domain = urllib.parse.parse_qs(urllib.parse.urlparse(
@@ -67,7 +73,7 @@ class SkyItPlayerIE(InfoExtractor):
return self._parse_video(video, video_id)
class SkyItVideoIE(SkyItPlayerIE): # XXX: Do not subclass from concrete IE
class SkyItVideoIE(SkyItBaseIE):
IE_NAME = 'video.sky.it'
_VALID_URL = r'https?://(?:masterchef|video|xfactor)\.sky\.it(?:/[^/]+)*/video/[0-9a-z-]+-(?P<id>\d+)'
_TESTS = [{
@@ -96,7 +102,7 @@ class SkyItVideoIE(SkyItPlayerIE): # XXX: Do not subclass from concrete IE
return self._player_url_result(video_id)
class SkyItVideoLiveIE(SkyItPlayerIE): # XXX: Do not subclass from concrete IE
class SkyItVideoLiveIE(SkyItBaseIE):
IE_NAME = 'video.sky.it:live'
_VALID_URL = r'https?://video\.sky\.it/diretta/(?P<id>[^/?&#]+)'
_TEST = {
@@ -124,7 +130,7 @@ class SkyItVideoLiveIE(SkyItPlayerIE): # XXX: Do not subclass from concrete IE
return self._parse_video(livestream, asset_id)
class SkyItIE(SkyItPlayerIE): # XXX: Do not subclass from concrete IE
class SkyItIE(SkyItBaseIE):
IE_NAME = 'sky.it'
_VALID_URL = r'https?://(?:sport|tg24)\.sky\.it(?:/[^/]+)*/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)'
_TESTS = [{
@@ -223,3 +229,80 @@ class TV8ItIE(SkyItVideoIE): # XXX: Do not subclass from concrete IE
'params': {'skip_download': 'm3u8'},
}]
_DOMAIN = 'mtv8'
class TV8ItLiveIE(SkyItBaseIE):
IE_NAME = 'tv8.it:live'
IE_DESC = 'TV8 Live'
_VALID_URL = r'https?://(?:www\.)?tv8\.it/streaming'
_TESTS = [{
'url': 'https://tv8.it/streaming',
'info_dict': {
'id': 'tv8',
'ext': 'mp4',
'title': str,
'description': str,
'is_live': True,
'live_status': 'is_live',
},
}]
def _real_extract(self, url):
video_id = 'tv8'
livestream = self._download_json(
'https://apid.sky.it/vdp/v1/getLivestream', video_id,
'Downloading manifest JSON', query={'id': '7'})
metadata = self._download_json('https://tv8.it/api/getStreaming', video_id, fatal=False)
return {
**self._parse_video(livestream, video_id),
**traverse_obj(metadata, ('info', {
'title': ('title', 'text', {str}),
'description': ('description', 'html', {clean_html}),
})),
}
class TV8ItPlaylistIE(InfoExtractor):
IE_NAME = 'tv8.it:playlist'
IE_DESC = 'TV8 Playlist'
_VALID_URL = r'https?://(?:www\.)?tv8\.it/(?!video)[^/#?]+/(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'https://tv8.it/intrattenimento/tv8-gialappas-night',
'playlist_mincount': 32,
'info_dict': {
'id': 'tv8-gialappas-night',
'title': 'Tv8 Gialappa\'s Night',
'description': 'md5:c876039d487d9cf40229b768872718ed',
'thumbnail': r're:https://static\.sky\.it/.+\.(png|jpe?g|webp)',
},
}, {
'url': 'https://tv8.it/sport/uefa-europa-league',
'playlist_mincount': 11,
'info_dict': {
'id': 'uefa-europa-league',
'title': 'UEFA Europa League',
'description': 'md5:9ab1832b7a8b1705b1f590e13a36bc6a',
'thumbnail': r're:https://static\.sky\.it/.+\.(png|jpe?g|webp)',
},
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
data = self._search_nextjs_data(webpage, playlist_id)['props']['pageProps']['data']
entries = [self.url_result(
urljoin('https://tv8.it', card['href']), ie=TV8ItIE,
**traverse_obj(card, {
'description': ('extraData', 'videoDesc', {str}),
'id': ('extraData', 'asset_id', {str}),
'thumbnail': ('image', 'src', {url_or_none}),
'title': ('title', 'typography', 'text', {str}),
}))
for card in traverse_obj(data, ('lastContent', 'cards', lambda _, v: v['href']))]
return self.playlist_result(entries, playlist_id, **traverse_obj(data, ('card', 'desktop', {
'description': ('description', 'html', {clean_html}),
'thumbnail': ('image', 'src', {url_or_none}),
'title': ('title', 'text', {str}),
})))

236
yt_dlp/extractor/streaks.py Normal file
View File

@@ -0,0 +1,236 @@
import json
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
filter_dict,
float_or_none,
join_nonempty,
mimetype2ext,
parse_iso8601,
unsmuggle_url,
update_url_query,
url_or_none,
)
from ..utils.traversal import traverse_obj
class StreaksBaseIE(InfoExtractor):
_API_URL_TEMPLATE = 'https://{}.api.streaks.jp/v1/projects/{}/medias/{}{}'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['JP']
def _extract_from_streaks_api(self, project_id, media_id, headers=None, query=None, ssai=False):
try:
response = self._download_json(
self._API_URL_TEMPLATE.format('playback', project_id, media_id, ''),
media_id, 'Downloading STREAKS playback API JSON', headers={
'Accept': 'application/json',
'Origin': 'https://players.streaks.jp',
**self.geo_verification_headers(),
**(headers or {}),
})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status in {403, 404}:
error = self._parse_json(e.cause.response.read().decode(), media_id, fatal=False)
message = traverse_obj(error, ('message', {str}))
code = traverse_obj(error, ('code', {str}))
if code == 'REQUEST_FAILED':
self.raise_geo_restricted(message, countries=self._GEO_COUNTRIES)
elif code == 'MEDIA_NOT_FOUND':
raise ExtractorError(message, expected=True)
elif code or message:
raise ExtractorError(join_nonempty(code, message, delim=': '))
raise
streaks_id = response['id']
live_status = {
'clip': 'was_live',
'file': 'not_live',
'linear': 'is_live',
'live': 'is_live',
}.get(response.get('type'))
formats, subtitles = [], {}
drm_formats = False
for source in traverse_obj(response, ('sources', lambda _, v: v['src'])):
if source.get('key_systems'):
drm_formats = True
continue
src_url = source['src']
is_live = live_status == 'is_live'
ext = mimetype2ext(source.get('type'))
if ext != 'm3u8':
self.report_warning(f'Unsupported stream type: {ext}')
continue
if is_live and ssai:
session_params = traverse_obj(self._download_json(
self._API_URL_TEMPLATE.format('ssai', project_id, streaks_id, '/ssai/session'),
media_id, 'Downloading session parameters',
headers={'Content-Type': 'application/json', 'Accept': 'application/json'},
data=json.dumps({'id': source['id']}).encode(),
), (0, 'query', {urllib.parse.parse_qs}))
src_url = update_url_query(src_url, session_params)
fmts, subs = self._extract_m3u8_formats_and_subtitles(
src_url, media_id, 'mp4', m3u8_id='hls', fatal=False, live=is_live, query=query)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if not formats and drm_formats:
self.report_drm(media_id)
self._remove_duplicate_formats(formats)
for subs in traverse_obj(response, (
'tracks', lambda _, v: v['kind'] in ('captions', 'subtitles') and url_or_none(v['src']),
)):
lang = traverse_obj(subs, ('srclang', {str.lower})) or 'ja'
subtitles.setdefault(lang, []).append({'url': subs['src']})
return {
'id': streaks_id,
'display_id': media_id,
'formats': formats,
'live_status': live_status,
'subtitles': subtitles,
'uploader_id': project_id,
**traverse_obj(response, {
'title': ('name', {str}),
'description': ('description', {str}, filter),
'duration': ('duration', {float_or_none}),
'modified_timestamp': ('updated_at', {parse_iso8601}),
'tags': ('tags', ..., {str}),
'thumbnails': (('poster', 'thumbnail'), 'src', {'url': {url_or_none}}),
'timestamp': ('created_at', {parse_iso8601}),
}),
}
class StreaksIE(StreaksBaseIE):
_VALID_URL = [
r'https?://players\.streaks\.jp/(?P<project_id>[\w-]+)/[\da-f]+/index\.html\?(?:[^#]+&)?m=(?P<id>(?:ref:)?[\w-]+)',
r'https?://playback\.api\.streaks\.jp/v1/projects/(?P<project_id>[\w-]+)/medias/(?P<id>(?:ref:)?[\w-]+)',
]
_EMBED_REGEX = [rf'<iframe\s+[^>]*\bsrc\s*=\s*["\'](?P<url>{_VALID_URL[0]})']
_TESTS = [{
'url': 'https://players.streaks.jp/tipness/08155cd19dc14c12bebefb69b92eafcc/index.html?m=dbdf2df35b4d483ebaeeaeb38c594647',
'info_dict': {
'id': 'dbdf2df35b4d483ebaeeaeb38c594647',
'ext': 'mp4',
'title': '3shunenCM_edit.mp4',
'display_id': 'dbdf2df35b4d483ebaeeaeb38c594647',
'duration': 47.533,
'live_status': 'not_live',
'modified_date': '20230726',
'modified_timestamp': 1690356180,
'timestamp': 1690355996,
'upload_date': '20230726',
'uploader_id': 'tipness',
},
}, {
'url': 'https://players.streaks.jp/ktv-web/0298e8964c164ab384c07ef6e08c444b/index.html?m=ref:mycoffeetime_250317',
'info_dict': {
'id': 'dccdc079e3fd41f88b0c8435e2d453ab',
'ext': 'mp4',
'title': 'わたしの珈琲時間_250317',
'display_id': 'ref:mycoffeetime_250317',
'duration': 122.99,
'live_status': 'not_live',
'modified_date': '20250310',
'modified_timestamp': 1741586302,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1741585839,
'upload_date': '20250310',
'uploader_id': 'ktv-web',
},
}, {
'url': 'https://playback.api.streaks.jp/v1/projects/ktv-web/medias/b5411938e1e5435dac71edf829dd4813',
'info_dict': {
'id': 'b5411938e1e5435dac71edf829dd4813',
'ext': 'mp4',
'title': 'KANTELE_SYUSEi_0630',
'display_id': 'b5411938e1e5435dac71edf829dd4813',
'live_status': 'not_live',
'modified_date': '20250122',
'modified_timestamp': 1737522999,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1735205137,
'upload_date': '20241226',
'uploader_id': 'ktv-web',
},
}, {
# TVer Olympics: website already down, but api remains accessible
'url': 'https://playback.api.streaks.jp/v1/projects/tver-olympic/medias/ref:sp_240806_1748_dvr',
'info_dict': {
'id': 'c10f7345adb648cf804d7578ab93b2e3',
'ext': 'mp4',
'title': 'サッカー 男子 準決勝_dvr',
'display_id': 'ref:sp_240806_1748_dvr',
'duration': 12960.0,
'live_status': 'was_live',
'modified_date': '20240805',
'modified_timestamp': 1722896263,
'timestamp': 1722777618,
'upload_date': '20240804',
'uploader_id': 'tver-olympic',
},
}, {
# TBS FREE: 24-hour stream
'url': 'https://playback.api.streaks.jp/v1/projects/tbs/medias/ref:simul-02',
'info_dict': {
'id': 'c4e83a7b48f4409a96adacec674b4e22',
'ext': 'mp4',
'title': str,
'display_id': 'ref:simul-02',
'live_status': 'is_live',
'modified_date': '20241031',
'modified_timestamp': 1730339858,
'timestamp': 1705466840,
'upload_date': '20240117',
'uploader_id': 'tbs',
},
}, {
# DRM protected
'url': 'https://players.streaks.jp/sp-jbc/a12d7ee0f40c49d6a0a2bff520639677/index.html?m=5f89c62f37ee4a68be8e6e3b1396c7d8',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://event.play.jp/playnext2023/',
'info_dict': {
'id': '2d975178293140dc8074a7fc536a7604',
'ext': 'mp4',
'title': 'PLAY NEXTキームービー（本番）',
'uploader_id': 'play',
'duration': 17.05,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1668387517,
'upload_date': '20221114',
'modified_timestamp': 1739411523,
'modified_date': '20250213',
'live_status': 'not_live',
},
}, {
'url': 'https://wowshop.jp/Page/special/cooking_goods/?bid=wowshop&srsltid=AfmBOor_phUNoPEE_UCPiGGSCMrJE5T2US397smvsbrSdLqUxwON0el4',
'playlist_mincount': 2,
'info_dict': {
'id': '?bid=wowshop&srsltid=AfmBOor_phUNoPEE_UCPiGGSCMrJE5T2US397smvsbrSdLqUxwON0el4',
'title': 'ワンランク上の料理道具でとびきりの“おいしい”を食卓へ｜wowshop',
'description': 'md5:914b5cb8624fc69274c7fb7b2342958f',
'age_limit': 0,
'thumbnail': 'https://wowshop.jp/Page/special/cooking_goods/images/ogp.jpg',
},
}]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
project_id, media_id = self._match_valid_url(url).group('project_id', 'id')
return self._extract_from_streaks_api(
project_id, media_id, headers=filter_dict({
'X-Streaks-Api-Key': smuggled_data.get('api_key'),
}))

6
yt_dlp/extractor/taptap.py
View File

@@ -191,12 +191,12 @@ class TapTapAppIE(TapTapBaseIE):
}]
class TapTapIntlBase(TapTapBaseIE):
class TapTapIntlBaseIE(TapTapBaseIE):
_X_UA = 'V=1&PN=WebAppIntl2&LANG=zh_TW&VN_CODE=115&VN=0.1.0&LOC=CN&PLT=PC&DS=Android&UID={uuid}&CURR=&DT=PC&OS=Windows&OSV=NT%208.0.0'
_VIDEO_API = 'https://www.taptap.io/webapiv2/video-resource/v1/multi-get'
class TapTapAppIntlIE(TapTapIntlBase):
class TapTapAppIntlIE(TapTapIntlBaseIE):
_VALID_URL = r'https?://www\.taptap\.io/app/(?P<id>\d+)'
_INFO_API = 'https://www.taptap.io/webapiv2/i/app/v5/detail'
_DATA_PATH = 'app'
@@ -227,7 +227,7 @@ class TapTapAppIntlIE(TapTapIntlBase):
}]
class TapTapPostIntlIE(TapTapIntlBase):
class TapTapPostIntlIE(TapTapIntlBaseIE):
_VALID_URL = r'https?://www\.taptap\.io/post/(?P<id>\d+)'
_INFO_API = 'https://www.taptap.io/webapiv2/creation/post/v1/detail'
_INFO_QUERY_KEY = 'id_str'

2
yt_dlp/extractor/telecinco.py
View File

@@ -46,7 +46,7 @@ class TelecincoBaseIE(InfoExtractor):
error_code = traverse_obj(
self._webpage_read_content(error.cause.response, caronte['cerbero'], video_id, fatal=False),
({json.loads}, 'code', {int}))
if error_code == 4038:
if error_code in (4038, 40313):
self.raise_geo_restricted(countries=['ES'])
raise

149
yt_dlp/extractor/tver.py
View File

@@ -1,31 +1,70 @@
from .common import InfoExtractor
from .streaks import StreaksBaseIE
from ..utils import (
ExtractorError,
int_or_none,
join_nonempty,
make_archive_id,
smuggle_url,
str_or_none,
strip_or_none,
traverse_obj,
update_url_query,
)
from ..utils.traversal import require, traverse_obj
class TVerIE(InfoExtractor):
class TVerIE(StreaksBaseIE):
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature)/)+(?P<id>[a-zA-Z0-9]+)'
_GEO_COUNTRIES = ['JP']
_GEO_BYPASS = False
_TESTS = [{
'skip': 'videos are only available for 7 days',
'url': 'https://tver.jp/episodes/ep83nf3w4p',
# via Streaks backend
'url': 'https://tver.jp/episodes/epc1hdugbk',
'info_dict': {
'title': '家事ヤロウ!!! 売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
'description': 'md5:dc2c06b6acc23f1e7c730c513737719b',
'series': '家事ヤロウ!!!',
'episode': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
'alt_title': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
'channel': 'テレビ朝日',
'id': 'ep83nf3w4p',
'id': 'epc1hdugbk',
'ext': 'mp4',
'display_id': 'ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068',
'title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル）',
'alt_title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル） 日テレ',
'description': 'md5:2726f742d5e3886edeaf72fb6d740fef',
'uploader_id': 'tver-ntv',
'channel': '日テレ',
'duration': 1158.024,
'thumbnail': 'https://statics.tver.jp/images/content/thumbnail/episode/xlarge/epc1hdugbk.jpg?v=16',
'series': '神回だけ見せます！',
'episode': '#2 壮烈！車大騎馬戦（木曜スペシャル）',
'episode_number': 2,
'timestamp': 1736486036,
'upload_date': '20250110',
'modified_timestamp': 1736870264,
'modified_date': '20250114',
'live_status': 'not_live',
'release_timestamp': 1651453200,
'release_date': '20220502',
'_old_archive_ids': ['brightcovenew ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068'],
},
'add_ie': ['BrightcoveNew'],
}, {
# via Brightcove backend (deprecated)
'url': 'https://tver.jp/episodes/epc1hdugbk',
'info_dict': {
'id': 'ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068',
'ext': 'mp4',
'title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル）',
'alt_title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル） 日テレ',
'description': 'md5:2726f742d5e3886edeaf72fb6d740fef',
'uploader_id': '4394098882001',
'channel': '日テレ',
'duration': 1158.101,
'thumbnail': 'https://statics.tver.jp/images/content/thumbnail/episode/xlarge/epc1hdugbk.jpg?v=16',
'tags': [],
'series': '神回だけ見せます！',
'episode': '#2 壮烈！車大騎馬戦（木曜スペシャル）',
'episode_number': 2,
'timestamp': 1651388531,
'upload_date': '20220501',
'release_timestamp': 1651453200,
'release_date': '20220502',
},
'params': {'extractor_args': {'tver': {'backend': ['brightcove']}}},
}, {
'url': 'https://tver.jp/corner/f0103888',
'only_matching': True,
@@ -38,26 +77,7 @@ class TVerIE(InfoExtractor):
'id': 'srtxft431v',
'title': '名探偵コナン',
},
'playlist': [
{
'md5': '779ffd97493ed59b0a6277ea726b389e',
'info_dict': {
'id': 'ref:conan-1137-241005',
'ext': 'mp4',
'title': '名探偵コナン #1137「行列店、味変の秘密」',
'uploader_id': '5330942432001',
'tags': [],
'channel': '読売テレビ',
'series': '名探偵コナン',
'description': 'md5:601fccc1d2430d942a2c8068c4b33eb5',
'episode': '#1137「行列店、味変の秘密」',
'duration': 1469.077,
'timestamp': 1728030405,
'upload_date': '20241004',
'alt_title': '名探偵コナン #1137「行列店、味変の秘密」 読売テレビ 10月5日(土)放送分',
'thumbnail': r're:https://.+\.jpg',
},
}],
'playlist_mincount': 21,
}, {
'url': 'https://tver.jp/series/sru35hwdd2',
'info_dict': {
@@ -70,7 +90,11 @@ class TVerIE(InfoExtractor):
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
_HEADERS = {'x-tver-platform-type': 'web'}
_HEADERS = {
'x-tver-platform-type': 'web',
'Origin': 'https://tver.jp',
'Referer': 'https://tver.jp/',
}
_PLATFORM_QUERY = {}
def _real_initialize(self):
@@ -103,6 +127,9 @@ class TVerIE(InfoExtractor):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
backend = self._configuration_arg('backend', ['streaks'])[0]
if backend not in ('brightcove', 'streaks'):
raise ExtractorError(f'Invalid backend value: {backend}', expected=True)
if video_type == 'series':
series_info = self._call_platform_api(
@@ -129,12 +156,6 @@ class TVerIE(InfoExtractor):
video_info = self._download_json(
f'https://statics.tver.jp/content/episode/{video_id}.json', video_id, 'Downloading video info',
query={'v': version}, headers={'Referer': 'https://tver.jp/'})
p_id = video_info['video']['accountID']
r_id = traverse_obj(video_info, ('video', ('videoRefID', 'videoID')), get_all=False)
if not r_id:
raise ExtractorError('Failed to extract reference ID for Brightcove')
if not r_id.isdigit():
r_id = f'ref:{r_id}'
episode = strip_or_none(episode_content.get('title'))
series = str_or_none(episode_content.get('seriesTitle'))
@@ -161,17 +182,53 @@ class TVerIE(InfoExtractor):
]
]
return {
'_type': 'url_transparent',
metadata = {
'title': title,
'series': series,
'episode': episode,
# an another title which is considered "full title" for some viewers
'alt_title': join_nonempty(title, provider, onair_label, delim=' '),
'channel': provider,
'description': str_or_none(video_info.get('description')),
'thumbnails': thumbnails,
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id), {'geo_countries': ['JP']}),
'ie_key': 'BrightcoveNew',
**traverse_obj(video_info, {
'description': ('description', {str}),
'release_timestamp': ('viewStatus', 'startAt', {int_or_none}),
'episode_number': ('no', {int_or_none}),
}),
}
brightcove_id = traverse_obj(video_info, ('video', ('videoRefID', 'videoID'), {str}, any))
if brightcove_id and not brightcove_id.isdecimal():
brightcove_id = f'ref:{brightcove_id}'
streaks_id = traverse_obj(video_info, ('streaks', 'videoRefID', {str}))
if streaks_id and not streaks_id.startswith('ref:'):
streaks_id = f'ref:{streaks_id}'
# Deprecated Brightcove extraction reachable w/extractor-arg or fallback; errors are expected
if backend == 'brightcove' or not streaks_id:
if backend != 'brightcove':
self.report_warning(
'No STREAKS ID found; falling back to Brightcove extraction', video_id=video_id)
if not brightcove_id:
raise ExtractorError('Unable to extract brightcove reference ID', expected=True)
account_id = traverse_obj(video_info, (
'video', 'accountID', {str}, {require('brightcove account ID', expected=True)}))
return {
**metadata,
'_type': 'url_transparent',
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, brightcove_id),
{'geo_countries': ['JP']}),
'ie_key': 'BrightcoveNew',
}
return {
**self._extract_from_streaks_api(video_info['streaks']['projectID'], streaks_id, {
'Origin': 'https://tver.jp',
'Referer': 'https://tver.jp/',
}),
**metadata,
'id': video_id,
'_old_archive_ids': [make_archive_id('BrightcoveNew', brightcove_id)] if brightcove_id else None,
}

171
yt_dlp/extractor/twitch.py
View File

@@ -14,19 +14,20 @@ from ..utils import (
dict_get,
float_or_none,
int_or_none,
join_nonempty,
make_archive_id,
parse_duration,
parse_iso8601,
parse_qs,
qualities,
str_or_none,
traverse_obj,
try_get,
unified_timestamp,
update_url_query,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj, value
class TwitchBaseIE(InfoExtractor):
@@ -42,10 +43,10 @@ class TwitchBaseIE(InfoExtractor):
'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
'ShareClipRenderStatus': 'f130048a462a0ac86bb54d653c968c514e9ab9ca94db52368c1179e97b0f16eb',
'ChannelCollectionsContent': '447aec6a0cc1e8d0a8d7732d47eb0762c336a2294fdb009e9c9d854e49d484b9',
'StreamMetadata': 'a647c2a13599e5991e175155f798ca7f1ecddde73f7f341f39009c14dbf59962',
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
'VideoAccessToken_Clip': '36b89d2507fce29e5ca551df756d27c1cfe079e2609642b4390aa4c35796eb11',
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
'VideoMetadata': '49b5b8f268cdeb259d75b58dcb0c1a748e3b575003448a2333dc5cdafd49adad',
'VideoPlayer_ChapterSelectButtonVideo': '8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41',
@@ -1083,16 +1084,44 @@ class TwitchClipsIE(TwitchBaseIE):
'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat',
'md5': '761769e1eafce0ffebfb4089cb3847cd',
'info_dict': {
'id': '42850523',
'id': '396245304',
'display_id': 'FaintLightGullWholeWheat',
'ext': 'mp4',
'title': 'EA Play 2016 Live from the Novo Theatre',
'duration': 32,
'view_count': int,
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1465767393,
'upload_date': '20160612',
'creator': 'EA',
'uploader': 'stereotype_',
'uploader_id': '43566419',
'creators': ['EA'],
'channel': 'EA',
'channel_id': '25163635',
'channel_is_verified': False,
'channel_follower_count': int,
'uploader': 'EA',
'uploader_id': '25163635',
},
}, {
'url': 'https://www.twitch.tv/xqc/clip/CulturedAmazingKuduDatSheffy-TiZ_-ixAGYR3y2Uy',
'md5': 'e90fe616b36e722a8cfa562547c543f0',
'info_dict': {
'id': '3207364882',
'display_id': 'CulturedAmazingKuduDatSheffy-TiZ_-ixAGYR3y2Uy',
'ext': 'mp4',
'title': 'A day in the life of xQc',
'duration': 60,
'view_count': int,
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1742869615,
'upload_date': '20250325',
'creators': ['xQc'],
'channel': 'xQc',
'channel_id': '71092938',
'channel_is_verified': True,
'channel_follower_count': int,
'uploader': 'xQc',
'uploader_id': '71092938',
'categories': ['Just Chatting'],
},
}, {
# multiple formats
@@ -1116,16 +1145,14 @@ class TwitchClipsIE(TwitchBaseIE):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
slug = self._match_id(url)
clip = self._download_gql(
video_id, [{
'operationName': 'VideoAccessToken_Clip',
'variables': {
'slug': video_id,
},
slug, [{
'operationName': 'ShareClipRenderStatus',
'variables': {'slug': slug},
}],
'Downloading clip access token GraphQL')[0]['data']['clip']
'Downloading clip GraphQL')[0]['data']['clip']
if not clip:
raise ExtractorError(
@@ -1135,81 +1162,71 @@ class TwitchClipsIE(TwitchBaseIE):
'sig': clip['playbackAccessToken']['signature'],
'token': clip['playbackAccessToken']['value'],
}
data = self._download_base_gql(
video_id, {
'query': '''{
clip(slug: "%s") {
broadcaster {
displayName
}
createdAt
curator {
displayName
id
}
durationSeconds
id
tiny: thumbnailURL(width: 86, height: 45)
small: thumbnailURL(width: 260, height: 147)
medium: thumbnailURL(width: 480, height: 272)
title
videoQualities {
frameRate
quality
sourceURL
}
viewCount
}
}''' % video_id}, 'Downloading clip GraphQL', fatal=False) # noqa: UP031
if data:
clip = try_get(data, lambda x: x['data']['clip'], dict) or clip
asset_default = traverse_obj(clip, ('assets', 0, {dict})) or {}
asset_portrait = traverse_obj(clip, ('assets', 1, {dict})) or {}
formats = []
for option in clip.get('videoQualities', []):
if not isinstance(option, dict):
continue
source = url_or_none(option.get('sourceURL'))
if not source:
continue
default_aspect_ratio = float_or_none(asset_default.get('aspectRatio'))
formats.extend(traverse_obj(asset_default, ('videoQualities', lambda _, v: url_or_none(v['sourceURL']), {
'url': ('sourceURL', {update_url_query(query=access_query)}),
'format_id': ('quality', {str}),
'height': ('quality', {int_or_none}),
'fps': ('frameRate', {float_or_none}),
'aspect_ratio': {value(default_aspect_ratio)},
})))
portrait_aspect_ratio = float_or_none(asset_portrait.get('aspectRatio'))
for source in traverse_obj(asset_portrait, ('videoQualities', lambda _, v: url_or_none(v['sourceURL']))):
formats.append({
'url': update_url_query(source, access_query),
'format_id': option.get('quality'),
'height': int_or_none(option.get('quality')),
'fps': int_or_none(option.get('frameRate')),
'url': update_url_query(source['sourceURL'], access_query),
'format_id': join_nonempty('portrait', source.get('quality')),
'height': int_or_none(source.get('quality')),
'fps': float_or_none(source.get('frameRate')),
'aspect_ratio': portrait_aspect_ratio,
'quality': -2,
})
thumbnails = []
for thumbnail_id in ('tiny', 'small', 'medium'):
thumbnail_url = clip.get(thumbnail_id)
if not thumbnail_url:
continue
thumb = {
'id': thumbnail_id,
'url': thumbnail_url,
}
mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url)
if mobj:
thumb.update({
'height': int(mobj.group(2)),
'width': int(mobj.group(1)),
})
thumbnails.append(thumb)
thumb_asset_default_url = url_or_none(asset_default.get('thumbnailURL'))
if thumb_asset_default_url:
thumbnails.append({
'id': 'default',
'url': thumb_asset_default_url,
'preference': 0,
})
if thumb_asset_portrait_url := url_or_none(asset_portrait.get('thumbnailURL')):
thumbnails.append({
'id': 'portrait',
'url': thumb_asset_portrait_url,
'preference': -1,
})
thumb_default_url = url_or_none(clip.get('thumbnailURL'))
if thumb_default_url and thumb_default_url != thumb_asset_default_url:
thumbnails.append({
'id': 'small',
'url': thumb_default_url,
'preference': -2,
})
old_id = self._search_regex(r'%7C(\d+)(?:-\d+)?.mp4', formats[-1]['url'], 'old id', default=None)
return {
'id': clip.get('id') or video_id,
'id': clip.get('id') or slug,
'_old_archive_ids': [make_archive_id(self, old_id)] if old_id else None,
'display_id': video_id,
'title': clip.get('title'),
'display_id': slug,
'formats': formats,
'duration': int_or_none(clip.get('durationSeconds')),
'view_count': int_or_none(clip.get('viewCount')),
'timestamp': unified_timestamp(clip.get('createdAt')),
'thumbnails': thumbnails,
'creator': try_get(clip, lambda x: x['broadcaster']['displayName'], str),
'uploader': try_get(clip, lambda x: x['curator']['displayName'], str),
'uploader_id': try_get(clip, lambda x: x['curator']['id'], str),
**traverse_obj(clip, {
'title': ('title', {str}),
'duration': ('durationSeconds', {int_or_none}),
'view_count': ('viewCount', {int_or_none}),
'timestamp': ('createdAt', {parse_iso8601}),
'creators': ('broadcaster', 'displayName', {str}, filter, all),
'channel': ('broadcaster', 'displayName', {str}),
'channel_id': ('broadcaster', 'id', {str}),
'channel_follower_count': ('broadcaster', 'followers', 'totalCount', {int_or_none}),
'channel_is_verified': ('broadcaster', 'isPartner', {bool}),
'uploader': ('broadcaster', 'displayName', {str}),
'uploader_id': ('broadcaster', 'id', {str}),
'categories': ('game', 'displayName', {str}, filter, all, filter),
}),
}

8
yt_dlp/extractor/unsupported.py
View File

@@ -51,6 +51,8 @@ class KnownDRMIE(UnsupportedInfoExtractor):
r'(?:watch|front)\.njpwworld\.com',
r'qub\.ca/vrai',
r'(?:beta\.)?crunchyroll\.com',
r'viki\.com',
r'deezer\.com',
)
_TESTS = [{
@@ -160,6 +162,12 @@ class KnownDRMIE(UnsupportedInfoExtractor):
}, {
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
'only_matching': True,
}, {
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
'only_matching': True,
}, {
'url': 'http://www.deezer.com/playlist/176747451',
'only_matching': True,
}]
def _real_extract(self, url):

346
yt_dlp/extractor/viki.py
View File

@@ -1,346 +0,0 @@
import hashlib
import hmac
import json
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
parse_iso8601,
try_get,
)
class VikiBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
_API_URL_TEMPLATE = 'https://api.viki.io%s'
_DEVICE_ID = '112395910d'
_APP = '100005a'
_APP_VERSION = '6.11.3'
_APP_SECRET = 'd96704b180208dbb2efa30fe44c48bd8690441af9f567ba8fd710a72badc85198f7472'
_GEO_BYPASS = False
_NETRC_MACHINE = 'viki'
_token = None
_ERRORS = {
'geo': 'Sorry, this content is not available in your region.',
'upcoming': 'Sorry, this content is not yet available.',
'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
}
def _stream_headers(self, timestamp, sig):
return {
'X-Viki-manufacturer': 'vivo',
'X-Viki-device-model': 'vivo 1606',
'X-Viki-device-os-ver': '6.0.1',
'X-Viki-connection-type': 'WIFI',
'X-Viki-carrier': '',
'X-Viki-as-id': '100005a-1625321982-3932',
'timestamp': str(timestamp),
'signature': str(sig),
'x-viki-app-ver': self._APP_VERSION,
}
def _api_query(self, path, version=4, **kwargs):
path += '?' if '?' not in path else '&'
query = f'/v{version}/{path}app={self._APP}'
if self._token:
query += f'&token={self._token}'
return query + ''.join(f'&{name}={val}' for name, val in kwargs.items())
def _sign_query(self, path):
timestamp = int(time.time())
query = self._api_query(path, version=5)
sig = hmac.new(
self._APP_SECRET.encode('ascii'), f'{query}&t={timestamp}'.encode('ascii'), hashlib.sha1).hexdigest()
return timestamp, sig, self._API_URL_TEMPLATE % query
def _call_api(
self, path, video_id, note='Downloading JSON metadata', data=None, query=None, fatal=True):
if query is None:
timestamp, sig, url = self._sign_query(path)
else:
url = self._API_URL_TEMPLATE % self._api_query(path, version=4)
resp = self._download_json(
url, video_id, note, fatal=fatal, query=query,
data=json.dumps(data).encode() if data else None,
headers=({'x-viki-app-ver': self._APP_VERSION} if data
else self._stream_headers(timestamp, sig) if query is None
else None), expected_status=400) or {}
self._raise_error(resp.get('error'), fatal)
return resp
def _raise_error(self, error, fatal=True):
if error is None:
return
msg = f'{self.IE_NAME} said: {error}'
if fatal:
raise ExtractorError(msg, expected=True)
else:
self.report_warning(msg)
def _check_errors(self, data):
for reason, status in (data.get('blocking') or {}).items():
if status and reason in self._ERRORS:
message = self._ERRORS[reason]
if reason == 'geo':
self.raise_geo_restricted(msg=message)
elif reason == 'paywall':
if try_get(data, lambda x: x['paywallable']['tvod']):
self._raise_error('This video is for rent only or TVOD (Transactional Video On demand)')
self.raise_login_required(message)
self._raise_error(message)
def _perform_login(self, username, password):
self._token = self._call_api(
'sessions.json', None, 'Logging in', fatal=False,
data={'username': username, 'password': password}).get('token')
if not self._token:
self.report_warning('Login Failed: Unable to get session token')
@staticmethod
def dict_selection(dict_obj, preferred_key):
if preferred_key in dict_obj:
return dict_obj[preferred_key]
return (list(filter(None, dict_obj.values())) or [None])[0]
class VikiIE(VikiBaseIE):
IE_NAME = 'viki'
_VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:videos|player)/(?P<id>[0-9]+v)'
_TESTS = [{
'note': 'Free non-DRM video with storyboards in MPD',
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
'info_dict': {
'id': '1175236v',
'ext': 'mp4',
'title': 'Choosing Spouse by Lottery - Episode 1',
'timestamp': 1606463239,
'age_limit': 13,
'uploader': 'FCC',
'upload_date': '20201127',
},
}, {
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
'info_dict': {
'id': '1023585v',
'ext': 'mp4',
'title': 'Heirs - Episode 14',
'uploader': 'SBS Contents Hub',
'timestamp': 1385047627,
'upload_date': '20131121',
'age_limit': 13,
'duration': 3570,
'episode_number': 14,
},
'skip': 'Blocked in the US',
}, {
# clip
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
'md5': '86c0b5dbd4d83a6611a79987cc7a1989',
'info_dict': {
'id': '1067139v',
'ext': 'mp4',
'title': "'The Avengers: Age of Ultron' Press Conference",
'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
'duration': 352,
'timestamp': 1430380829,
'upload_date': '20150430',
'uploader': 'Arirang TV',
'like_count': int,
'age_limit': 0,
},
'skip': 'Sorry. There was an error loading this video',
}, {
'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
'info_dict': {
'id': '1048879v',
'ext': 'mp4',
'title': 'Ankhon Dekhi',
'duration': 6512,
'timestamp': 1408532356,
'upload_date': '20140820',
'uploader': 'Spuul',
'like_count': int,
'age_limit': 13,
},
'skip': 'Blocked in the US',
}, {
# episode
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
'md5': '0a53dc252e6e690feccd756861495a8c',
'info_dict': {
'id': '44699v',
'ext': 'mp4',
'title': 'Boys Over Flowers - Episode 1',
'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
'duration': 4172,
'timestamp': 1270496524,
'upload_date': '20100405',
'uploader': 'group8',
'like_count': int,
'age_limit': 13,
'episode_number': 1,
},
}, {
# youtube external
'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
'md5': '63f8600c1da6f01b7640eee7eca4f1da',
'info_dict': {
'id': '50562v',
'ext': 'webm',
'title': 'Poor Nastya [COMPLETE] - Episode 1',
'description': '',
'duration': 606,
'timestamp': 1274949505,
'upload_date': '20101213',
'uploader': 'ad14065n',
'uploader_id': 'ad14065n',
'like_count': int,
'age_limit': 13,
},
'skip': 'Page not found!',
}, {
'url': 'http://www.viki.com/player/44699v',
'only_matching': True,
}, {
# non-English description
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
'md5': '41faaba0de90483fb4848952af7c7d0d',
'info_dict': {
'id': '158036v',
'ext': 'mp4',
'uploader': 'I Planet Entertainment',
'upload_date': '20111122',
'timestamp': 1321985454,
'description': 'md5:44b1e46619df3a072294645c770cef36',
'title': 'Love In Magic',
'age_limit': 13,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._call_api(f'videos/{video_id}.json', video_id, 'Downloading video JSON', query={})
self._check_errors(video)
title = try_get(video, lambda x: x['titles']['en'], str)
episode_number = int_or_none(video.get('number'))
if not title:
title = f'Episode {episode_number}' if video.get('type') == 'episode' else video.get('id') or video_id
container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
container_title = self.dict_selection(container_titles, 'en')
title = f'{container_title} - {title}'
thumbnails = [{
'id': thumbnail_id,
'url': thumbnail['url'],
} for thumbnail_id, thumbnail in (video.get('images') or {}).items() if thumbnail.get('url')]
resp = self._call_api(
f'playback_streams/{video_id}.json?drms=dt3&device_id={self._DEVICE_ID}',
video_id, 'Downloading video streams JSON')['main'][0]
stream_id = try_get(resp, lambda x: x['properties']['track']['stream_id'])
subtitles = dict((lang, [{
'ext': ext,
'url': self._API_URL_TEMPLATE % self._api_query(
f'videos/{video_id}/auth_subtitles/{lang}.{ext}', stream_id=stream_id),
} for ext in ('srt', 'vtt')]) for lang in (video.get('subtitle_completions') or {}))
mpd_url = resp['url']
# 720p is hidden in another MPD which can be found in the current manifest content
mpd_content = self._download_webpage(mpd_url, video_id, note='Downloading initial MPD manifest')
mpd_url = self._search_regex(
r'(?mi)<BaseURL>(http.+.mpd)', mpd_content, 'new manifest', default=mpd_url)
if 'mpdhd_high' not in mpd_url and 'sig=' not in mpd_url:
# Modify the URL to get 1080p
mpd_url = mpd_url.replace('mpdhd', 'mpdhd_high')
formats = self._extract_mpd_formats(mpd_url, video_id)
return {
'id': video_id,
'formats': formats,
'title': title,
'description': self.dict_selection(video.get('descriptions', {}), 'en'),
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('created_at')),
'uploader': video.get('author'),
'uploader_url': video.get('author_url'),
'like_count': int_or_none(try_get(video, lambda x: x['likes']['count'])),
'age_limit': parse_age_limit(video.get('rating')),
'thumbnails': thumbnails,
'subtitles': subtitles,
'episode_number': episode_number,
}
class VikiChannelIE(VikiBaseIE):
IE_NAME = 'viki:channel'
_VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:tv|news|movies|artists)/(?P<id>[0-9]+c)'
_TESTS = [{
'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
'info_dict': {
'id': '50c',
'title': 'Boys Over Flowers',
'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
},
'playlist_mincount': 51,
}, {
'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
'info_dict': {
'id': '1354c',
'title': 'Poor Nastya [COMPLETE]',
'description': 'md5:05bf5471385aa8b21c18ad450e350525',
},
'playlist_count': 127,
'skip': 'Page not found',
}, {
'url': 'http://www.viki.com/news/24569c-showbiz-korea',
'only_matching': True,
}, {
'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005',
'only_matching': True,
}, {
'url': 'http://www.viki.com/artists/2141c-shinee',
'only_matching': True,
}]
_video_types = ('episodes', 'movies', 'clips', 'trailers')
def _entries(self, channel_id):
params = {
'app': self._APP, 'token': self._token, 'only_ids': 'true',
'direction': 'asc', 'sort': 'number', 'per_page': 30,
}
video_types = self._configuration_arg('video_types') or self._video_types
for video_type in video_types:
if video_type not in self._video_types:
self.report_warning(f'Unknown video_type: {video_type}')
page_num = 0
while True:
page_num += 1
params['page'] = page_num
res = self._call_api(
f'containers/{channel_id}/{video_type}.json', channel_id, query=params, fatal=False,
note=f'Downloading {video_type.title()} JSON page {page_num}')
for video_id in res.get('response') or []:
yield self.url_result(f'https://www.viki.com/videos/{video_id}', VikiIE.ie_key(), video_id)
if not res.get('more'):
break
def _real_extract(self, url):
channel_id = self._match_id(url)
channel = self._call_api(f'containers/{channel_id}.json', channel_id, 'Downloading channel JSON')
self._check_errors(channel)
return self.playlist_result(
self._entries(channel_id), channel_id,
self.dict_selection(channel['titles'], 'en'),
self.dict_selection(channel['descriptions'], 'en'))

2
yt_dlp/extractor/vk.py
View File

@@ -544,7 +544,7 @@ class VKIE(VKBaseIE):
'uploader_id': (('author_id', 'authorId'), {str_or_none}, any),
'duration': ('duration', {int_or_none}),
'chapters': ('time_codes', lambda _, v: isinstance(v['time'], int), {
'title': ('text', {str}),
'title': ('text', {unescapeHTML}),
'start_time': 'time',
}),
}),

185
yt_dlp/extractor/vrsquare.py Normal file
View File

@@ -0,0 +1,185 @@
import itertools
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
parse_duration,
parse_qs,
)
from ..utils.traversal import (
find_element,
find_elements,
traverse_obj,
)
class VrSquareIE(InfoExtractor):
IE_NAME = 'vrsquare'
IE_DESC = 'VR SQUARE'
_BASE_URL = 'https://livr.jp'
_VALID_URL = r'https?://livr\.jp/contents/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://livr.jp/contents/P470896661',
'info_dict': {
'id': 'P470896661',
'ext': 'mp4',
'title': 'そこ曲がったら、櫻坂？ ７年間お疲れ様！菅井友香の卒業を祝う会！前半 2022年11月6日放送分',
'description': 'md5:523726dc835aa8014dfe1e2b38d36cd1',
'duration': 1515.0,
'tags': 'count:2',
'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
},
}, {
'url': 'https://livr.jp/contents/P589523973',
'info_dict': {
'id': 'P589523973',
'ext': 'mp4',
'title': '薄闇に仰ぐ しだれ桜の妖艶',
'description': 'md5:a042f517b2cbb4ed6746707afec4d306',
'duration': 1084.0,
'tags': list,
'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
},
'skip': 'Paid video',
}, {
'url': 'https://livr.jp/contents/P316939908',
'info_dict': {
'id': 'P316939908',
'ext': 'mp4',
'title': '2024年5月16日（木） 「今日は誰に恋をする？」公演 小栗有以 生誕祭',
'description': 'md5:2110bdcf947f28bd7d06ec420e51b619',
'duration': 8559.0,
'tags': list,
'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
},
'skip': 'Premium channel subscribers only',
}, {
# Accessible only in the VR SQUARE app
'url': 'https://livr.jp/contents/P126481458',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
status = self._download_json(
f'{self._BASE_URL}/webApi/contentsStatus/{video_id}',
video_id, 'Checking contents status', fatal=False)
if traverse_obj(status, 'result_code') == '40407':
self.raise_login_required('Unable to access this video')
try:
web_api = self._download_json(
f'{self._BASE_URL}/webApi/play/url/{video_id}', video_id)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 500:
raise ExtractorError('VR SQUARE app-only videos are not supported', expected=True)
raise
return {
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': self._html_search_meta('description', webpage),
'formats': self._extract_m3u8_formats(traverse_obj(web_api, (
'urls', ..., 'url', any)), video_id, 'mp4', fatal=False),
'thumbnail': self._html_search_meta('og:image', webpage),
**traverse_obj(webpage, {
'duration': ({find_element(cls='layout-product-data-time')}, {parse_duration}),
'tags': ({find_elements(cls='search-tag')}, ..., {clean_html}),
}),
}
class VrSquarePlaylistBaseIE(InfoExtractor):
_BASE_URL = 'https://livr.jp'
def _fetch_vids(self, source, keys=()):
for url_path in traverse_obj(source, (
*keys, {find_elements(cls='video', html=True)}, ...,
{extract_attributes}, 'data-url', {str}, filter),
):
yield self.url_result(
f'{self._BASE_URL}/contents/{url_path.removeprefix("/contents/")}', VrSquareIE)
def _entries(self, path, display_id, query=None):
for page in itertools.count(1):
ajax = self._download_json(
f'{self._BASE_URL}{path}', display_id,
f'Downloading playlist JSON page {page}',
query={'p': page, **(query or {})})
yield from self._fetch_vids(ajax, ('contents_render_list', ...))
if not traverse_obj(ajax, (('has_next', 'hasNext'), {bool}, any)):
break
class VrSquareChannelIE(VrSquarePlaylistBaseIE):
IE_NAME = 'vrsquare:channel'
_VALID_URL = r'https?://livr\.jp/channel/(?P<id>\w+)'
_TESTS = [{
'url': 'https://livr.jp/channel/H372648599',
'info_dict': {
'id': 'H372648599',
'title': 'AKB48＋チャンネル',
},
'playlist_mincount': 502,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
return self.playlist_result(
self._entries(f'/ajax/channel/{playlist_id}', playlist_id),
playlist_id, self._html_search_meta('og:title', webpage))
class VrSquareSearchIE(VrSquarePlaylistBaseIE):
IE_NAME = 'vrsquare:search'
_VALID_URL = r'https?://livr\.jp/web-search/?\?(?:[^#]+&)?w=[^#]+'
_TESTS = [{
'url': 'https://livr.jp/web-search?w=%23%E5%B0%8F%E6%A0%97%E6%9C%89%E4%BB%A5',
'info_dict': {
'id': '#小栗有以',
},
'playlist_mincount': 60,
}]
def _real_extract(self, url):
search_query = parse_qs(url)['w'][0]
return self.playlist_result(
self._entries('/ajax/web-search', search_query, {'w': search_query}), search_query)
class VrSquareSectionIE(VrSquarePlaylistBaseIE):
IE_NAME = 'vrsquare:section'
_VALID_URL = r'https?://livr\.jp/(?:category|headline)/(?P<id>\w+)'
_TESTS = [{
'url': 'https://livr.jp/category/C133936275',
'info_dict': {
'id': 'C133936275',
'title': 'そこ曲がったら、櫻坂？VR',
},
'playlist_mincount': 308,
}, {
'url': 'https://livr.jp/headline/A296449604',
'info_dict': {
'id': 'A296449604',
'title': 'AKB48 アフターVR',
},
'playlist_mincount': 22,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
return self.playlist_result(
self._fetch_vids(webpage), playlist_id, self._html_search_meta('og:title', webpage))

97
yt_dlp/extractor/vrt.py
View File

@@ -201,7 +201,35 @@ class VrtNUIE(VRTBaseIE):
'timestamp': 1740373200,
'title': 'Reeks 6 volledig vanaf 3 maart',
'upload_date': '20250224',
'_old_archive_ids': ['canvas pbs-pub-c8a78645-5d3e-468a-89ec-6f3ed5534bd5$vid-242ddfe9-18f5-4e16-ab45-09b122a19251'],
'_old_archive_ids': [
'canvas pbs-pub-c8a78645-5d3e-468a-89ec-6f3ed5534bd5$vid-242ddfe9-18f5-4e16-ab45-09b122a19251',
'ketnet pbs-pub-c8a78645-5d3e-468a-89ec-6f3ed5534bd5$vid-242ddfe9-18f5-4e16-ab45-09b122a19251',
],
},
}, {
'url': 'https://www.vrt.be/vrtmax/a-z/meisjes/6/meisjes-s6a5/',
'info_dict': {
'id': 'pbs-pub-97b541ab-e05c-43b9-9a40-445702ef7189$vid-5e306921-a9aa-4fa9-9f39-5b82c8f1028e',
'ext': 'mp4',
'channel': 'ketnet',
'description': 'md5:713793f15cbf677f66200b36b7b1ec5a',
'display_id': 'meisjes-s6a5',
'duration': 1336.02,
'episode': 'Week 5',
'episode_id': '1684157692901',
'episode_number': 5,
'season': '6',
'season_id': '1684157692901',
'season_number': 6,
'series': 'Meisjes',
'thumbnail': 'https://images.vrt.be/orig/2023/05/14/bf526ae0-f1d9-11ed-91d7-02b7b76bf47f.jpg',
'timestamp': 1685251800,
'title': 'Week 5',
'upload_date': '20230528',
'_old_archive_ids': [
'canvas pbs-pub-97b541ab-e05c-43b9-9a40-445702ef7189$vid-5e306921-a9aa-4fa9-9f39-5b82c8f1028e',
'ketnet pbs-pub-97b541ab-e05c-43b9-9a40-445702ef7189$vid-5e306921-a9aa-4fa9-9f39-5b82c8f1028e',
],
},
}, {
'url': 'https://www.vrt.be/vrtnu/a-z/taboe/3/taboe-s3a4/',
@@ -223,7 +251,10 @@ class VrtNUIE(VRTBaseIE):
'timestamp': 1740286800,
'title': 'Mensen met het syndroom van Gilles de la Tourette',
'upload_date': '20250223',
'_old_archive_ids': ['canvas pbs-pub-f50faa3a-1778-46b6-9117-4ba85f197703$vid-547507fe-1c8b-4394-b361-21e627cbd0fd'],
'_old_archive_ids': [
'canvas pbs-pub-f50faa3a-1778-46b6-9117-4ba85f197703$vid-547507fe-1c8b-4394-b361-21e627cbd0fd',
'ketnet pbs-pub-f50faa3a-1778-46b6-9117-4ba85f197703$vid-547507fe-1c8b-4394-b361-21e627cbd0fd',
],
},
}]
_NETRC_MACHINE = 'vrtnu'
@@ -423,66 +454,8 @@ class VrtNUIE(VRTBaseIE):
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'_old_archive_ids': [make_archive_id('Canvas', video_id)],
}
class KetnetIE(VRTBaseIE):
_VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'https://www.ketnet.be/kijken/m/meisjes/6/meisjes-s6a5',
'info_dict': {
'id': 'pbs-pub-39f8351c-a0a0-43e6-8394-205d597d6162$vid-5e306921-a9aa-4fa9-9f39-5b82c8f1028e',
'ext': 'mp4',
'title': 'Meisjes',
'episode': 'Reeks 6: Week 5',
'season': 'Reeks 6',
'series': 'Meisjes',
'timestamp': 1685251800,
'upload_date': '20230528',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
video = self._download_json(
'https://senior-bff.ketnet.be/graphql', display_id, query={
'query': '''{
video(id: "content/ketnet/nl/%s.model.json") {
description
episodeNr
imageUrl
mediaReference
programTitle
publicationDate
seasonTitle
subtitleVideodetail
titleVideodetail
}
}''' % display_id, # noqa: UP031
})['data']['video']
video_id = urllib.parse.unquote(video['mediaReference'])
data = self._call_api(video_id, 'ketnet@PROD', version='v1')
formats, subtitles = self._extract_formats_and_subtitles(data, video_id)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'_old_archive_ids': [make_archive_id('Canvas', video_id)],
**traverse_obj(video, {
'title': ('titleVideodetail', {str}),
'description': ('description', {str}),
'thumbnail': ('thumbnail', {url_or_none}),
'timestamp': ('publicationDate', {parse_iso8601}),
'series': ('programTitle', {str}),
'season': ('seasonTitle', {str}),
'episode': ('subtitleVideodetail', {str}),
'episode_number': ('episodeNr', {int_or_none}),
}),
'_old_archive_ids': [make_archive_id('Canvas', video_id),
make_archive_id('Ketnet', video_id)],
}

4
yt_dlp/extractor/weibo.py
View File

@@ -109,7 +109,7 @@ class WeiboBaseIE(InfoExtractor):
**traverse_obj(video_info, {
'display_id': ('mblogid', {str_or_none}),
'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'),
{lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}, filter),
{lambda x: x.replace('\n', ' ')}, {truncate_string(left=72)}, filter),
'alt_title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, filter),
'description': ('text_raw', {str}),
'duration': ('page_info', 'media_info', 'duration', {int_or_none}),
@@ -213,6 +213,7 @@ class WeiboVideoIE(WeiboBaseIE):
'ext': 'mp4',
'display_id': 'LEZDodaiW',
'title': '呃，稍微了解了一下靡烟miya，感觉这东西也太二了',
'alt_title': '呃，稍微了解了一下靡烟miya，感觉这东西也太二了',
'description': '呃，稍微了解了一下靡烟miya，感觉这东西也太二了 http://t.cn/A6aerGsM \u200b\u200b\u200b',
'duration': 76,
'timestamp': 1659344278,
@@ -224,6 +225,7 @@ class WeiboVideoIE(WeiboBaseIE):
'view_count': int,
'like_count': int,
'repost_count': int,
'_old_archive_ids': ['weibomobile 4797700463137878'],
},
}]

10
yt_dlp/extractor/wykop.py
View File

@@ -11,7 +11,7 @@ from ..utils import (
)
class WykopBaseExtractor(InfoExtractor):
class WykopBaseIE(InfoExtractor):
def _get_token(self, force_refresh=False):
if not force_refresh:
maybe_cached = self.cache.load('wykop', 'bearer')
@@ -72,7 +72,7 @@ class WykopBaseExtractor(InfoExtractor):
}
class WykopDigIE(WykopBaseExtractor):
class WykopDigIE(WykopBaseIE):
IE_NAME = 'wykop:dig'
_VALID_URL = r'https?://(?:www\.)?wykop\.pl/link/(?P<id>\d+)'
@@ -128,7 +128,7 @@ class WykopDigIE(WykopBaseExtractor):
}
class WykopDigCommentIE(WykopBaseExtractor):
class WykopDigCommentIE(WykopBaseIE):
IE_NAME = 'wykop:dig:comment'
_VALID_URL = r'https?://(?:www\.)?wykop\.pl/link/(?P<dig_id>\d+)/[^/]+/komentarz/(?P<id>\d+)'
@@ -177,7 +177,7 @@ class WykopDigCommentIE(WykopBaseExtractor):
}
class WykopPostIE(WykopBaseExtractor):
class WykopPostIE(WykopBaseIE):
IE_NAME = 'wykop:post'
_VALID_URL = r'https?://(?:www\.)?wykop\.pl/wpis/(?P<id>\d+)'
@@ -228,7 +228,7 @@ class WykopPostIE(WykopBaseExtractor):
}
class WykopPostCommentIE(WykopBaseExtractor):
class WykopPostCommentIE(WykopBaseIE):
IE_NAME = 'wykop:post:comment'
_VALID_URL = r'https?://(?:www\.)?wykop\.pl/wpis/(?P<post_id>\d+)/[^/#]+#(?P<id>\d+)'

14
yt_dlp/extractor/youporn.py
View File

@@ -227,7 +227,7 @@ class YouPornIE(InfoExtractor):
return result
class YouPornListBase(InfoExtractor):
class YouPornListBaseIE(InfoExtractor):
def _get_next_url(self, url, pl_id, html):
return urljoin(url, self._search_regex(
r'''<a [^>]*?\bhref\s*=\s*("|')(?P<url>(?:(?!\1)[^>])+)\1''',
@@ -284,7 +284,7 @@ class YouPornListBase(InfoExtractor):
playlist_id=pl_id, playlist_title=title)
class YouPornCategoryIE(YouPornListBase):
class YouPornCategoryIE(YouPornListBaseIE):
IE_DESC = 'YouPorn category, with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
@@ -319,7 +319,7 @@ class YouPornCategoryIE(YouPornListBase):
}]
class YouPornChannelIE(YouPornListBase):
class YouPornChannelIE(YouPornListBaseIE):
IE_DESC = 'YouPorn channel, with sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
@@ -349,7 +349,7 @@ class YouPornChannelIE(YouPornListBase):
return re.sub(r'_', ' ', title_slug).title()
class YouPornCollectionIE(YouPornListBase):
class YouPornCollectionIE(YouPornListBaseIE):
IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
@@ -394,7 +394,7 @@ class YouPornCollectionIE(YouPornListBase):
return playlist
class YouPornTagIE(YouPornListBase):
class YouPornTagIE(YouPornListBaseIE):
IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
@@ -442,7 +442,7 @@ class YouPornTagIE(YouPornListBase):
return super()._real_extract(url)
class YouPornStarIE(YouPornListBase):
class YouPornStarIE(YouPornListBaseIE):
IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
@@ -493,7 +493,7 @@ class YouPornStarIE(YouPornListBase):
}
class YouPornVideosIE(YouPornListBase):
class YouPornVideosIE(YouPornListBaseIE):
IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/

12
yt_dlp/extractor/youtube/_base.py
View File

@@ -803,12 +803,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
@classmethod
def _extract_continuation_ep_data(cls, continuation_ep: dict):
if isinstance(continuation_ep, dict):
continuation = try_get(
continuation_ep, lambda x: x['continuationCommand']['token'], str)
continuation_commands = traverse_obj(
continuation_ep, ('commandExecutorCommand', 'commands', ..., {dict}))
continuation_commands.append(continuation_ep)
for command in continuation_commands:
continuation = traverse_obj(command, ('continuationCommand', 'token', {str}))
if not continuation:
return
ctp = continuation_ep.get('clickTrackingParams')
continue
ctp = command.get('clickTrackingParams')
return cls._build_api_continuation_query(continuation, ctp)
@classmethod

185
yt_dlp/extractor/youtube/_video.py
View File

@@ -34,6 +34,7 @@ from ...utils import (
clean_html,
datetime_from_str,
filesize_from_tbr,
filter_dict,
float_or_none,
format_field,
get_first,
@@ -130,7 +131,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
_RETURN_TYPE = 'video' # XXX: How to handle multifeed?
_PLAYER_INFO_RE = (
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/(?:tv-)?player',
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
)
@@ -1760,6 +1761,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
},
]
_PLAYER_JS_VARIANT_MAP = {
'main': 'player_ias.vflset/en_US/base.js',
'tce': 'player_ias_tce.vflset/en_US/base.js',
'tv': 'tv-player-ias.vflset/tv-player-ias.js',
'tv_es6': 'tv-player-es6.vflset/tv-player-es6.js',
'phone': 'player-plasma-ias-phone-en_US.vflset/base.js',
'tablet': 'player-plasma-ias-tablet-en_US.vflset/base.js',
}
_INVERSE_PLAYER_JS_VARIANT_MAP = {v: k for k, v in _PLAYER_JS_VARIANT_MAP.items()}
@classmethod
def suitable(cls, url):
from yt_dlp.utils import parse_qs
@@ -1939,11 +1950,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
get_all=False, expected_type=str)
if not player_url:
return
# TODO: Add proper support for the 'tce' variant players
# See https://github.com/yt-dlp/yt-dlp/issues/12398
if '/player_ias_tce.vflset/' in player_url:
self.write_debug(f'Modifying tce player URL: {player_url}')
player_url = player_url.replace('/player_ias_tce.vflset/', '/player_ias.vflset/')
requested_js_variant = self._configuration_arg('player_js_variant', [''])[0] or 'actual'
if requested_js_variant in self._PLAYER_JS_VARIANT_MAP:
player_id = self._extract_player_info(player_url)
original_url = player_url
player_url = f'/s/player/{player_id}/{self._PLAYER_JS_VARIANT_MAP[requested_js_variant]}'
if original_url != player_url:
self.write_debug(
f'Forcing "{requested_js_variant}" player JS variant for player {player_id}\n'
f' original url = {original_url}', only_once=True)
elif requested_js_variant != 'actual':
self.report_warning(
f'Invalid player JS variant name "{requested_js_variant}" requested. '
f'Valid choices are: {", ".join(self._PLAYER_JS_VARIANT_MAP)}', only_once=True)
return urljoin('https://www.youtube.com', player_url)
def _download_player_url(self, video_id, fatal=False):
@@ -1958,6 +1979,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if player_version:
return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
def _player_js_cache_key(self, player_url):
player_id = self._extract_player_info(player_url)
player_path = remove_start(urllib.parse.urlparse(player_url).path, f'/s/player/{player_id}/')
variant = self._INVERSE_PLAYER_JS_VARIANT_MAP.get(player_path)
if not variant:
self.write_debug(
f'Unable to determine player JS variant\n'
f' player = {player_url}', only_once=True)
variant = re.sub(r'[^a-zA-Z0-9]', '_', remove_end(player_path, '.js'))
return join_nonempty(player_id, variant)
def _signature_cache_id(self, example_sig):
""" Return a string representation of a signature """
return '.'.join(str(len(part)) for part in example_sig.split('.'))
@@ -1973,30 +2005,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return id_m.group('id')
def _load_player(self, video_id, player_url, fatal=True):
player_id = self._extract_player_info(player_url)
if player_id not in self._code_cache:
player_js_key = self._player_js_cache_key(player_url)
if player_js_key not in self._code_cache:
code = self._download_webpage(
player_url, video_id, fatal=fatal,
note='Downloading player ' + player_id,
errnote=f'Download of {player_url} failed')
note=f'Downloading player {player_js_key}',
errnote=f'Download of {player_js_key} failed')
if code:
self._code_cache[player_id] = code
return self._code_cache.get(player_id)
self._code_cache[player_js_key] = code
return self._code_cache.get(player_js_key)
def _extract_signature_function(self, video_id, player_url, example_sig):
player_id = self._extract_player_info(player_url)
# Read from filesystem cache
func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
func_id = join_nonempty(
self._player_js_cache_key(player_url), self._signature_cache_id(example_sig))
assert os.path.basename(func_id) == func_id
self.write_debug(f'Extracting signature function {func_id}')
cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
cache_spec, code = self.cache.load('youtube-sigfuncs', func_id, min_ver='2025.03.31'), None
if not cache_spec:
code = self._load_player(video_id, player_url)
if code:
res = self._parse_sig_js(code)
res = self._parse_sig_js(code, player_url)
test_string = ''.join(map(chr, range(len(example_sig))))
cache_spec = [ord(c) for c in res(test_string)]
self.cache.store('youtube-sigfuncs', func_id, cache_spec)
@@ -2044,7 +2075,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f' return {expr_code}\n')
self.to_screen('Extracted signature function:\n' + code)
def _parse_sig_js(self, jscode):
def _parse_sig_js(self, jscode, player_url):
# Examples where `sig` is funcname:
# sig=function(a){a=a.split(""); ... ;return a.join("")};
# ;c&&(c=sig(decodeURIComponent(c)),a.set(b,encodeURIComponent(c)));return a};
@@ -2068,8 +2099,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
jsi = JSInterpreter(jscode)
initial_function = jsi.extract_function(funcname)
initial_function = jsi.extract_function(funcname, filter_dict({varname: global_list}))
return lambda s: initial_function([s])
def _cached(self, func, *cache_id):
@@ -2088,6 +2120,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return ret
return inner
def _load_nsig_code_from_cache(self, player_url):
cache_id = ('youtube-nsig', self._player_js_cache_key(player_url))
if func_code := self._player_cache.get(cache_id):
return func_code
func_code = self.cache.load(*cache_id, min_ver='2025.03.31')
if func_code:
self._player_cache[cache_id] = func_code
return func_code
def _store_nsig_code_to_cache(self, player_url, func_code):
cache_id = ('youtube-nsig', self._player_js_cache_key(player_url))
if cache_id not in self._player_cache:
self.cache.store(*cache_id, func_code)
self._player_cache[cache_id] = func_code
def _decrypt_signature(self, s, video_id, player_url):
"""Turn the encrypted s field into a working signature"""
extract_sig = self._cached(
@@ -2128,9 +2178,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_id=video_id, note='Executing signature code').strip()
self.write_debug(f'Decrypted nsig {s} => {ret}')
# Only cache nsig func JS code to disk if successful, and only once
self._store_nsig_code_to_cache(player_url, func_code)
return ret
def _extract_n_function_name(self, jscode, player_url=None):
varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
if debug_str := traverse_obj(global_list, (lambda _, v: v.endswith('_w8_'), any)):
funcname = self._search_regex(
r'''(?xs)
[;\n](?:
(?P<f>function\s+)|
(?:var\s+)?
)(?P<funcname>[a-zA-Z0-9_$]+)\s*(?(f)|=\s*function\s*)
\((?P<argname>[a-zA-Z0-9_$]+)\)\s*\{
(?:(?!\}[;\n]).)+
\}\s*catch\(\s*[a-zA-Z0-9_$]+\s*\)\s*
\{\s*return\s+%s\[%d\]\s*\+\s*(?P=argname)\s*\}\s*return\s+[^}]+\}[;\n]
''' % (re.escape(varname), global_list.index(debug_str)),
jscode, 'nsig function name', group='funcname', default=None)
if funcname:
return funcname
self.write_debug(join_nonempty(
'Initial search was unable to find nsig function name',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
# Examples (with placeholders nfunc, narray, idx):
# * .get("n"))&&(b=nfunc(b)
# * .get("n"))&&(b=narray[idx](b)
@@ -2160,7 +2232,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if not funcname:
self.report_warning(join_nonempty(
'Falling back to generic n function search',
player_url and f' player = {player_url}', delim='\n'))
player_url and f' player = {player_url}', delim='\n'), only_once=True)
return self._search_regex(
r'''(?xs)
;\s*(?P<name>[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\)
@@ -2173,14 +2245,60 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
def _fixup_n_function_code(self, argnames, code):
return argnames, re.sub(
rf';\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(["\'])undefined\1\s*\)\s*return\s+{argnames[0]};',
';', code)
def _extract_player_js_global_var(self, jscode, player_url):
"""Returns tuple of strings: variable assignment code, variable name, variable value code"""
extract_global_var = self._cached(self._search_regex, 'js global array', player_url)
varcode, varname, varvalue = extract_global_var(
r'''(?x)
(?P<q1>["\'])use\s+strict(?P=q1);\s*
(?P<code>
var\s+(?P<name>[a-zA-Z0-9_$]+)\s*=\s*
(?P<value>
(?P<q2>["\'])(?:(?!(?P=q2)).|\\.)+(?P=q2)
\.split\((?P<q3>["\'])(?:(?!(?P=q3)).)+(?P=q3)\)
|\[\s*(?:(?P<q4>["\'])(?:(?!(?P=q4)).|\\.)*(?P=q4)\s*,?\s*)+\]
)
)[;,]
''', jscode, 'global variable', group=('code', 'name', 'value'), default=(None, None, None))
if not varcode:
self.write_debug(join_nonempty(
'No global array variable found in player JS',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
return varcode, varname, varvalue
def _interpret_player_js_global_var(self, jscode, player_url):
"""Returns tuple of: variable name string, variable value list"""
_, varname, array_code = self._extract_player_js_global_var(jscode, player_url)
jsi = JSInterpreter(array_code)
interpret_global_var = self._cached(jsi.interpret_expression, 'js global list', player_url)
return varname, interpret_global_var(array_code, {}, allow_recursion=10)
def _fixup_n_function_code(self, argnames, nsig_code, jscode, player_url):
varcode, varname, _ = self._extract_player_js_global_var(jscode, player_url)
if varcode and varname:
nsig_code = varcode + '; ' + nsig_code
_, global_list = self._interpret_player_js_global_var(jscode, player_url)
else:
varname = 'dlp_wins'
global_list = []
undefined_idx = global_list.index('undefined') if 'undefined' in global_list else r'\d+'
fixed_code = re.sub(
rf'''(?x)
;\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(?:
(["\'])undefined\1|
{re.escape(varname)}\[{undefined_idx}\]
)\s*\)\s*return\s+{re.escape(argnames[0])};
''', ';', nsig_code)
if fixed_code == nsig_code:
self.write_debug(join_nonempty(
'No typeof statement found in nsig function code',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
return argnames, fixed_code
def _extract_n_function_code(self, video_id, player_url):
player_id = self._extract_player_info(player_url)
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2025.02.19')
func_code = self._load_nsig_code_from_cache(player_url)
jscode = func_code or self._load_player(video_id, player_url)
jsi = JSInterpreter(jscode)
@@ -2189,10 +2307,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
func_name = self._extract_n_function_name(jscode, player_url=player_url)
# XXX: Workaround for the `typeof` gotcha
func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name))
# XXX: Workaround for the global array variable and lack of `typeof` implementation
func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name), jscode, player_url)
self.cache.store('youtube-nsig', player_id, func_code)
return jsi, player_id, func_code
def _extract_n_function_from_code(self, jsi, func_code):
@@ -3141,14 +3258,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'n': decrypt_nsig(query['n'][0], video_id, player_url),
})
except ExtractorError as e:
phantomjs_hint = ''
if isinstance(e, JSInterpreter.Exception):
phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
if player_url:
self.report_warning(
f'nsig extraction failed: Some formats may be missing\n{phantomjs_hint}'
f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
f'nsig extraction failed: Some formats may be missing\n'
f' n = {query["n"][0]} ; player = {player_url}\n'
f' {bug_reports_message(before="")}',
video_id=video_id, only_once=True)
self.write_debug(e, only_once=True)
else:
self.report_warning(
@@ -3165,7 +3280,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
is_damaged = try_call(lambda: format_duration < duration // 2)
if is_damaged:
self.report_warning(
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
'Some formats are possibly damaged. They will be deprioritized', video_id, only_once=True)
po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)