artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-10 02:43:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into playsuisse-handle-locale-parameters-from-urls

Browse Source
This commit is contained in:
v3DJG6GL 2025-04-10 12:27:25 +02:00 committed by GitHub
commit 87cb35a0c6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
15 changed files with 467 additions and 151 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/test_utils.py
View File

@ -659,6 +659,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
self.assertEqual(url_or_none('ws://foo.de'), 'ws://foo.de')
self.assertEqual(url_or_none('wss://foo.de'), 'wss://foo.de')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)

1
yt_dlp/downloader/niconico.py
View File

@ -85,6 +85,7 @@ class NiconicoLiveFD(FileDownloader):
'quality': live_quality,
'protocol': 'hls+fmp4',
'latency': live_latency,
'accessRightMethod': 'single_cookie',
'chasePlay': False,
},
'room': {

11
yt_dlp/extractor/_extractors.py
View File

@ -903,6 +903,7 @@ from .ivi import (
IviIE,
)
from .ivideon import IvideonIE
from .ivoox import IvooxIE
from .iwara import (
IwaraIE,
IwaraPlaylistIE,
@ -960,7 +961,10 @@ from .kick import (
)
from .kicker import KickerIE
from .kickstarter import KickStarterIE
from .kika import KikaIE
from .kika import (
KikaIE,
KikaPlaylistIE,
)
from .kinja import KinjaEmbedIE
from .kinopoisk import KinoPoiskIE
from .kommunetv import KommunetvIE
@ -1061,6 +1065,7 @@ from .loom import (
from .lovehomeporn import LoveHomePornIE
from .lrt import (
LRTVODIE,
LRTRadioIE,
LRTStreamIE,
)
from .lsm import (
@ -1493,6 +1498,10 @@ from .paramountplus import (
)
from .parler import ParlerIE
from .parlview import ParlviewIE
from .parti import (
PartiLivestreamIE,
PartiVideoIE,
)
from .patreon import (
PatreonCampaignIE,
PatreonIE,

27
yt_dlp/extractor/agora.py
View File

@ -146,7 +146,7 @@ class TokFMPodcastIE(InfoExtractor):
'url': 'https://audycje.tokfm.pl/podcast/91275,-Systemowy-rasizm-Czy-zamieszki-w-USA-po-morderstwie-w-Minneapolis-doprowadza-do-zmian-w-sluzbach-panstwowych',
'info_dict': {
'id': '91275',
'ext': 'aac',
'ext': 'mp3',
'title': 'md5:a9b15488009065556900169fb8061cce',
'episode': 'md5:a9b15488009065556900169fb8061cce',
'series': 'Analizy',
@ -164,23 +164,20 @@ class TokFMPodcastIE(InfoExtractor):
raise ExtractorError('No such podcast', expected=True)
metadata = metadata[0]
formats = []
for ext in ('aac', 'mp3'):
url_data = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
media_id, f'Downloading podcast {ext} URL')
# prevents inserting the mp3 (default) multiple times
if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
formats.append({
'url': url_data['link_ssl'],
'ext': ext,
'vcodec': 'none',
'acodec': ext,
})
mp3_url = self._download_json(
'https://api.podcast.radioagora.pl/api4/getSongUrl',
media_id, 'Downloading podcast mp3 URL', query={
'podcast_id': media_id,
'device_id': str(uuid.uuid4()),
'ppre': 'false',
'audio': 'mp3',
})['link_ssl']
return {
'id': media_id,
'formats': formats,
'url': mp3_url,
'vcodec': 'none',
'ext': 'mp3',
'title': metadata.get('podcast_name'),
'series': metadata.get('series_name'),
'episode': metadata.get('podcast_name'),

2
yt_dlp/extractor/common.py
View File

@ -1570,6 +1570,8 @@ class InfoExtractor:
"""Yield all json ld objects in the html"""
if default is not NO_DEFAULT:
fatal = False
if not fatal and not isinstance(html, str):
return
for mobj in re.finditer(JSON_LD_RE, html):
json_ld_item = self._parse_json(
mobj.group('json_ld'), video_id, fatal=fatal,

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'],

78
yt_dlp/extractor/ivoox.py Normal file
View File

@ -0,0 +1,78 @@
from .common import InfoExtractor
from ..utils import int_or_none, parse_iso8601, url_or_none, urljoin
from ..utils.traversal import traverse_obj
class IvooxIE(InfoExtractor):
_VALID_URL = (
r'https?://(?:www\.)?ivoox\.com/(?:\w{2}/)?[^/?#]+_rf_(?P<id>[0-9]+)_1\.html',
r'https?://go\.ivoox\.com/rf/(?P<id>[0-9]+)',
)
_TESTS = [{
'url': 'https://www.ivoox.com/dex-08x30-rostros-del-mal-los-asesinos-en-audios-mp3_rf_143594959_1.html',
'md5': '993f712de5b7d552459fc66aa3726885',
'info_dict': {
'id': '143594959',
'ext': 'mp3',
'timestamp': 1742731200,
'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
'description': 'md5:eae8b4b9740d0216d3871390b056bb08',
'uploader': 'Santiago Camacho',
'thumbnail': 'https://static-1.ivoox.com/audios/c/d/5/2/cd52f46783fe735000c33a803dce2554_XXL.jpg',
'upload_date': '20250323',
'episode': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
'duration': 11837,
'tags': ['españa', 'asesinos en serie', 'arropiero', 'historia criminal', 'mataviejas'],
},
}, {
'url': 'https://go.ivoox.com/rf/143594959',
'only_matching': True,
}, {
'url': 'https://www.ivoox.com/en/campodelgas-28-03-2025-audios-mp3_rf_144036942_1.html',
'only_matching': True,
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id, fatal=False)
data = self._search_nuxt_data(
webpage, media_id, fatal=False, traverse=('data', 0, 'data', 'audio'))
direct_download = self._download_json(
f'https://vcore-web.ivoox.com/v1/public/audios/{media_id}/download-url', media_id, fatal=False,
note='Fetching direct download link', headers={'Referer': url})
download_paths = {
*traverse_obj(direct_download, ('data', 'downloadUrl', {str}, filter, all)),
*traverse_obj(data, (('downloadUrl', 'mediaUrl'), {str}, filter)),
}
formats = []
for path in download_paths:
formats.append({
'url': urljoin('https://ivoox.com', path),
'http_headers': {'Referer': url},
})
return {
'id': media_id,
'formats': formats,
'uploader': self._html_search_regex(r'data-prm-author="([^"]+)"', webpage, 'author', default=None),
'timestamp': parse_iso8601(
self._html_search_regex(r'data-prm-pubdate="([^"]+)"', webpage, 'timestamp', default=None)),
'channel': self._html_search_regex(r'data-prm-podname="([^"]+)"', webpage, 'channel', default=None),
'title': self._html_search_regex(r'data-prm-title="([^"]+)"', webpage, 'title', default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
**self._search_json_ld(webpage, media_id, default={}),
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('image', {url_or_none}),
'timestamp': ('uploadDate', {parse_iso8601(delimiter=' ')}),
'duration': ('duration', {int_or_none}),
'tags': ('tags', ..., 'name', {str}),
}),
}

42
yt_dlp/extractor/kika.py
View File

@ -1,3 +1,5 @@
import itertools
from .common import InfoExtractor
from ..utils import (
determine_ext,
@ -124,3 +126,43 @@ class KikaIE(InfoExtractor):
'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
}),
}
class KikaPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kika\.de/[\w-]+/(?P<id>[a-z-]+\d+)'
_TESTS = [{
'url': 'https://www.kika.de/logo/logo-die-welt-und-ich-562',
'info_dict': {
'id': 'logo-die-welt-und-ich-562',
'title': 'logo!',
'description': 'md5:7b9d7f65561b82fa512f2cfb553c397d',
},
'playlist_count': 100,
}]
def _entries(self, playlist_url, playlist_id):
for page in itertools.count(1):
data = self._download_json(playlist_url, playlist_id, note=f'Downloading page {page}')
for item in traverse_obj(data, ('content', lambda _, v: url_or_none(v['api']['url']))):
yield self.url_result(
item['api']['url'], ie=KikaIE,
**traverse_obj(item, {
'id': ('id', {str}),
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': ('date', {parse_iso8601}),
}))
playlist_url = traverse_obj(data, ('links', 'next', {url_or_none}))
if not playlist_url:
break
def _real_extract(self, url):
playlist_id = self._match_id(url)
brand_data = self._download_json(
f'https://www.kika.de/_next-api/proxy/v1/brands/{playlist_id}', playlist_id)
return self.playlist_result(
self._entries(brand_data['videoSubchannel']['videosPageUrl'], playlist_id),
playlist_id, title=brand_data.get('title'), description=brand_data.get('description'))

44
yt_dlp/extractor/lrt.py
View File

@ -2,8 +2,11 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
merge_dicts,
str_or_none,
traverse_obj,
unified_timestamp,
url_or_none,
urljoin,
)
@ -80,7 +83,7 @@ class LRTVODIE(LRTBaseIE):
}]
def _real_extract(self, url):
path, video_id = self._match_valid_url(url).groups()
path, video_id = self._match_valid_url(url).group('path', 'id')
webpage = self._download_webpage(url, video_id)
media_url = self._extract_js_var(webpage, 'main_url', path)
@ -106,3 +109,42 @@ class LRTVODIE(LRTBaseIE):
}
return merge_dicts(clean_info, jw_data, json_ld_data)
class LRTRadioIE(LRTBaseIE):
_VALID_URL = r'https?://(?:www\.)?lrt\.lt/radioteka/irasas/(?P<id>\d+)/(?P<path>[^?#/]+)'
_TESTS = [{
# m3u8 download
'url': 'https://www.lrt.lt/radioteka/irasas/2000359728/nemarios-eiles-apie-pragarus-ir-skaistyklas-su-aiste-kiltinaviciute',
'info_dict': {
'id': '2000359728',
'ext': 'm4a',
'title': 'Nemarios eilės: apie pragarus ir skaistyklas su Aiste Kiltinavičiūte',
'description': 'md5:5eee9a0e86a55bf547bd67596204625d',
'timestamp': 1726143120,
'upload_date': '20240912',
'tags': 'count:5',
'thumbnail': r're:https?://.+/.+\.jpe?g',
'categories': ['Daiktiniai įrodymai'],
},
}, {
'url': 'https://www.lrt.lt/radioteka/irasas/2000304654/vakaras-su-knyga-svetlana-aleksijevic-cernobylio-malda-v-dalis?season=%2Fmediateka%2Faudio%2Fvakaras-su-knyga%2F2023',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, path = self._match_valid_url(url).group('id', 'path')
media = self._download_json(
'https://www.lrt.lt/radioteka/api/media', video_id,
query={'url': f'/mediateka/irasas/{video_id}/{path}'})
return traverse_obj(media, {
'id': ('id', {int}, {str_or_none}),
'title': ('title', {str}),
'tags': ('tags', ..., 'name', {str}),
'categories': ('playlist_item', 'category', {str}, filter, all, filter),
'description': ('content', {clean_html}, {str}),
'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
'formats': ('playlist_item', 'file', {lambda x: self._extract_m3u8_formats(x, video_id)}),
})

73
yt_dlp/extractor/mixcloud.py
View File

@ -10,7 +10,9 @@ from ..utils import (
parse_iso8601,
strip_or_none,
try_get,
url_or_none,
)
from ..utils.traversal import traverse_obj
class MixcloudBaseIE(InfoExtractor):
@ -37,7 +39,7 @@ class MixcloudIE(MixcloudBaseIE):
'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach',
'uploader': 'dholbach',
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
@ -46,10 +48,11 @@ class MixcloudIE(MixcloudBaseIE):
'uploader_url': 'https://www.mixcloud.com/dholbach/',
'artist': 'Submorphics & Chino , Telekinesis, Porter Robinson, Enei, Breakage ft Jess Mills',
'duration': 3723,
'tags': [],
'tags': ['liquid drum and bass', 'drum and bass'],
'comment_count': int,
'repost_count': int,
'like_count': int,
'artists': list,
},
'params': {'skip_download': 'm3u8'},
}, {
@ -67,7 +70,7 @@ class MixcloudIE(MixcloudBaseIE):
'upload_date': '20150203',
'uploader_url': 'https://www.mixcloud.com/gillespeterson/',
'duration': 2992,
'tags': [],
'tags': ['jazz', 'soul', 'world music', 'funk'],
'comment_count': int,
'repost_count': int,
'like_count': int,
@ -149,8 +152,6 @@ class MixcloudIE(MixcloudBaseIE):
elif reason:
raise ExtractorError('Track is restricted', expected=True)
title = cloudcast['name']
stream_info = cloudcast['streamInfo']
formats = []
@ -182,47 +183,39 @@ class MixcloudIE(MixcloudBaseIE):
self.raise_login_required(metadata_available=True)
comments = []
for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []):
node = edge.get('node') or {}
for node in traverse_obj(cloudcast, ('comments', 'edges', ..., 'node', {dict})):
text = strip_or_none(node.get('comment'))
if not text:
continue
user = node.get('user') or {}
comments.append({
'author': user.get('displayName'),
'author_id': user.get('username'),
'text': text,
'timestamp': parse_iso8601(node.get('created')),
**traverse_obj(node, {
'author': ('user', 'displayName', {str}),
'author_id': ('user', 'username', {str}),
'timestamp': ('created', {parse_iso8601}),
}),
})
tags = []
for t in cloudcast.get('tags'):
tag = try_get(t, lambda x: x['tag']['name'], str)
if not tag:
tags.append(tag)
get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount']))
owner = cloudcast.get('owner') or {}
return {
'id': track_id,
'title': title,
'formats': formats,
'description': cloudcast.get('description'),
'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], str),
'uploader': owner.get('displayName'),
'timestamp': parse_iso8601(cloudcast.get('publishDate')),
'uploader_id': owner.get('username'),
'uploader_url': owner.get('url'),
'duration': int_or_none(cloudcast.get('audioLength')),
'view_count': int_or_none(cloudcast.get('plays')),
'like_count': get_count('favorites'),
'repost_count': get_count('reposts'),
'comment_count': get_count('comments'),
'comments': comments,
'tags': tags,
'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None,
**traverse_obj(cloudcast, {
'title': ('name', {str}),
'description': ('description', {str}),
'thumbnail': ('picture', 'url', {url_or_none}),
'timestamp': ('publishDate', {parse_iso8601}),
'duration': ('audioLength', {int_or_none}),
'uploader': ('owner', 'displayName', {str}),
'uploader_id': ('owner', 'username', {str}),
'uploader_url': ('owner', 'url', {url_or_none}),
'view_count': ('plays', {int_or_none}),
'like_count': ('favorites', 'totalCount', {int_or_none}),
'repost_count': ('reposts', 'totalCount', {int_or_none}),
'comment_count': ('comments', 'totalCount', {int_or_none}),
'tags': ('tags', ..., 'tag', 'name', {str}, filter, all, filter),
'artists': ('featuringArtistList', ..., {str}, filter, all, filter),
}),
}
@ -295,7 +288,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'url': 'http://www.mixcloud.com/dholbach/',
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
'title': 'dholbach (uploads)',
'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
},
'playlist_mincount': 36,
@ -303,7 +296,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'url': 'http://www.mixcloud.com/dholbach/uploads/',
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
'title': 'dholbach (uploads)',
'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
},
'playlist_mincount': 36,
@ -311,7 +304,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'url': 'http://www.mixcloud.com/dholbach/favorites/',
'info_dict': {
'id': 'dholbach_favorites',
'title': 'Daniel Holbach (favorites)',
'title': 'dholbach (favorites)',
'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
},
# 'params': {
@ -337,7 +330,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'title': 'First Ear (stream)',
'description': 'we maraud for ears',
},
'playlist_mincount': 269,
'playlist_mincount': 267,
}]
_TITLE_KEY = 'displayName'
@ -361,7 +354,7 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
'id': 'maxvibes_jazzcat-on-ness-radio',
'title': 'Ness Radio sessions',
},
'playlist_mincount': 59,
'playlist_mincount': 58,
}]
_TITLE_KEY = 'name'
_DESCRIPTION_KEY = 'description'

8
yt_dlp/extractor/niconico.py
View File

@ -27,6 +27,7 @@ from ..utils import (
traverse_obj,
try_get,
unescapeHTML,
unified_timestamp,
update_url_query,
url_basename,
url_or_none,
@ -985,6 +986,7 @@ class NiconicoLiveIE(InfoExtractor):
'quality': 'abr',
'protocol': 'hls+fmp4',
'latency': latency,
'accessRightMethod': 'single_cookie',
'chasePlay': False,
},
'room': {
@ -1005,6 +1007,7 @@ class NiconicoLiveIE(InfoExtractor):
if data.get('type') == 'stream':
m3u8_url = data['data']['uri']
qualities = data['data']['availableQualities']
cookies = data['data']['cookies']
break
elif data.get('type') == 'disconnect':
self.write_debug(recv)
@ -1043,6 +1046,11 @@ class NiconicoLiveIE(InfoExtractor):
**res,
})
for cookie in cookies:
self._set_cookie(
cookie['domain'], cookie['name'], cookie['value'],
expire_time=unified_timestamp(cookie['expires']), path=cookie['path'], secure=cookie['secure'])
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
for fmt, q in zip(formats, reversed(qualities[1:])):
fmt.update({

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}),
}),
}

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 = {

149
yt_dlp/extractor/yandexvideo.py
View File

@ -2,15 +2,17 @@ import itertools
from .common import InfoExtractor
from ..utils import (
bug_reports_message,
determine_ext,
extract_attributes,
int_or_none,
lowercase_escape,
parse_qs,
traverse_obj,
qualities,
try_get,
update_url_query,
url_or_none,
)
from ..utils.traversal import traverse_obj
class YandexVideoIE(InfoExtractor):
@ -186,7 +188,22 @@ class YandexVideoPreviewIE(InfoExtractor):
return self.url_result(data_json['video']['url'])
class ZenYandexIE(InfoExtractor):
class ZenYandexBaseIE(InfoExtractor):
def _fetch_ssr_data(self, url, video_id):
webpage = self._download_webpage(url, video_id)
redirect = self._search_json(
r'(?:var|let|const)\s+it\s*=', webpage, 'redirect', video_id, default={}).get('retpath')
if redirect:
video_id = self._match_id(redirect)
webpage = self._download_webpage(redirect, video_id, note='Redirecting')
return video_id, self._search_json(
r'(?:var|let|const)\s+_params\s*=\s*\(', webpage, 'metadata', video_id,
contains_pattern=r'{["\']ssrData.+}')['ssrData']
class ZenYandexIE(ZenYandexBaseIE):
IE_NAME = 'dzen.ru'
IE_DESC = 'Дзен (dzen) formerly Яндекс.Дзен (Yandex Zen)'
_VALID_URL = r'https?://(zen\.yandex|dzen)\.ru(?:/video)?/(media|watch)/(?:(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-)?(?P<id>[a-z0-9-]+)'
_TESTS = [{
'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
@ -216,6 +233,7 @@ class ZenYandexIE(InfoExtractor):
'timestamp': 1573465585,
},
'params': {'skip_download': 'm3u8'},
'skip': 'The page does not exist',
}, {
'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3',
'info_dict': {
@ -227,6 +245,9 @@ class ZenYandexIE(InfoExtractor):
'uploader': 'TechInsider',
'timestamp': 1611378221,
'upload_date': '20210123',
'view_count': int,
'duration': 243,
'tags': ['опыт', 'эксперимент', 'огонь'],
},
'params': {'skip_download': 'm3u8'},
}, {
@ -240,6 +261,9 @@ class ZenYandexIE(InfoExtractor):
'uploader': 'TechInsider',
'upload_date': '20210123',
'timestamp': 1611378221,
'view_count': int,
'duration': 243,
'tags': ['опыт', 'эксперимент', 'огонь'],
},
'params': {'skip_download': 'm3u8'},
}, {
@ -252,44 +276,56 @@ class ZenYandexIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
redirect = self._search_json(r'var it\s*=', webpage, 'redirect', id, default={}).get('retpath')
if redirect:
video_id = self._match_id(redirect)
webpage = self._download_webpage(redirect, video_id, note='Redirecting')
data_json = self._search_json(
r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state')
uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
webpage, 'uploader', default='<a>')
uploader_name = extract_attributes(uploader).get('aria-label')
item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str}))
video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {}
video_id, ssr_data = self._fetch_ssr_data(url, video_id)
video_data = ssr_data['videoMetaResponse']
formats, subtitles = [], {}
for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})):
quality = qualities(('4', '0', '1', '2', '3', '5', '6', '7'))
# Deduplicate stream URLs. The "dzen_dash" query parameter is present in some URLs but can be omitted
stream_urls = set(traverse_obj(video_data, (
'video', ('id', ('streams', ...), ('mp4Streams', ..., 'url'), ('oneVideoStreams', ..., 'url')),
{url_or_none}, {update_url_query(query={'dzen_dash': []})})))
for s_url in stream_urls:
ext = determine_ext(s_url)
if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')
elif ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4')
content_type = traverse_obj(parse_qs(s_url), ('ct', 0))
if ext == 'mpd' or content_type == '6':
fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash', fatal=False)
elif ext == 'm3u8' or content_type == '8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
elif content_type == '0':
format_type = traverse_obj(parse_qs(s_url), ('type', 0))
formats.append({
'url': s_url,
'format_id': format_type,
'ext': 'mp4',
'quality': quality(format_type),
})
continue
else:
self.report_warning(f'Unsupported stream URL: {s_url}{bug_reports_message()}')
continue
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'title': video_json.get('title') or self._og_search_title(webpage),
'formats': formats,
'subtitles': subtitles,
'duration': int_or_none(video_json.get('duration')),
'view_count': int_or_none(video_json.get('views')),
'timestamp': int_or_none(video_json.get('publicationDate')),
'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']),
'description': video_json.get('description') or self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']),
**traverse_obj(video_data, {
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('image', {url_or_none}),
'duration': ('video', 'duration', {int_or_none}),
'view_count': ('video', 'views', {int_or_none}),
'timestamp': ('publicationDate', {int_or_none}),
'tags': ('tags', ..., {str}),
'uploader': ('source', 'title', {str}),
}),
}
class ZenYandexChannelIE(InfoExtractor):
class ZenYandexChannelIE(ZenYandexBaseIE):
IE_NAME = 'dzen.ru:channel'
_VALID_URL = r'https?://(zen\.yandex|dzen)\.ru/(?!media|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
_TESTS = [{
'url': 'https://zen.yandex.ru/tok_media',
@ -323,8 +359,8 @@ class ZenYandexChannelIE(InfoExtractor):
'url': 'https://zen.yandex.ru/jony_me',
'info_dict': {
'id': 'jony_me',
'description': 'md5:ce0a5cad2752ab58701b5497835b2cc5',
'title': 'JONY ',
'description': 'md5:7c30d11dc005faba8826feae99da3113',
'title': 'JONY',
},
'playlist_count': 18,
}, {
@ -333,9 +369,8 @@ class ZenYandexChannelIE(InfoExtractor):
'url': 'https://zen.yandex.ru/tatyanareva',
'info_dict': {
'id': 'tatyanareva',
'description': 'md5:40a1e51f174369ec3ba9d657734ac31f',
'description': 'md5:92e56fa730a932ca2483ba5c2186ad96',
'title': 'Татьяна Рева',
'entries': 'maxcount:200',
},
'playlist_mincount': 46,
}, {
@ -348,43 +383,31 @@ class ZenYandexChannelIE(InfoExtractor):
'playlist_mincount': 657,
}]
def _entries(self, item_id, server_state_json, server_settings_json):
items = (traverse_obj(server_state_json, ('feed', 'items', ...))
or traverse_obj(server_settings_json, ('exportData', 'items', ...)))
more = (traverse_obj(server_state_json, ('links', 'more'))
or traverse_obj(server_settings_json, ('exportData', 'more', 'link')))
def _entries(self, feed_data, channel_id):
next_page_id = None
for page in itertools.count(1):
for item in items or []:
if item.get('type') != 'gif':
continue
video_id = traverse_obj(item, 'publication_id', 'publicationId') or ''
yield self.url_result(item['link'], ZenYandexIE, video_id.split(':')[-1])
for item in traverse_obj(feed_data, (
(None, ('items', lambda _, v: v['tab'] in ('shorts', 'longs'))),
'items', lambda _, v: url_or_none(v['link']),
)):
yield self.url_result(item['link'], ZenYandexIE, item.get('id'), title=item.get('title'))
more = traverse_obj(feed_data, ('more', 'link', {url_or_none}))
current_page_id = next_page_id
next_page_id = traverse_obj(parse_qs(more), ('next_page_id', -1))
if not all((more, items, next_page_id, next_page_id != current_page_id)):
if not all((more, next_page_id, next_page_id != current_page_id)):
break
data = self._download_json(more, item_id, note=f'Downloading Page {page}')
items, more = data.get('items'), traverse_obj(data, ('more', 'link'))
feed_data = self._download_json(more, channel_id, note=f'Downloading Page {page}')
def _real_extract(self, url):
item_id = self._match_id(url)
webpage = self._download_webpage(url, item_id)
redirect = self._search_json(
r'var it\s*=', webpage, 'redirect', item_id, default={}).get('retpath')
if redirect:
item_id = self._match_id(redirect)
webpage = self._download_webpage(redirect, item_id, note='Redirecting')
data = self._search_json(
r'("data"\s*:|data\s*=)', webpage, 'channel data', item_id, contains_pattern=r'{\"__serverState__.+}')
server_state_json = traverse_obj(data, lambda k, _: k.startswith('__serverState__'), get_all=False)
server_settings_json = traverse_obj(data, lambda k, _: k.startswith('__serverSettings__'), get_all=False)
channel_id = self._match_id(url)
channel_id, ssr_data = self._fetch_ssr_data(url, channel_id)
channel_data = ssr_data['exportResponse']
return self.playlist_result(
self._entries(item_id, server_state_json, server_settings_json),
item_id, traverse_obj(server_state_json, ('channel', 'source', 'title')),
traverse_obj(server_state_json, ('channel', 'source', 'description')))
self._entries(channel_data['feedData'], channel_id),
channel_id, **traverse_obj(channel_data, ('channel', 'source', {
'title': ('title', {str}),
'description': ('description', {str}),
})))

2
yt_dlp/utils/_utils.py
View File

@ -2044,7 +2044,7 @@ def url_or_none(url):
if not url or not isinstance(url, str):
return None
url = url.strip()
return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?|wss?):)?//', url) else None
def strftime_or_none(timestamp, date_format='%Y%m%d', default=None):