Merge branch 'yt-dlp:master' into streaks

pull/12679/head
bashonly 4 weeks ago
commit 8504c6907d
No known key found for this signature in database
GPG Key ID: 783F096F253D15B0

@ -638,6 +638,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'img_bipbop_adv_example_fmp4',
'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
[{
# 60kbps (bitrate not provided in m3u8); sorted as worst because it's grouped with lowest bitrate video track
'format_id': 'aud1-English',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a1/prog_index.m3u8',
'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
@ -645,22 +646,27 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'ext': 'mp4',
'protocol': 'm3u8_native',
'audio_ext': 'mp4',
'source_preference': 0,
}, {
'format_id': 'aud2-English',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a2/prog_index.m3u8',
# 192kbps (bitrate not provided in m3u8)
'format_id': 'aud3-English',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a3/prog_index.m3u8',
'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
'language': 'en',
'ext': 'mp4',
'protocol': 'm3u8_native',
'audio_ext': 'mp4',
'source_preference': 1,
}, {
'format_id': 'aud3-English',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a3/prog_index.m3u8',
# 384kbps (bitrate not provided in m3u8); sorted as best because it's grouped with the highest bitrate video track
'format_id': 'aud2-English',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a2/prog_index.m3u8',
'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
'language': 'en',
'ext': 'mp4',
'protocol': 'm3u8_native',
'audio_ext': 'mp4',
'source_preference': 2,
}, {
'format_id': '530',
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/v2/prog_index.m3u8',

@ -1260,6 +1260,7 @@ class TestUtil(unittest.TestCase):
def test_js_to_json_malformed(self):
self.assertEqual(js_to_json('42a1'), '42"a1"')
self.assertEqual(js_to_json('42a-1'), '42"a"-1')
self.assertEqual(js_to_json('{a: `${e("")}`}'), '{"a": "\\"e\\"(\\"\\")"}')
def test_js_to_json_template_literal(self):
self.assertEqual(js_to_json('`Hello ${name}`', {'name': '"world"'}), '"Hello world"')

@ -83,6 +83,11 @@ _SIG_TESTS = [
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
),
(
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
),
]
_NSIG_TESTS = [
@ -234,6 +239,10 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
),
(
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
),
]

@ -839,6 +839,7 @@ from .icareus import IcareusIE
from .ichinanalive import (
IchinanaLiveClipIE,
IchinanaLiveIE,
IchinanaLiveVODIE,
)
from .idolplus import IdolPlusIE
from .ign import (
@ -2393,6 +2394,12 @@ from .voxmedia import (
VoxMediaIE,
VoxMediaVolumeIE,
)
from .vrsquare import (
VrSquareChannelIE,
VrSquareIE,
VrSquareSearchIE,
VrSquareSectionIE,
)
from .vrt import (
VRTIE,
DagelijkseKostIE,

@ -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(

@ -16,6 +16,7 @@ from ..utils import (
MEDIA_EXTENSIONS,
ExtractorError,
UnsupportedError,
base_url,
determine_ext,
determine_protocol,
dict_get,
@ -2531,7 +2532,7 @@ 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)

@ -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}),
})

@ -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 「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))

@ -2176,10 +2176,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
"""Returns tuple of strings: variable assignment code, variable name, variable value code"""
return self._search_regex(
r'''(?x)
\'use\s+strict\';\s*
(?P<q1>["\'])use\s+strict(?P=q1);\s*
(?P<code>
var\s+(?P<name>[a-zA-Z0-9_$]+)\s*=\s*
(?P<value>"(?:[^"\\]|\\.)+"\.split\("[^"]+"\))
(?P<value>
(?P<q2>["\'])(?:(?!(?P=q2)).|\\.)+(?P=q2)
\.split\((?P<q3>["\'])(?:(?!(?P=q3)).)+(?P=q3)\)
)
)[;,]
''', jscode, 'global variable', group=('code', 'name', 'value'), default=(None, None, None))
@ -2187,7 +2190,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
global_var, varname, _ = self._extract_player_js_global_var(full_code)
if global_var:
self.write_debug(f'Prepending n function code with global array variable "{varname}"')
code = global_var + ', ' + code
code = global_var + '; ' + code
else:
self.write_debug('No global array variable found in player JS')
return argnames, re.sub(
@ -2196,7 +2199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
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='2025.03.21')
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2025.03.24')
jscode = func_code or self._load_player(video_id, player_url)
jsi = JSInterpreter(jscode)

@ -2767,7 +2767,8 @@ def js_to_json(code, vars={}, *, strict=False):
def template_substitute(match):
evaluated = js_to_json(match.group(1), vars, strict=strict)
if evaluated[0] == '"':
return json.loads(evaluated)
with contextlib.suppress(json.JSONDecodeError):
return json.loads(evaluated)
return evaluated
def fix_kv(m):

Loading…
Cancel
Save