Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-28 22:24:34 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Refactored ZenYandexIE to parse metadata from var _params

Browse source 
Refactored ZenYandexIE to parse metadata from `var _params`, updated MPD/M3U8 stream detection, 
and adjusted title/description/thumbnail extraction to use new SSR response fields.
This commit is contained in:
Semyon Saprykin 2024-12-26 01:56:08 +03:00 committed by GitHub
parent 3905f64920
commit 4c5482d570
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 21 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
yt_dlp/extractor/yandexvideo.py
View file

@ -258,34 +258,42 @@ class ZenYandexIE(InfoExtractor):
video_id = self._match_id(redirect) video_id = self._match_id(redirect)
webpage = self._download_webpage(redirect, video_id, note='Redirecting') webpage = self._download_webpage(redirect, video_id, note='Redirecting')
data_json = self._search_json( data_json = self._search_json(
r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}') r'var _params=\(', webpage, 'metadata', video_id, contains_pattern=r'{.+streamsResponse.+}')
serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state')
uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)', uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
webpage, 'uploader', default='<a>') webpage, 'uploader', default='<a>')
uploader_name = extract_attributes(uploader).get('aria-label') uploader_name = extract_attributes(uploader).get('aria-label')
item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str})) video_meta = traverse_obj(data_json, ('ssrData', 'videoMetaResponse', {dict}))
video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {} video_meta2 = traverse_obj(video_meta, ('video', {dict}))
m3u8_url = traverse_obj(video_meta2, ('id', {str}))
streams = traverse_obj(data_json, ('ssrData', 'streamsResponse', 'SingleStream', 0, {dict}))
formats, subtitles = [], {} formats, subtitles = [], {}
for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})): for s_url in traverse_obj(streams, ('StreamInfo', ..., "OutputStream", {url_or_none})):
ext = determine_ext(s_url) ext = determine_ext(s_url)
if ext == 'mpd': if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash') fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')
elif ext == 'm3u8': elif ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4') fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4')
else:
fmts = [{'url': s_url}]
subs = {}
formats.extend(fmts) formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs) subtitles = self._merge_subtitles(subtitles, subs)
return { return {
'id': video_id, 'id': video_id,
'title': video_json.get('title') or self._og_search_title(webpage), 'title': video_meta.get('title') or self._og_search_title(webpage),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'duration': int_or_none(video_json.get('duration')), 'duration': int_or_none(video_meta2.get('duration')),
'view_count': int_or_none(video_json.get('views')), 'view_count': int_or_none(video_meta2.get('views')),
'timestamp': int_or_none(video_json.get('publicationDate')), 'timestamp': int_or_none(video_meta.get('publicationDate')),
'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']), 'uploader': uploader_name or try_get(video_meta, lambda x: x['source']['title']),
'description': video_json.get('description') or self._og_search_description(webpage), 'description': video_meta.get('description') or self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']), 'thumbnail': self._og_search_thumbnail(webpage) or video_meta.get('image'),
} }