[yt-dlp.git] / yt_dlp / extractor / yandexvideo.py

import itertools
import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    extract_attributes,
    int_or_none,
    lowercase_escape,
    try_get,
    url_or_none,
)


class YandexVideoIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    https?://
                        (?:
                            yandex\.ru(?:/(?:portal/(?:video|efir)|efir))?/?\?.*?stream_id=|
                            frontend\.vh\.yandex\.ru/player/
                        )
                        (?P<id>(?:[\da-f]{32}|[\w-]{12}))
                    '''
    _TESTS = [{
        'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
        'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
        'info_dict': {
            'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
            'ext': 'mp4',
            'title': 'Русский Вудсток - главный рок-фест в истории СССР / вДудь',
            'description': 'md5:7d6b8d4bc4a3b9a56499916c1ea5b5fa',
            'thumbnail': r're:^https?://',
            'timestamp': 1549972939,
            'duration': 5575,
            'age_limit': 18,
            'upload_date': '20190212',
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
        },
    }, {
        'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
        'only_matching': True,
    }, {
        'url': 'https://yandex.ru/?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
        'only_matching': True,
    }, {
        'url': 'https://frontend.vh.yandex.ru/player/4dbb262b4fe5cf15a215de4f34eee34d?from=morda',
        'only_matching': True,
    }, {
        # vod-episode, series episode
        'url': 'https://yandex.ru/portal/video?stream_id=45b11db6e4b68797919c93751a938cee',
        'only_matching': True,
    }, {
        # episode, sports
        'url': 'https://yandex.ru/?stream_channel=1538487871&stream_id=4132a07f71fb0396be93d74b3477131d',
        'only_matching': True,
    }, {
        # DASH with DRM
        'url': 'https://yandex.ru/portal/video?from=morda&stream_id=485a92d94518d73a9d0ff778e13505f8',
        'only_matching': True,
    }, {
        'url': 'https://yandex.ru/efir?stream_active=watching&stream_id=v7a2dZ-v5mSI&from_block=efir_newtab',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        player = try_get((self._download_json(
            'https://frontend.vh.yandex.ru/graphql', video_id, data=('''{
  player(content_id: "%s") {
    computed_title
    content_url
    description
    dislikes
    duration
    likes
    program_title
    release_date
    release_date_ut
    release_year
    restriction_age
    season
    start_time
    streams
    thumbnail
    title
    views_count
  }
}''' % video_id).encode(), fatal=False)), lambda x: x['player']['content'])
        if not player or player.get('error'):
            player = self._download_json(
                'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
                video_id, query={
                    'stream_options': 'hires',
                    'disable_trackings': 1,
                })
        content = player['content']

        title = content.get('title') or content['computed_title']

        formats = []
        streams = content.get('streams') or []
        streams.append({'url': content.get('content_url')})
        for stream in streams:
            content_url = url_or_none(stream.get('url'))
            if not content_url:
                continue
            ext = determine_ext(content_url)
            if ext == 'ismc':
                continue
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    content_url, video_id, 'mp4',
                    'm3u8_native', m3u8_id='hls', fatal=False))
            elif ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    content_url, video_id, mpd_id='dash', fatal=False))
            else:
                formats.append({'url': content_url})

        self._sort_formats(formats)

        timestamp = (int_or_none(content.get('release_date'))
                     or int_or_none(content.get('release_date_ut'))
                     or int_or_none(content.get('start_time')))
        season = content.get('season') or {}

        return {
            'id': video_id,
            'title': title,
            'description': content.get('description'),
            'thumbnail': content.get('thumbnail'),
            'timestamp': timestamp,
            'duration': int_or_none(content.get('duration')),
            'series': content.get('program_title'),
            'age_limit': int_or_none(content.get('restriction_age')),
            'view_count': int_or_none(content.get('views_count')),
            'like_count': int_or_none(content.get('likes')),
            'dislike_count': int_or_none(content.get('dislikes')),
            'season_number': int_or_none(season.get('season_number')),
            'season_id': season.get('id'),
            'release_year': int_or_none(content.get('release_year')),
            'formats': formats,
        }


class YandexVideoPreviewIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?yandex\.\w{2,3}(?:\.(?:am|ge|il|tr))?/video/preview(?:/?\?.*?filmId=|/)(?P<id>\d+)'
    _TESTS = [{  # Odnoklassniki
        'url': 'https://yandex.ru/video/preview/?filmId=10682852472978372885&text=summer',
        'info_dict': {
            'id': '1352565459459',
            'ext': 'mp4',
            'like_count': int,
            'upload_date': '20191202',
            'age_limit': 0,
            'duration': 196,
            'thumbnail': 'https://i.mycdn.me/videoPreview?id=544866765315&type=37&idx=13&tkn=TY5qjLYZHxpmcnK8U2LgzYkgmaU&fn=external_8',
            'uploader_id': '481054701571',
            'title': 'LOFT - summer, summer, summer HD',
            'uploader': 'АРТЁМ КУДРОВ',
        },
    }, {  # youtube
        'url': 'https://yandex.ru/video/preview/?filmId=4479424425337895262&source=main_redirect&text=видео&utm_source=main_stripe_big',
        'only_matching': True,
    }, {  # YandexVideo
        'url': 'https://yandex.ru/video/preview/5275069442094787341',
        'only_matching': True,
    }, {  # youtube
        'url': 'https://yandex.ru/video/preview/?filmId=16658118429797832897&from=tabbar&p=1&text=%D0%BF%D1%80%D0%BE%D1%81%D0%BC%D0%BE%D1%82%D1%80+%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82%D0%B0+%D0%BC%D0%B0%D0%BB%D0%B5%D0%BD%D1%8C%D0%BA%D0%B8%D0%B9+%D0%BF%D1%80%D0%B8%D0%BD%D1%86+%D0%BC%D1%8B+%D0%B2+%D0%BE%D1%82%D0%B2%D0%B5%D1%82%D0%B5+%D0%B7%D0%B0+%D1%82%D0%B5%D1%85+%D0%BA%D0%BE%D0%B3%D0%BE+%D0%BF%D1%80%D0%B8%D1%80%D1%83%D1%87%D0%B8%D0%BB%D0%B8',
        'only_matching': True,
    }, {  # Odnoklassniki
        'url': 'https://yandex.ru/video/preview/?text=Francis%20Lai%20-%20Le%20Bon%20Et%20Les%20MC)chants&path=wizard&parent-reqid=1643208087979310-1481782809207673478-sas3-0931-2f9-sas-l7-balancer-8080-BAL-9380&wiz_type=vital&filmId=12508152936505397283',
        'only_matching': True,
    }, {  # Odnoklassniki
        'url': 'https://yandex.com/video/preview/?text=dossier%2051%20film%201978&path=yandex_search&parent-reqid=1664361087754492-8727541069609384458-sas2-0340-sas-l7-balancer-8080-BAL-8045&noreask=1&from_type=vast&filmId=5794987234584444632',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        id = self._match_id(url)
        webpage = self._download_webpage(url, id)
        data_raw = self._search_regex(r'window.Ya.__inline_params__\s*=\s*JSON.parse\(\'([^"]+?\\u0022video\\u0022:[^"]+?})\'\);', webpage, 'data_raw')
        data_json = self._parse_json(data_raw, id, transform_source=lowercase_escape)
        return self.url_result(data_json['video']['url'])


class ZenYandexIE(InfoExtractor):
    _VALID_URL = r'https?://zen\.yandex\.ru(?:/video)?/(media|watch)/(?:(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-)?(?P<id>[a-z0-9-]+)'
    _TESTS = [{
        'url': 'https://zen.yandex.ru/media/popmech/izverjenie-vulkana-iz-spichek-zreliscnyi-opyt-6002240ff8b1af50bb2da5e3',
        'info_dict': {
            'id': '6002240ff8b1af50bb2da5e3',
            'ext': 'mp4',
            'title': 'Извержение вулкана из спичек: зрелищный опыт',
            'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
            'thumbnail': 're:^https://avatars.mds.yandex.net/',
            'uploader': 'Популярная механика',
        },
        'params': {
            'skip_download': 'm3u8',
        },
    }, {
        'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
        'info_dict': {
            'id': '60c7c443da18892ebfe85ed7',
            'ext': 'mp4',
            'title': 'ВОТ ЭТО Focus. Деды Морозы на гидроциклах',
            'description': 'md5:f3db3d995763b9bbb7b56d4ccdedea89',
            'thumbnail': 're:^https://avatars.mds.yandex.net/',
            'uploader': 'AcademeG DailyStream'
        },
        'params': {
            'skip_download': 'm3u8',
            'format': 'bestvideo',
        },
    }, {
        'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3',
        'info_dict': {
            'id': '6002240ff8b1af50bb2da5e3',
            'ext': 'mp4',
            'title': 'Извержение вулкана из спичек: зрелищный опыт',
            'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
            'uploader': 'Популярная механика',
        },
        'params': {
            'skip_download': 'm3u8',
        },
    }, {
        'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/novyi-samsung-fold-3-moskvich-barahlit-612f93b7f8d48e7e945792a2?from=channel&rid=2286618386.482.1630817595976.42360',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        id = self._match_id(url)
        webpage = self._download_webpage(url, id)
        data_json = self._parse_json(
            self._search_regex(r'data\s*=\s*({["\']_*serverState_*video.+?});', webpage, 'metadata'), id)
        serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)',
                                         webpage, 'server state').replace('State', 'Settings')
        uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
                                      webpage, 'uploader', default='<a>')
        uploader_name = extract_attributes(uploader).get('aria-label')
        video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict)
        stream_urls = try_get(video_json, lambda x: x['video']['streams'])
        formats = []
        for s_url in stream_urls:
            ext = determine_ext(s_url)
            if ext == 'mpd':
                formats.extend(self._extract_mpd_formats(s_url, id, mpd_id='dash'))
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4'))
        self._sort_formats(formats)
        return {
            'id': id,
            'title': video_json.get('title') or self._og_search_title(webpage),
            'formats': formats,
            'duration': int_or_none(video_json.get('duration')),
            'view_count': int_or_none(video_json.get('views')),
            'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']),
            'description': self._og_search_description(webpage) or try_get(data_json, lambda x: x['og']['description']),
            'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']),
        }


class ZenYandexChannelIE(InfoExtractor):
    _VALID_URL = r'https?://zen\.yandex\.ru/(?!media|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
    _TESTS = [{
        'url': 'https://zen.yandex.ru/tok_media',
        'info_dict': {
            'id': 'tok_media',
        },
        'playlist_mincount': 169,
    }, {
        'url': 'https://zen.yandex.ru/id/606fd806cc13cb3c58c05cf5',
        'info_dict': {
            'id': '606fd806cc13cb3c58c05cf5',
        },
        'playlist_mincount': 657,
    }]

    def _entries(self, id, url):
        webpage = self._download_webpage(url, id)
        data_json = self._parse_json(re.findall(r'var\s?data\s?=\s?({.+?})\s?;', webpage)[-1], id)
        for key in data_json.keys():
            if key.startswith('__serverState__'):
                data_json = data_json[key]
        items = list(try_get(data_json, lambda x: x['feed']['items'], dict).values())
        more = try_get(data_json, lambda x: x['links']['more']) or None
        for page in itertools.count(1):
            for item in items:
                video_id = item.get('publication_id') or item.get('publicationId')
                video_url = item.get('link')
                yield self.url_result(video_url, ie=ZenYandexIE.ie_key(), video_id=video_id.split(':')[-1])
            if not more:
                break
            data_json = self._download_json(more, id, note='Downloading Page %d' % page)
            items = data_json.get('items', [])
            more = try_get(data_json, lambda x: x['more']['link']) or None

    def _real_extract(self, url):
        id = self._match_id(url)
        return self.playlist_result(self._entries(id, url), playlist_id=id)
Commit	Line	Data
dc9de9cb A	1	import itertools
	2	import re
	3
8428fdcc S	4	from .common import InfoExtractor
8428fdcc S	5	from ..utils import (
33b529fa	6	determine_ext,
a109acbf	7	extract_attributes,
8428fdcc	8	int_or_none,
304ad45a	9	lowercase_escape,
29f7c58a	10	try_get,
8428fdcc S	11	url_or_none,
	12	)
	13
	14
	15	class YandexVideoIE(InfoExtractor):
	16	_VALID_URL = r'''(?x)
	17	https?://
	18	(?:
29f7c58a	19	yandex\.ru(?:/(?:portal/(?:video\|efir)\|efir))?/?\?.*?stream_id=\|
8428fdcc S	20	frontend\.vh\.yandex\.ru/player/
8428fdcc S	21	)
29f7c58a	22	(?P<id>(?:[\da-f]{32}\|[\w-]{12}))
8428fdcc S	23	'''
8428fdcc S	24	_TESTS = [{
29f7c58a	25	'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
29f7c58a	26	'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
8428fdcc	27	'info_dict': {
29f7c58a	28	'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
8428fdcc	29	'ext': 'mp4',
29f7c58a	30	'title': 'Русский Вудсток - главный рок-фест в истории СССР / вДудь',
	31	'description': 'md5:7d6b8d4bc4a3b9a56499916c1ea5b5fa',
	32	'thumbnail': r're:^https?://',
	33	'timestamp': 1549972939,
	34	'duration': 5575,
8428fdcc	35	'age_limit': 18,
29f7c58a	36	'upload_date': '20190212',
	37	'view_count': int,
	38	'like_count': int,
	39	'dislike_count': int,
8428fdcc S	40	},
8428fdcc S	41	}, {
29f7c58a	42	'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
8428fdcc S	43	'only_matching': True,
	44	}, {
	45	'url': 'https://yandex.ru/?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
	46	'only_matching': True,
	47	}, {
	48	'url': 'https://frontend.vh.yandex.ru/player/4dbb262b4fe5cf15a215de4f34eee34d?from=morda',
	49	'only_matching': True,
	50	}, {
	51	# vod-episode, series episode
	52	'url': 'https://yandex.ru/portal/video?stream_id=45b11db6e4b68797919c93751a938cee',
	53	'only_matching': True,
	54	}, {
	55	# episode, sports
	56	'url': 'https://yandex.ru/?stream_channel=1538487871&stream_id=4132a07f71fb0396be93d74b3477131d',
	57	'only_matching': True,
33b529fa S	58	}, {
	59	# DASH with DRM
	60	'url': 'https://yandex.ru/portal/video?from=morda&stream_id=485a92d94518d73a9d0ff778e13505f8',
	61	'only_matching': True,
29f7c58a	62	}, {
	63	'url': 'https://yandex.ru/efir?stream_active=watching&stream_id=v7a2dZ-v5mSI&from_block=efir_newtab',
	64	'only_matching': True,
8428fdcc S	65	}]
	66
	67	def _real_extract(self, url):
	68	video_id = self._match_id(url)
	69
29f7c58a	70	player = try_get((self._download_json(
	71	'https://frontend.vh.yandex.ru/graphql', video_id, data=('''{
	72	player(content_id: "%s") {
	73	computed_title
	74	content_url
	75	description
	76	dislikes
	77	duration
	78	likes
	79	program_title
	80	release_date
	81	release_date_ut
	82	release_year
	83	restriction_age
	84	season
	85	start_time
	86	streams
	87	thumbnail
	88	title
	89	views_count
	90	}
	91	}''' % video_id).encode(), fatal=False)), lambda x: x['player']['content'])
	92	if not player or player.get('error'):
	93	player = self._download_json(
	94	'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
	95	video_id, query={
	96	'stream_options': 'hires',
	97	'disable_trackings': 1,
	98	})
	99	content = player['content']
8428fdcc	100
29f7c58a	101	title = content.get('title') or content['computed_title']
33b529fa	102
29f7c58a	103	formats = []
	104	streams = content.get('streams') or []
	105	streams.append({'url': content.get('content_url')})
	106	for stream in streams:
	107	content_url = url_or_none(stream.get('url'))
	108	if not content_url:
	109	continue
	110	ext = determine_ext(content_url)
	111	if ext == 'ismc':
	112	continue
	113	elif ext == 'm3u8':
	114	formats.extend(self._extract_m3u8_formats(
	115	content_url, video_id, 'mp4',
	116	'm3u8_native', m3u8_id='hls', fatal=False))
	117	elif ext == 'mpd':
	118	formats.extend(self._extract_mpd_formats(
	119	content_url, video_id, mpd_id='dash', fatal=False))
	120	else:
	121	formats.append({'url': content_url})
33b529fa	122
8428fdcc S	123	self._sort_formats(formats)
8428fdcc S	124
3089bc74 S	125	timestamp = (int_or_none(content.get('release_date'))
	126	or int_or_none(content.get('release_date_ut'))
	127	or int_or_none(content.get('start_time')))
29f7c58a	128	season = content.get('season') or {}
8428fdcc S	129
	130	return {
	131	'id': video_id,
	132	'title': title,
29f7c58a	133	'description': content.get('description'),
29f7c58a	134	'thumbnail': content.get('thumbnail'),
8428fdcc	135	'timestamp': timestamp,
29f7c58a	136	'duration': int_or_none(content.get('duration')),
	137	'series': content.get('program_title'),
	138	'age_limit': int_or_none(content.get('restriction_age')),
	139	'view_count': int_or_none(content.get('views_count')),
	140	'like_count': int_or_none(content.get('likes')),
	141	'dislike_count': int_or_none(content.get('dislikes')),
	142	'season_number': int_or_none(season.get('season_number')),
	143	'season_id': season.get('id'),
	144	'release_year': int_or_none(content.get('release_year')),
8428fdcc S	145	'formats': formats,
8428fdcc S	146	}
dc9de9cb A	147
dc9de9cb A	148
e26f9cc1	149	class YandexVideoPreviewIE(InfoExtractor):
2e0f8d4f	150	_VALID_URL = r'https?://(?:www\.)?yandex\.\w{2,3}(?:\.(?:am\|ge\|il\|tr))?/video/preview(?:/?\?.*?filmId=\|/)(?P<id>\d+)'
e26f9cc1 K	151	_TESTS = [{ # Odnoklassniki
	152	'url': 'https://yandex.ru/video/preview/?filmId=10682852472978372885&text=summer',
	153	'info_dict': {
	154	'id': '1352565459459',
	155	'ext': 'mp4',
	156	'like_count': int,
	157	'upload_date': '20191202',
	158	'age_limit': 0,
	159	'duration': 196,
	160	'thumbnail': 'https://i.mycdn.me/videoPreview?id=544866765315&type=37&idx=13&tkn=TY5qjLYZHxpmcnK8U2LgzYkgmaU&fn=external_8',
	161	'uploader_id': '481054701571',
	162	'title': 'LOFT - summer, summer, summer HD',
e26f9cc1 K	163	'uploader': 'АРТЁМ КУДРОВ',
	164	},
	165	}, { # youtube
	166	'url': 'https://yandex.ru/video/preview/?filmId=4479424425337895262&source=main_redirect&text=видео&utm_source=main_stripe_big',
	167	'only_matching': True,
	168	}, { # YandexVideo
	169	'url': 'https://yandex.ru/video/preview/5275069442094787341',
	170	'only_matching': True,
	171	}, { # youtube
	172	'url': 'https://yandex.ru/video/preview/?filmId=16658118429797832897&from=tabbar&p=1&text=%D0%BF%D1%80%D0%BE%D1%81%D0%BC%D0%BE%D1%82%D1%80+%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82%D0%B0+%D0%BC%D0%B0%D0%BB%D0%B5%D0%BD%D1%8C%D0%BA%D0%B8%D0%B9+%D0%BF%D1%80%D0%B8%D0%BD%D1%86+%D0%BC%D1%8B+%D0%B2+%D0%BE%D1%82%D0%B2%D0%B5%D1%82%D0%B5+%D0%B7%D0%B0+%D1%82%D0%B5%D1%85+%D0%BA%D0%BE%D0%B3%D0%BE+%D0%BF%D1%80%D0%B8%D1%80%D1%83%D1%87%D0%B8%D0%BB%D0%B8',
	173	'only_matching': True,
	174	}, { # Odnoklassniki
	175	'url': 'https://yandex.ru/video/preview/?text=Francis%20Lai%20-%20Le%20Bon%20Et%20Les%20MC)chants&path=wizard&parent-reqid=1643208087979310-1481782809207673478-sas3-0931-2f9-sas-l7-balancer-8080-BAL-9380&wiz_type=vital&filmId=12508152936505397283',
	176	'only_matching': True,
2e0f8d4f SS	177	}, { # Odnoklassniki
	178	'url': 'https://yandex.com/video/preview/?text=dossier%2051%20film%201978&path=yandex_search&parent-reqid=1664361087754492-8727541069609384458-sas2-0340-sas-l7-balancer-8080-BAL-8045&noreask=1&from_type=vast&filmId=5794987234584444632',
	179	'only_matching': True,
e26f9cc1 K	180	}]
	181
	182	def _real_extract(self, url):
	183	id = self._match_id(url)
	184	webpage = self._download_webpage(url, id)
	185	data_raw = self._search_regex(r'window.Ya.__inline_params__\s=\sJSON.parse\(\'([^"]+?\\u0022video\\u0022:[^"]+?})\'\);', webpage, 'data_raw')
	186	data_json = self._parse_json(data_raw, id, transform_source=lowercase_escape)
	187	return self.url_result(data_json['video']['url'])
	188
	189
dc9de9cb	190	class ZenYandexIE(InfoExtractor):
a109acbf	191	_VALID_URL = r'https?://zen\.yandex\.ru(?:/video)?/(media\|watch)/(?:(?:id/[^/]+/\|[^/]+/)(?:[a-z0-9-]+)-)?(?P<id>[a-z0-9-]+)'
dc9de9cb A	192	_TESTS = [{
	193	'url': 'https://zen.yandex.ru/media/popmech/izverjenie-vulkana-iz-spichek-zreliscnyi-opyt-6002240ff8b1af50bb2da5e3',
	194	'info_dict': {
	195	'id': '6002240ff8b1af50bb2da5e3',
	196	'ext': 'mp4',
	197	'title': 'Извержение вулкана из спичек: зрелищный опыт',
	198	'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
a109acbf	199	'thumbnail': 're:^https://avatars.mds.yandex.net/',
dc9de9cb A	200	'uploader': 'Популярная механика',
dc9de9cb A	201	},
a109acbf	202	'params': {
	203	'skip_download': 'm3u8',
	204	},
dc9de9cb A	205	}, {
	206	'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
	207	'info_dict': {
	208	'id': '60c7c443da18892ebfe85ed7',
	209	'ext': 'mp4',
	210	'title': 'ВОТ ЭТО Focus. Деды Морозы на гидроциклах',
a109acbf	211	'description': 'md5:f3db3d995763b9bbb7b56d4ccdedea89',
a109acbf	212	'thumbnail': 're:^https://avatars.mds.yandex.net/',
dc9de9cb A	213	'uploader': 'AcademeG DailyStream'
dc9de9cb A	214	},
a109acbf	215	'params': {
	216	'skip_download': 'm3u8',
	217	'format': 'bestvideo',
	218	},
	219	}, {
	220	'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3',
	221	'info_dict': {
	222	'id': '6002240ff8b1af50bb2da5e3',
	223	'ext': 'mp4',
	224	'title': 'Извержение вулкана из спичек: зрелищный опыт',
	225	'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
	226	'uploader': 'Популярная механика',
	227	},
	228	'params': {
	229	'skip_download': 'm3u8',
	230	},
dc9de9cb A	231	}, {
	232	'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/novyi-samsung-fold-3-moskvich-barahlit-612f93b7f8d48e7e945792a2?from=channel&rid=2286618386.482.1630817595976.42360',
	233	'only_matching': True,
	234	}]
	235
	236	def _real_extract(self, url):
	237	id = self._match_id(url)
	238	webpage = self._download_webpage(url, id)
a109acbf	239	data_json = self._parse_json(
	240	self._search_regex(r'data\s=\s({["\']_serverState_video.+?});', webpage, 'metadata'), id)
	241	serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)',
	242	webpage, 'server state').replace('State', 'Settings')
	243	uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
	244	webpage, 'uploader', default='<a>')
	245	uploader_name = extract_attributes(uploader).get('aria-label')
	246	video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict)
	247	stream_urls = try_get(video_json, lambda x: x['video']['streams'])
	248	formats = []
	249	for s_url in stream_urls:
	250	ext = determine_ext(s_url)
	251	if ext == 'mpd':
	252	formats.extend(self._extract_mpd_formats(s_url, id, mpd_id='dash'))
	253	elif ext == 'm3u8':
	254	formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4'))
dc9de9cb A	255	self._sort_formats(formats)
	256	return {
	257	'id': id,
a109acbf	258	'title': video_json.get('title') or self._og_search_title(webpage),
dc9de9cb	259	'formats': formats,
a109acbf	260	'duration': int_or_none(video_json.get('duration')),
	261	'view_count': int_or_none(video_json.get('views')),
	262	'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']),
	263	'description': self._og_search_description(webpage) or try_get(data_json, lambda x: x['og']['description']),
	264	'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']),
dc9de9cb A	265	}
	266
	267
	268	class ZenYandexChannelIE(InfoExtractor):
a109acbf	269	_VALID_URL = r'https?://zen\.yandex\.ru/(?!media\|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
dc9de9cb A	270	_TESTS = [{
	271	'url': 'https://zen.yandex.ru/tok_media',
	272	'info_dict': {
	273	'id': 'tok_media',
	274	},
	275	'playlist_mincount': 169,
	276	}, {
	277	'url': 'https://zen.yandex.ru/id/606fd806cc13cb3c58c05cf5',
	278	'info_dict': {
	279	'id': '606fd806cc13cb3c58c05cf5',
	280	},
	281	'playlist_mincount': 657,
	282	}]
	283
	284	def _entries(self, id, url):
	285	webpage = self._download_webpage(url, id)
	286	data_json = self._parse_json(re.findall(r'var\s?data\s?=\s?({.+?})\s?;', webpage)[-1], id)
	287	for key in data_json.keys():
	288	if key.startswith('__serverState__'):
	289	data_json = data_json[key]
	290	items = list(try_get(data_json, lambda x: x['feed']['items'], dict).values())
	291	more = try_get(data_json, lambda x: x['links']['more']) or None
	292	for page in itertools.count(1):
	293	for item in items:
	294	video_id = item.get('publication_id') or item.get('publicationId')
	295	video_url = item.get('link')
	296	yield self.url_result(video_url, ie=ZenYandexIE.ie_key(), video_id=video_id.split(':')[-1])
	297	if not more:
	298	break
	299	data_json = self._download_json(more, id, note='Downloading Page %d' % page)
	300	items = data_json.get('items', [])
	301	more = try_get(data_json, lambda x: x['more']['link']) or None
	302
	303	def _real_extract(self, url):
	304	id = self._match_id(url)
	305	return self.playlist_result(self._entries(id, url), playlist_id=id)