import itertools
-import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
extract_attributes,
int_or_none,
+ lowercase_escape,
+ parse_qs,
+ traverse_obj,
try_get,
url_or_none,
- lowercase_escape,
)
'''
_TESTS = [{
'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
- 'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
'info_dict': {
'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
'ext': 'mp4',
'like_count': int,
'dislike_count': int,
},
+ 'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
'only_matching': True,
title
views_count
}
-}''' % video_id).encode(), fatal=False)), lambda x: x['player']['content'])
+}''' % video_id).encode(), fatal=False)), lambda x: x['player']['content']) # noqa: UP031
if not player or player.get('error'):
player = self._download_json(
- 'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
+ f'https://frontend.vh.yandex.ru/v23/player/{video_id}.json',
video_id, query={
'stream_options': 'hires',
'disable_trackings': 1,
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')))
class YandexVideoPreviewIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?yandex\.ru/video/preview(?:/?\?.*?filmId=|/)(?P<id>\d+)'
+ _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': {
}, { # 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)
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_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)
+ data_json = self._parse_json(data_raw, video_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-]+)'
+ _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/popmech/izverjenie-vulkana-iz-spichek-zreliscnyi-opyt-6002240ff8b1af50bb2da5e3',
+ 'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
'info_dict': {
- 'id': '6002240ff8b1af50bb2da5e3',
+ 'id': '60c7c443da18892ebfe85ed7',
'ext': 'mp4',
- 'title': 'Ð\98звеÑ\80жение вÑ\83лкана из Ñ\81пиÑ\87ек: зÑ\80елиÑ\89нÑ\8bй опÑ\8bÑ\82',
- 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
- 'thumbnail': 're:^https://avatars.mds.yandex.net/',
- 'uploader': 'Популярная механика',
+ 'title': 'Ð\92Ð\9eТ ÐТÐ\9e Focus. Ð\94едÑ\8b Ð\9cоÑ\80озÑ\8b на гидÑ\80оÑ\86иклаÑ\85',
+ 'description': 'md5:8684912f6086f298f8078d4af0e8a600',
+ 'thumbnail': 're:^https://avatars.dzeninfra.ru/',
+ 'uploader': 'AcademeG DailyStream',
},
'params': {
'skip_download': 'm3u8',
+ 'format': 'bestvideo',
},
+ 'skip': 'The page does not exist',
}, {
- 'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
+ 'url': 'https://dzen.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',
+ 'description': 'md5:8684912f6086f298f8078d4af0e8a600',
+ 'thumbnail': r're:^https://avatars\.dzeninfra\.ru/',
+ 'uploader': 'AcademeG DailyStream',
+ 'upload_date': '20191111',
+ 'timestamp': 1573465585,
},
+ 'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3',
'info_dict': {
'ext': 'mp4',
'title': 'Извержение вулкана из спичек: зрелищный опыт',
'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
- 'uploader': 'Популярная механика',
+ 'thumbnail': r're:^https://avatars\.dzeninfra\.ru/',
+ 'uploader': 'TechInsider',
+ 'timestamp': 1611378221,
+ 'upload_date': '20210123',
},
- 'params': {
- 'skip_download': 'm3u8',
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'https://dzen.ru/video/watch/6002240ff8b1af50bb2da5e3',
+ 'info_dict': {
+ 'id': '6002240ff8b1af50bb2da5e3',
+ 'ext': 'mp4',
+ 'title': 'Извержение вулкана из спичек: зрелищный опыт',
+ 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633',
+ 'thumbnail': 're:^https://avatars.dzeninfra.ru/',
+ 'uploader': 'TechInsider',
+ 'upload_date': '20210123',
+ 'timestamp': 1611378221,
},
+ '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,
+ }, {
+ 'url': 'https://dzen.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')
+ 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')
- 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:
+ item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str}))
+ video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {}
+
+ formats, subtitles = [], {}
+ for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})):
ext = determine_ext(s_url)
if ext == 'mpd':
- formats.extend(self._extract_mpd_formats(s_url, id, mpd_id='dash'))
+ fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')
elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4'))
- self._sort_formats(formats)
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4')
+ formats.extend(fmts)
+ subtitles = self._merge_subtitles(subtitles, subs)
return {
- 'id': id,
+ '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': self._og_search_description(webpage) or try_get(data_json, lambda x: x['og']['description']),
+ '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']),
}
class ZenYandexChannelIE(InfoExtractor):
- _VALID_URL = r'https?://zen\.yandex\.ru/(?!media|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
+ _VALID_URL = r'https?://(zen\.yandex|dzen)\.ru/(?!media|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
_TESTS = [{
'url': 'https://zen.yandex.ru/tok_media',
'info_dict': {
'id': 'tok_media',
+ 'title': 'СПЕКТР',
+ 'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56',
},
'playlist_mincount': 169,
+ 'skip': 'The page does not exist',
+ }, {
+ 'url': 'https://dzen.ru/tok_media',
+ 'info_dict': {
+ 'id': 'tok_media',
+ 'title': 'СПЕКТР',
+ 'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56',
+ },
+ 'playlist_mincount': 169,
+ 'skip': 'The page does not exist',
}, {
'url': 'https://zen.yandex.ru/id/606fd806cc13cb3c58c05cf5',
'info_dict': {
'id': '606fd806cc13cb3c58c05cf5',
+ 'description': 'md5:517b7c97d8ca92e940f5af65448fd928',
+ 'title': 'AcademeG DailyStream',
+ },
+ 'playlist_mincount': 657,
+ }, {
+ # Test that the playlist extractor finishes extracting when the
+ # channel has less than one page
+ 'url': 'https://zen.yandex.ru/jony_me',
+ 'info_dict': {
+ 'id': 'jony_me',
+ 'description': 'md5:ce0a5cad2752ab58701b5497835b2cc5',
+ 'title': 'JONY ',
+ },
+ 'playlist_count': 18,
+ }, {
+ # Test that the playlist extractor finishes extracting when the
+ # channel has more than one page of entries
+ 'url': 'https://zen.yandex.ru/tatyanareva',
+ 'info_dict': {
+ 'id': 'tatyanareva',
+ 'description': 'md5:40a1e51f174369ec3ba9d657734ac31f',
+ 'title': 'Татьяна Рева',
+ 'entries': 'maxcount:200',
+ },
+ 'playlist_mincount': 46,
+ }, {
+ 'url': 'https://dzen.ru/id/606fd806cc13cb3c58c05cf5',
+ 'info_dict': {
+ 'id': '606fd806cc13cb3c58c05cf5',
+ 'title': 'AcademeG DailyStream',
+ 'description': 'md5:517b7c97d8ca92e940f5af65448fd928',
},
'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
+ 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')))
+
+ next_page_id = 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:
+ 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])
+
+ 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)):
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
+
+ data = self._download_json(more, item_id, note=f'Downloading Page {page}')
+ items, more = data.get('items'), traverse_obj(data, ('more', 'link'))
def _real_extract(self, url):
- id = self._match_id(url)
- return self.playlist_result(self._entries(id, url), playlist_id=id)
+ 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)
+
+ 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')))