yt_dlp/extractor/rutube.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     UnsupportedError,
   6     bool_or_none,
   7     determine_ext,
   8     int_or_none,
   9     js_to_json,
  10     parse_qs,
  11     str_or_none,
  12     try_get,
  13     unified_timestamp,
  14     url_or_none,
  15 )
  16 from ..utils.traversal import (
  17     subs_list_to_dict,
  18     traverse_obj,
  19 )
  20
  21
  22 class RutubeBaseIE(InfoExtractor):
  23     def _download_api_info(self, video_id, query=None):
  24         if not query:
  25             query = {}
  26         query['format'] = 'json'
  27         return self._download_json(
  28             f'https://rutube.ru/api/video/{video_id}/',
  29             video_id, 'Downloading video JSON',
  30             'Unable to download video JSON', query=query)
  31
  32     def _extract_info(self, video, video_id=None, require_title=True):
  33         title = video['title'] if require_title else video.get('title')
  34
  35         age_limit = video.get('is_adult')
  36         if age_limit is not None:
  37             age_limit = 18 if age_limit is True else 0
  38
  39         uploader_id = try_get(video, lambda x: x['author']['id'])
  40         category = try_get(video, lambda x: x['category']['name'])
  41         description = video.get('description')
  42         duration = int_or_none(video.get('duration'))
  43
  44         return {
  45             'id': video.get('id') or video_id if video_id else video['id'],
  46             'title': title,
  47             'description': description,
  48             'thumbnail': video.get('thumbnail_url'),
  49             'duration': duration,
  50             'uploader': try_get(video, lambda x: x['author']['name']),
  51             'uploader_id': str(uploader_id) if uploader_id else None,
  52             'timestamp': unified_timestamp(video.get('created_ts')),
  53             'categories': [category] if category else None,
  54             'age_limit': age_limit,
  55             'view_count': int_or_none(video.get('hits')),
  56             'comment_count': int_or_none(video.get('comments_count')),
  57             'is_live': bool_or_none(video.get('is_livestream')),
  58             'chapters': self._extract_chapters_from_description(description, duration),
  59         }
  60
  61     def _download_and_extract_info(self, video_id, query=None):
  62         return self._extract_info(
  63             self._download_api_info(video_id, query=query), video_id)
  64
  65     def _download_api_options(self, video_id, query=None):
  66         if not query:
  67             query = {}
  68         query['format'] = 'json'
  69         return self._download_json(
  70             f'https://rutube.ru/api/play/options/{video_id}/',
  71             video_id, 'Downloading options JSON',
  72             'Unable to download options JSON',
  73             headers=self.geo_verification_headers(), query=query)
  74
  75     def _extract_formats_and_subtitles(self, options, video_id):
  76         formats = []
  77         subtitles = {}
  78         for format_id, format_url in options['video_balancer'].items():
  79             ext = determine_ext(format_url)
  80             if ext == 'm3u8':
  81                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
  82                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
  83                 formats.extend(fmts)
  84                 self._merge_subtitles(subs, target=subtitles)
  85             elif ext == 'f4m':
  86                 formats.extend(self._extract_f4m_formats(
  87                     format_url, video_id, f4m_id=format_id, fatal=False))
  88             else:
  89                 formats.append({
  90                     'url': format_url,
  91                     'format_id': format_id,
  92                 })
  93         for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
  94             fmts, subs = self._extract_m3u8_formats_and_subtitles(
  95                 hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
  96             formats.extend(fmts)
  97             self._merge_subtitles(subs, target=subtitles)
  98         self._merge_subtitles(traverse_obj(options, ('captions', ..., {
  99             'id': 'code',
 100             'url': 'file',
 101             'name': ('langTitle', {str}),
 102         }, all, {subs_list_to_dict(lang='ru')})), target=subtitles)
 103         return formats, subtitles
 104
 105     def _download_and_extract_formats_and_subtitles(self, video_id, query=None):
 106         return self._extract_formats_and_subtitles(
 107             self._download_api_options(video_id, query=query), video_id)
 108
 109
 110 class RutubeIE(RutubeBaseIE):
 111     IE_NAME = 'rutube'
 112     IE_DESC = 'Rutube videos'
 113     _VALID_URL = r'https?://rutube\.ru/(?:(?:live/)?video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
 114     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
 115
 116     _TESTS = [{
 117         'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 118         'md5': '3d73fdfe5bb81b9aef139e22ef3de26a',
 119         'info_dict': {
 120             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 121             'ext': 'mp4',
 122             'title': 'Раненный кенгуру забежал в аптеку',
 123             'description': 'http://www.ntdtv.ru ',
 124             'duration': 81,
 125             'uploader': 'NTDRussian',
 126             'uploader_id': '29790',
 127             'timestamp': 1381943602,
 128             'upload_date': '20131016',
 129             'age_limit': 0,
 130             'view_count': int,
 131             'thumbnail': 'https://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
 132             'categories': ['Новости и СМИ'],
 133             'chapters': [],
 134         },
 135     }, {
 136         'url': 'https://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
 137         'only_matching': True,
 138     }, {
 139         'url': 'https://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
 140         'only_matching': True,
 141     }, {
 142         'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
 143         'only_matching': True,
 144     }, {
 145         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
 146         'only_matching': True,
 147     }, {
 148         'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
 149         'md5': '4fce7b4fcc7b1bcaa3f45eb1e1ad0dd7',
 150         'info_dict': {
 151             'id': '884fb55f07a97ab673c7d654553e0f48',
 152             'ext': 'mp4',
 153             'title': 'Яцуноками, Nioh2',
 154             'description': 'Nioh2: финал сражения с боссом Яцуноками',
 155             'duration': 15,
 156             'uploader': 'mexus',
 157             'uploader_id': '24222106',
 158             'timestamp': 1670646232,
 159             'upload_date': '20221210',
 160             'age_limit': 0,
 161             'view_count': int,
 162             'thumbnail': 'https://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
 163             'categories': ['Видеоигры'],
 164             'chapters': [],
 165         },
 166     }, {
 167         'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
 168         'info_dict': {
 169             'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
 170             'ext': 'mp4',
 171             'chapters': 'count:4',
 172             'categories': ['Бизнес и предпринимательство'],
 173             'description': 'md5:252feac1305257d8c1bab215cedde75d',
 174             'thumbnail': 'https://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
 175             'duration': 782,
 176             'age_limit': 0,
 177             'uploader_id': '23491359',
 178             'timestamp': 1677153329,
 179             'view_count': int,
 180             'upload_date': '20230223',
 181             'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании #1',
 182             'uploader': 'Стас Быков',
 183         },
 184     }, {
 185         'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
 186         'info_dict': {
 187             'id': 'c58f502c7bb34a8fcdd976b221fca292',
 188             'ext': 'mp4',
 189             'categories': ['Телепередачи'],
 190             'description': '',
 191             'thumbnail': 'https://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
 192             'live_status': 'is_live',
 193             'age_limit': 0,
 194             'uploader_id': '23460655',
 195             'timestamp': 1652972968,
 196             'view_count': int,
 197             'upload_date': '20220519',
 198             'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 199             'uploader': 'Первый канал',
 200         },
 201     }, {
 202         'url': 'https://rutube.ru/play/embed/03a9cb54bac3376af4c5cb0f18444e01/',
 203         'info_dict': {
 204             'id': '03a9cb54bac3376af4c5cb0f18444e01',
 205             'ext': 'mp4',
 206             'age_limit': 0,
 207             'description': '',
 208             'title': 'Церемония начала торгов акциями ПАО «ЕвроТранс»',
 209             'chapters': [],
 210             'upload_date': '20240829',
 211             'duration': 293,
 212             'uploader': 'MOEX - Московская биржа',
 213             'timestamp': 1724946628,
 214             'thumbnail': 'https://pic.rutubelist.ru/video/2e/24/2e241fddb459baf0fa54acfca44874f4.jpg',
 215             'view_count': int,
 216             'uploader_id': '38420507',
 217             'categories': ['Интервью'],
 218         },
 219     }, {
 220         'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
 221         'only_matching': True,
 222     }, {
 223         'url': 'https://rutube.ru/live/video/private/c58f502c7bb34a8fcdd976b221fca292/',
 224         'only_matching': True,
 225     }]
 226
 227     def _real_extract(self, url):
 228         video_id = self._match_id(url)
 229         query = parse_qs(url)
 230         info = self._download_and_extract_info(video_id, query)
 231         formats, subtitles = self._download_and_extract_formats_and_subtitles(video_id, query)
 232         return {
 233             **info,
 234             'formats': formats,
 235             'subtitles': subtitles,
 236         }
 237
 238
 239 class RutubeEmbedIE(RutubeBaseIE):
 240     IE_NAME = 'rutube:embed'
 241     IE_DESC = 'Rutube embedded videos'
 242     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)(?:[?#/]|$)'
 243
 244     _TESTS = [{
 245         'url': 'https://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 246         'info_dict': {
 247             'id': 'a10e53b86e8f349080f718582ce4c661',
 248             'ext': 'mp4',
 249             'timestamp': 1387830582,
 250             'upload_date': '20131223',
 251             'uploader_id': '297833',
 252             'uploader': 'subziro89 ILya',
 253             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 254             'age_limit': 0,
 255             'duration': 1395,
 256             'chapters': [],
 257             'description': 'md5:a5acea57bbc3ccdc3cacd1f11a014b5b',
 258             'view_count': int,
 259             'thumbnail': 'https://pic.rutubelist.ru/video/d3/03/d3031f4670a6e6170d88fb3607948418.jpg',
 260             'categories': ['Сериалы'],
 261         },
 262         'params': {
 263             'skip_download': True,
 264         },
 265     }, {
 266         'url': 'https://rutube.ru/play/embed/8083783',
 267         'only_matching': True,
 268     }, {
 269         # private video
 270         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 271         'only_matching': True,
 272     }]
 273
 274     def _real_extract(self, url):
 275         embed_id = self._match_id(url)
 276         # Query may contain private videos token and should be passed to API
 277         # requests (see #19163)
 278         query = parse_qs(url)
 279         options = self._download_api_options(embed_id, query)
 280         video_id = options['effective_video']
 281         formats, subtitles = self._extract_formats_and_subtitles(options, video_id)
 282         info = self._download_and_extract_info(video_id, query)
 283         info.update({
 284             'extractor_key': 'Rutube',
 285             'formats': formats,
 286             'subtitles': subtitles,
 287         })
 288         return info
 289
 290
 291 class RutubePlaylistBaseIE(RutubeBaseIE):
 292     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 293         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 294
 295     def _entries(self, playlist_id, *args, **kwargs):
 296         next_page_url = None
 297         for pagenum in itertools.count(1):
 298             page = self._download_json(
 299                 next_page_url or self._next_page_url(
 300                     pagenum, playlist_id, *args, **kwargs),
 301                 playlist_id, f'Downloading page {pagenum}')
 302
 303             results = page.get('results')
 304             if not results or not isinstance(results, list):
 305                 break
 306
 307             for result in results:
 308                 video_url = url_or_none(result.get('video_url'))
 309                 if not video_url:
 310                     continue
 311                 entry = self._extract_info(result, require_title=False)
 312                 entry.update({
 313                     '_type': 'url',
 314                     'url': video_url,
 315                     'ie_key': RutubeIE.ie_key(),
 316                 })
 317                 yield entry
 318
 319             next_page_url = page.get('next')
 320             if not next_page_url or not page.get('has_next'):
 321                 break
 322
 323     def _extract_playlist(self, playlist_id, *args, **kwargs):
 324         return self.playlist_result(
 325             self._entries(playlist_id, *args, **kwargs),
 326             playlist_id, kwargs.get('playlist_name'))
 327
 328     def _real_extract(self, url):
 329         return self._extract_playlist(self._match_id(url))
 330
 331
 332 class RutubeTagsIE(RutubePlaylistBaseIE):
 333     IE_NAME = 'rutube:tags'
 334     IE_DESC = 'Rutube tags'
 335     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 336     _TESTS = [{
 337         'url': 'https://rutube.ru/tags/video/1800/',
 338         'info_dict': {
 339             'id': '1800',
 340         },
 341         'playlist_mincount': 68,
 342     }]
 343
 344     _PAGE_TEMPLATE = 'https://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 345
 346
 347 class RutubeMovieIE(RutubePlaylistBaseIE):
 348     IE_NAME = 'rutube:movie'
 349     IE_DESC = 'Rutube movies'
 350     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 351
 352     _MOVIE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/?format=json'
 353     _PAGE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 354
 355     def _real_extract(self, url):
 356         movie_id = self._match_id(url)
 357         movie = self._download_json(
 358             self._MOVIE_TEMPLATE % movie_id, movie_id,
 359             'Downloading movie JSON')
 360         return self._extract_playlist(
 361             movie_id, playlist_name=movie.get('name'))
 362
 363
 364 class RutubePersonIE(RutubePlaylistBaseIE):
 365     IE_NAME = 'rutube:person'
 366     IE_DESC = 'Rutube person videos'
 367     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 368     _TESTS = [{
 369         'url': 'https://rutube.ru/video/person/313878/',
 370         'info_dict': {
 371             'id': '313878',
 372         },
 373         'playlist_mincount': 36,
 374     }]
 375
 376     _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json'
 377
 378
 379 class RutubePlaylistIE(RutubePlaylistBaseIE):
 380     IE_NAME = 'rutube:playlist'
 381     IE_DESC = 'Rutube playlists'
 382     _VALID_URL = r'https?://rutube\.ru/plst/(?P<id>\d+)'
 383     _TESTS = [{
 384         'url': 'https://rutube.ru/plst/308547/',
 385         'info_dict': {
 386             'id': '308547',
 387         },
 388         'playlist_mincount': 22,
 389     }]
 390     _PAGE_TEMPLATE = 'https://rutube.ru/api/playlist/custom/%s/videos?page=%s&format=json'
 391
 392
 393 class RutubeChannelIE(RutubePlaylistBaseIE):
 394     IE_NAME = 'rutube:channel'
 395     IE_DESC = 'Rutube channel'
 396     _VALID_URL = r'https?://rutube\.ru/(?:channel/(?P<id>\d+)|u/(?P<slug>\w+))(?:/(?P<section>videos|shorts|playlists))?'
 397     _TESTS = [{
 398         'url': 'https://rutube.ru/channel/639184/videos/',
 399         'info_dict': {
 400             'id': '639184_videos',
 401         },
 402         'playlist_mincount': 129,
 403     }, {
 404         'url': 'https://rutube.ru/channel/25902603/shorts/',
 405         'info_dict': {
 406             'id': '25902603_shorts',
 407         },
 408         'playlist_mincount': 277,
 409     }, {
 410         'url': 'https://rutube.ru/channel/25902603/',
 411         'info_dict': {
 412             'id': '25902603',
 413         },
 414         'playlist_mincount': 406,
 415     }, {
 416         'url': 'https://rutube.ru/u/rutube/videos/',
 417         'info_dict': {
 418             'id': '23704195_videos',
 419         },
 420         'playlist_mincount': 113,
 421     }]
 422
 423     _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json&origin__type=%s'
 424
 425     def _next_page_url(self, page_num, playlist_id, section):
 426         origin_type = {
 427             'videos': 'rtb,rst,ifrm,rspa',
 428             'shorts': 'rshorts',
 429             None: '',
 430         }.get(section)
 431         return self._PAGE_TEMPLATE % (playlist_id, page_num, origin_type)
 432
 433     def _real_extract(self, url):
 434         playlist_id, slug, section = self._match_valid_url(url).group('id', 'slug', 'section')
 435         if section == 'playlists':
 436             raise UnsupportedError(url)
 437         if slug:
 438             webpage = self._download_webpage(url, slug)
 439             redux_state = self._search_json(
 440                 r'window\.reduxState\s*=', webpage, 'redux state', slug, transform_source=js_to_json)
 441             playlist_id = traverse_obj(redux_state, (
 442                 'api', 'queries', lambda k, _: k.startswith('channelIdBySlug'),
 443                 'data', 'channel_id', {int}, {str_or_none}, any))
 444         playlist = self._extract_playlist(playlist_id, section=section)
 445         if section:
 446             playlist['id'] = f'{playlist_id}_{section}'
 447         return playlist