yt_dlp/extractor/rutube.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     bool_or_none,
   6     determine_ext,
   7     int_or_none,
   8     parse_qs,
   9     traverse_obj,
  10     try_get,
  11     unified_timestamp,
  12     url_or_none,
  13 )
  14
  15
  16 class RutubeBaseIE(InfoExtractor):
  17     def _download_api_info(self, video_id, query=None):
  18         if not query:
  19             query = {}
  20         query['format'] = 'json'
  21         return self._download_json(
  22             f'http://rutube.ru/api/video/{video_id}/',
  23             video_id, 'Downloading video JSON',
  24             'Unable to download video JSON', query=query)
  25
  26     def _extract_info(self, video, video_id=None, require_title=True):
  27         title = video['title'] if require_title else video.get('title')
  28
  29         age_limit = video.get('is_adult')
  30         if age_limit is not None:
  31             age_limit = 18 if age_limit is True else 0
  32
  33         uploader_id = try_get(video, lambda x: x['author']['id'])
  34         category = try_get(video, lambda x: x['category']['name'])
  35         description = video.get('description')
  36         duration = int_or_none(video.get('duration'))
  37
  38         return {
  39             'id': video.get('id') or video_id if video_id else video['id'],
  40             'title': title,
  41             'description': description,
  42             'thumbnail': video.get('thumbnail_url'),
  43             'duration': duration,
  44             'uploader': try_get(video, lambda x: x['author']['name']),
  45             'uploader_id': str(uploader_id) if uploader_id else None,
  46             'timestamp': unified_timestamp(video.get('created_ts')),
  47             'categories': [category] if category else None,
  48             'age_limit': age_limit,
  49             'view_count': int_or_none(video.get('hits')),
  50             'comment_count': int_or_none(video.get('comments_count')),
  51             'is_live': bool_or_none(video.get('is_livestream')),
  52             'chapters': self._extract_chapters_from_description(description, duration),
  53         }
  54
  55     def _download_and_extract_info(self, video_id, query=None):
  56         return self._extract_info(
  57             self._download_api_info(video_id, query=query), video_id)
  58
  59     def _download_api_options(self, video_id, query=None):
  60         if not query:
  61             query = {}
  62         query['format'] = 'json'
  63         return self._download_json(
  64             f'http://rutube.ru/api/play/options/{video_id}/',
  65             video_id, 'Downloading options JSON',
  66             'Unable to download options JSON',
  67             headers=self.geo_verification_headers(), query=query)
  68
  69     def _extract_formats(self, options, video_id):
  70         formats = []
  71         for format_id, format_url in options['video_balancer'].items():
  72             ext = determine_ext(format_url)
  73             if ext == 'm3u8':
  74                 formats.extend(self._extract_m3u8_formats(
  75                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  76             elif ext == 'f4m':
  77                 formats.extend(self._extract_f4m_formats(
  78                     format_url, video_id, f4m_id=format_id, fatal=False))
  79             else:
  80                 formats.append({
  81                     'url': format_url,
  82                     'format_id': format_id,
  83                 })
  84         for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
  85             formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
  86         return formats
  87
  88     def _download_and_extract_formats(self, video_id, query=None):
  89         return self._extract_formats(
  90             self._download_api_options(video_id, query=query), video_id)
  91
  92
  93 class RutubeIE(RutubeBaseIE):
  94     IE_NAME = 'rutube'
  95     IE_DESC = 'Rutube videos'
  96     _VALID_URL = r'https?://rutube\.ru/(?:(?:live/)?video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  97     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
  98
  99     _TESTS = [{
 100         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 101         'md5': 'e33ac625efca66aba86cbec9851f2692',
 102         'info_dict': {
 103             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 104             'ext': 'mp4',
 105             'title': 'Раненный кенгуру забежал в аптеку',
 106             'description': 'http://www.ntdtv.ru ',
 107             'duration': 81,
 108             'uploader': 'NTDRussian',
 109             'uploader_id': '29790',
 110             'timestamp': 1381943602,
 111             'upload_date': '20131016',
 112             'age_limit': 0,
 113             'view_count': int,
 114             'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
 115             'categories': ['Новости и СМИ'],
 116             'chapters': [],
 117         },
 118         'expected_warnings': ['Unable to download f4m'],
 119     }, {
 120         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
 121         'only_matching': True,
 122     }, {
 123         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
 124         'only_matching': True,
 125     }, {
 126         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
 127         'only_matching': True,
 128     }, {
 129         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
 130         'only_matching': True,
 131     }, {
 132         'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
 133         'md5': 'd106225f15d625538fe22971158e896f',
 134         'info_dict': {
 135             'id': '884fb55f07a97ab673c7d654553e0f48',
 136             'ext': 'mp4',
 137             'title': 'Яцуноками, Nioh2',
 138             'description': 'Nioh2: финал сражения с боссом Яцуноками',
 139             'duration': 15,
 140             'uploader': 'mexus',
 141             'uploader_id': '24222106',
 142             'timestamp': 1670646232,
 143             'upload_date': '20221210',
 144             'age_limit': 0,
 145             'view_count': int,
 146             'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
 147             'categories': ['Видеоигры'],
 148             'chapters': [],
 149         },
 150         'expected_warnings': ['Unable to download f4m'],
 151     }, {
 152         'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
 153         'info_dict': {
 154             'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
 155             'ext': 'mp4',
 156             'chapters': 'count:4',
 157             'categories': ['Бизнес и предпринимательство'],
 158             'description': 'md5:252feac1305257d8c1bab215cedde75d',
 159             'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
 160             'duration': 782,
 161             'age_limit': 0,
 162             'uploader_id': '23491359',
 163             'timestamp': 1677153329,
 164             'view_count': int,
 165             'upload_date': '20230223',
 166             'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
 167             'uploader': 'Стас Быков',
 168         },
 169         'expected_warnings': ['Unable to download f4m'],
 170     }, {
 171         'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
 172         'info_dict': {
 173             'id': 'c58f502c7bb34a8fcdd976b221fca292',
 174             'ext': 'mp4',
 175             'categories': ['Телепередачи'],
 176             'description': '',
 177             'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
 178             'live_status': 'is_live',
 179             'age_limit': 0,
 180             'uploader_id': '23460655',
 181             'timestamp': 1652972968,
 182             'view_count': int,
 183             'upload_date': '20220519',
 184             'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 185             'uploader': 'Первый канал',
 186         },
 187     }, {
 188         'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
 189         'only_matching': True,
 190     }, {
 191         'url': 'https://rutube.ru/live/video/private/c58f502c7bb34a8fcdd976b221fca292/',
 192         'only_matching': True,
 193     }]
 194
 195     @classmethod
 196     def suitable(cls, url):
 197         return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
 198
 199     def _real_extract(self, url):
 200         video_id = self._match_id(url)
 201         query = parse_qs(url)
 202         info = self._download_and_extract_info(video_id, query)
 203         info['formats'] = self._download_and_extract_formats(video_id, query)
 204         return info
 205
 206
 207 class RutubeEmbedIE(RutubeBaseIE):
 208     IE_NAME = 'rutube:embed'
 209     IE_DESC = 'Rutube embedded videos'
 210     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 211
 212     _TESTS = [{
 213         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 214         'info_dict': {
 215             'id': 'a10e53b86e8f349080f718582ce4c661',
 216             'ext': 'mp4',
 217             'timestamp': 1387830582,
 218             'upload_date': '20131223',
 219             'uploader_id': '297833',
 220             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 221             'uploader': 'subziro89 ILya',
 222             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 223         },
 224         'params': {
 225             'skip_download': True,
 226         },
 227     }, {
 228         'url': 'http://rutube.ru/play/embed/8083783',
 229         'only_matching': True,
 230     }, {
 231         # private video
 232         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 233         'only_matching': True,
 234     }]
 235
 236     def _real_extract(self, url):
 237         embed_id = self._match_id(url)
 238         # Query may contain private videos token and should be passed to API
 239         # requests (see #19163)
 240         query = parse_qs(url)
 241         options = self._download_api_options(embed_id, query)
 242         video_id = options['effective_video']
 243         formats = self._extract_formats(options, video_id)
 244         info = self._download_and_extract_info(video_id, query)
 245         info.update({
 246             'extractor_key': 'Rutube',
 247             'formats': formats,
 248         })
 249         return info
 250
 251
 252 class RutubePlaylistBaseIE(RutubeBaseIE):
 253     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 254         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 255
 256     def _entries(self, playlist_id, *args, **kwargs):
 257         next_page_url = None
 258         for pagenum in itertools.count(1):
 259             page = self._download_json(
 260                 next_page_url or self._next_page_url(
 261                     pagenum, playlist_id, *args, **kwargs),
 262                 playlist_id, f'Downloading page {pagenum}')
 263
 264             results = page.get('results')
 265             if not results or not isinstance(results, list):
 266                 break
 267
 268             for result in results:
 269                 video_url = url_or_none(result.get('video_url'))
 270                 if not video_url:
 271                     continue
 272                 entry = self._extract_info(result, require_title=False)
 273                 entry.update({
 274                     '_type': 'url',
 275                     'url': video_url,
 276                     'ie_key': RutubeIE.ie_key(),
 277                 })
 278                 yield entry
 279
 280             next_page_url = page.get('next')
 281             if not next_page_url or not page.get('has_next'):
 282                 break
 283
 284     def _extract_playlist(self, playlist_id, *args, **kwargs):
 285         return self.playlist_result(
 286             self._entries(playlist_id, *args, **kwargs),
 287             playlist_id, kwargs.get('playlist_name'))
 288
 289     def _real_extract(self, url):
 290         return self._extract_playlist(self._match_id(url))
 291
 292
 293 class RutubeTagsIE(RutubePlaylistBaseIE):
 294     IE_NAME = 'rutube:tags'
 295     IE_DESC = 'Rutube tags'
 296     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 297     _TESTS = [{
 298         'url': 'http://rutube.ru/tags/video/1800/',
 299         'info_dict': {
 300             'id': '1800',
 301         },
 302         'playlist_mincount': 68,
 303     }]
 304
 305     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 306
 307
 308 class RutubeMovieIE(RutubePlaylistBaseIE):
 309     IE_NAME = 'rutube:movie'
 310     IE_DESC = 'Rutube movies'
 311     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 312
 313     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 314     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 315
 316     def _real_extract(self, url):
 317         movie_id = self._match_id(url)
 318         movie = self._download_json(
 319             self._MOVIE_TEMPLATE % movie_id, movie_id,
 320             'Downloading movie JSON')
 321         return self._extract_playlist(
 322             movie_id, playlist_name=movie.get('name'))
 323
 324
 325 class RutubePersonIE(RutubePlaylistBaseIE):
 326     IE_NAME = 'rutube:person'
 327     IE_DESC = 'Rutube person videos'
 328     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 329     _TESTS = [{
 330         'url': 'http://rutube.ru/video/person/313878/',
 331         'info_dict': {
 332             'id': '313878',
 333         },
 334         'playlist_mincount': 37,
 335     }]
 336
 337     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 338
 339
 340 class RutubePlaylistIE(RutubePlaylistBaseIE):
 341     IE_NAME = 'rutube:playlist'
 342     IE_DESC = 'Rutube playlists'
 343     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 344     _TESTS = [{
 345         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 346         'info_dict': {
 347             'id': '3097',
 348         },
 349         'playlist_count': 27,
 350     }, {
 351         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 352         'only_matching': True,
 353     }]
 354
 355     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 356
 357     @classmethod
 358     def suitable(cls, url):
 359         from ..utils import int_or_none, parse_qs
 360
 361         if not super().suitable(url):
 362             return False
 363         params = parse_qs(url)
 364         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 365
 366     def _next_page_url(self, page_num, playlist_id, item_kind):
 367         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 368
 369     def _real_extract(self, url):
 370         qs = parse_qs(url)
 371         playlist_kind = qs['pl_type'][0]
 372         playlist_id = qs['pl_id'][0]
 373         return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 374
 375
 376 class RutubeChannelIE(RutubePlaylistBaseIE):
 377     IE_NAME = 'rutube:channel'
 378     IE_DESC = 'Rutube channel'
 379     _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
 380     _TESTS = [{
 381         'url': 'https://rutube.ru/channel/639184/videos/',
 382         'info_dict': {
 383             'id': '639184',
 384         },
 385         'playlist_mincount': 133,
 386     }]
 387
 388     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'