yt_dlp/extractor/rutube.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_str,
   6 )
   7 from ..utils import (
   8     bool_or_none,
   9     determine_ext,
  10     int_or_none,
  11     parse_qs,
  12     try_get,
  13     unified_timestamp,
  14     url_or_none,
  15 )
  16
  17
  18 class RutubeBaseIE(InfoExtractor):
  19     def _download_api_info(self, video_id, query=None):
  20         if not query:
  21             query = {}
  22         query['format'] = 'json'
  23         return self._download_json(
  24             'http://rutube.ru/api/video/%s/' % video_id,
  25             video_id, 'Downloading video JSON',
  26             'Unable to download video JSON', query=query)
  27
  28     def _extract_info(self, video, video_id=None, require_title=True):
  29         title = video['title'] if require_title else video.get('title')
  30
  31         age_limit = video.get('is_adult')
  32         if age_limit is not None:
  33             age_limit = 18 if age_limit is True else 0
  34
  35         uploader_id = try_get(video, lambda x: x['author']['id'])
  36         category = try_get(video, lambda x: x['category']['name'])
  37         description = video.get('description')
  38         duration = int_or_none(video.get('duration'))
  39
  40         return {
  41             'id': video.get('id') or video_id if video_id else video['id'],
  42             'title': title,
  43             'description': description,
  44             'thumbnail': video.get('thumbnail_url'),
  45             'duration': duration,
  46             'uploader': try_get(video, lambda x: x['author']['name']),
  47             'uploader_id': compat_str(uploader_id) if uploader_id else None,
  48             'timestamp': unified_timestamp(video.get('created_ts')),
  49             'categories': [category] if category else None,
  50             'age_limit': age_limit,
  51             'view_count': int_or_none(video.get('hits')),
  52             'comment_count': int_or_none(video.get('comments_count')),
  53             'is_live': bool_or_none(video.get('is_livestream')),
  54             'chapters': self._extract_chapters_from_description(description, duration),
  55         }
  56
  57     def _download_and_extract_info(self, video_id, query=None):
  58         return self._extract_info(
  59             self._download_api_info(video_id, query=query), video_id)
  60
  61     def _download_api_options(self, video_id, query=None):
  62         if not query:
  63             query = {}
  64         query['format'] = 'json'
  65         return self._download_json(
  66             'http://rutube.ru/api/play/options/%s/' % video_id,
  67             video_id, 'Downloading options JSON',
  68             'Unable to download options JSON',
  69             headers=self.geo_verification_headers(), query=query)
  70
  71     def _extract_formats(self, options, video_id):
  72         formats = []
  73         for format_id, format_url in options['video_balancer'].items():
  74             ext = determine_ext(format_url)
  75             if ext == 'm3u8':
  76                 formats.extend(self._extract_m3u8_formats(
  77                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  78             elif ext == 'f4m':
  79                 formats.extend(self._extract_f4m_formats(
  80                     format_url, video_id, f4m_id=format_id, fatal=False))
  81             else:
  82                 formats.append({
  83                     'url': format_url,
  84                     'format_id': format_id,
  85                 })
  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/(?: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
 172     @classmethod
 173     def suitable(cls, url):
 174         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 175
 176     def _real_extract(self, url):
 177         video_id = self._match_id(url)
 178         query = parse_qs(url)
 179         info = self._download_and_extract_info(video_id, query)
 180         info['formats'] = self._download_and_extract_formats(video_id, query)
 181         return info
 182
 183
 184 class RutubeEmbedIE(RutubeBaseIE):
 185     IE_NAME = 'rutube:embed'
 186     IE_DESC = 'Rutube embedded videos'
 187     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 188
 189     _TESTS = [{
 190         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 191         'info_dict': {
 192             'id': 'a10e53b86e8f349080f718582ce4c661',
 193             'ext': 'mp4',
 194             'timestamp': 1387830582,
 195             'upload_date': '20131223',
 196             'uploader_id': '297833',
 197             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 198             'uploader': 'subziro89 ILya',
 199             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 200         },
 201         'params': {
 202             'skip_download': True,
 203         },
 204     }, {
 205         'url': 'http://rutube.ru/play/embed/8083783',
 206         'only_matching': True,
 207     }, {
 208         # private video
 209         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 210         'only_matching': True,
 211     }]
 212
 213     def _real_extract(self, url):
 214         embed_id = self._match_id(url)
 215         # Query may contain private videos token and should be passed to API
 216         # requests (see #19163)
 217         query = parse_qs(url)
 218         options = self._download_api_options(embed_id, query)
 219         video_id = options['effective_video']
 220         formats = self._extract_formats(options, video_id)
 221         info = self._download_and_extract_info(video_id, query)
 222         info.update({
 223             'extractor_key': 'Rutube',
 224             'formats': formats,
 225         })
 226         return info
 227
 228
 229 class RutubePlaylistBaseIE(RutubeBaseIE):
 230     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 231         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 232
 233     def _entries(self, playlist_id, *args, **kwargs):
 234         next_page_url = None
 235         for pagenum in itertools.count(1):
 236             page = self._download_json(
 237                 next_page_url or self._next_page_url(
 238                     pagenum, playlist_id, *args, **kwargs),
 239                 playlist_id, 'Downloading page %s' % pagenum)
 240
 241             results = page.get('results')
 242             if not results or not isinstance(results, list):
 243                 break
 244
 245             for result in results:
 246                 video_url = url_or_none(result.get('video_url'))
 247                 if not video_url:
 248                     continue
 249                 entry = self._extract_info(result, require_title=False)
 250                 entry.update({
 251                     '_type': 'url',
 252                     'url': video_url,
 253                     'ie_key': RutubeIE.ie_key(),
 254                 })
 255                 yield entry
 256
 257             next_page_url = page.get('next')
 258             if not next_page_url or not page.get('has_next'):
 259                 break
 260
 261     def _extract_playlist(self, playlist_id, *args, **kwargs):
 262         return self.playlist_result(
 263             self._entries(playlist_id, *args, **kwargs),
 264             playlist_id, kwargs.get('playlist_name'))
 265
 266     def _real_extract(self, url):
 267         return self._extract_playlist(self._match_id(url))
 268
 269
 270 class RutubeTagsIE(RutubePlaylistBaseIE):
 271     IE_NAME = 'rutube:tags'
 272     IE_DESC = 'Rutube tags'
 273     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 274     _TESTS = [{
 275         'url': 'http://rutube.ru/tags/video/1800/',
 276         'info_dict': {
 277             'id': '1800',
 278         },
 279         'playlist_mincount': 68,
 280     }]
 281
 282     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 283
 284
 285 class RutubeMovieIE(RutubePlaylistBaseIE):
 286     IE_NAME = 'rutube:movie'
 287     IE_DESC = 'Rutube movies'
 288     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 289
 290     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 291     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 292
 293     def _real_extract(self, url):
 294         movie_id = self._match_id(url)
 295         movie = self._download_json(
 296             self._MOVIE_TEMPLATE % movie_id, movie_id,
 297             'Downloading movie JSON')
 298         return self._extract_playlist(
 299             movie_id, playlist_name=movie.get('name'))
 300
 301
 302 class RutubePersonIE(RutubePlaylistBaseIE):
 303     IE_NAME = 'rutube:person'
 304     IE_DESC = 'Rutube person videos'
 305     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 306     _TESTS = [{
 307         'url': 'http://rutube.ru/video/person/313878/',
 308         'info_dict': {
 309             'id': '313878',
 310         },
 311         'playlist_mincount': 37,
 312     }]
 313
 314     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 315
 316
 317 class RutubePlaylistIE(RutubePlaylistBaseIE):
 318     IE_NAME = 'rutube:playlist'
 319     IE_DESC = 'Rutube playlists'
 320     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 321     _TESTS = [{
 322         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 323         'info_dict': {
 324             'id': '3097',
 325         },
 326         'playlist_count': 27,
 327     }, {
 328         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 329         'only_matching': True,
 330     }]
 331
 332     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 333
 334     @classmethod
 335     def suitable(cls, url):
 336         from ..utils import int_or_none, parse_qs
 337
 338         if not super(RutubePlaylistIE, cls).suitable(url):
 339             return False
 340         params = parse_qs(url)
 341         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 342
 343     def _next_page_url(self, page_num, playlist_id, item_kind):
 344         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 345
 346     def _real_extract(self, url):
 347         qs = parse_qs(url)
 348         playlist_kind = qs['pl_type'][0]
 349         playlist_id = qs['pl_id'][0]
 350         return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 351
 352
 353 class RutubeChannelIE(RutubePlaylistBaseIE):
 354     IE_NAME = 'rutube:channel'
 355     IE_DESC = 'Rutube channel'
 356     _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
 357     _TESTS = [{
 358         'url': 'https://rutube.ru/channel/639184/videos/',
 359         'info_dict': {
 360             'id': '639184',
 361         },
 362         'playlist_mincount': 133,
 363     }]
 364
 365     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'