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     determine_ext,
   9     bool_or_none,
  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     @staticmethod
  29     def _extract_info(video, video_id=None, require_title=True):
  30         title = video['title'] if require_title else video.get('title')
  31
  32         age_limit = video.get('is_adult')
  33         if age_limit is not None:
  34             age_limit = 18 if age_limit is True else 0
  35
  36         uploader_id = try_get(video, lambda x: x['author']['id'])
  37         category = try_get(video, lambda x: x['category']['name'])
  38
  39         return {
  40             'id': video.get('id') or video_id if video_id else video['id'],
  41             'title': title,
  42             'description': video.get('description'),
  43             'thumbnail': video.get('thumbnail_url'),
  44             'duration': int_or_none(video.get('duration')),
  45             'uploader': try_get(video, lambda x: x['author']['name']),
  46             'uploader_id': compat_str(uploader_id) if uploader_id else None,
  47             'timestamp': unified_timestamp(video.get('created_ts')),
  48             'category': [category] if category else None,
  49             'age_limit': age_limit,
  50             'view_count': int_or_none(video.get('hits')),
  51             'comment_count': int_or_none(video.get('comments_count')),
  52             'is_live': bool_or_none(video.get('is_livestream')),
  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             'http://rutube.ru/api/play/options/%s/' % 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         return formats
  85
  86     def _download_and_extract_formats(self, video_id, query=None):
  87         return self._extract_formats(
  88             self._download_api_options(video_id, query=query), video_id)
  89
  90
  91 class RutubeIE(RutubeBaseIE):
  92     IE_NAME = 'rutube'
  93     IE_DESC = 'Rutube videos'
  94     _VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  95     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
  96
  97     _TESTS = [{
  98         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
  99         'md5': 'e33ac625efca66aba86cbec9851f2692',
 100         'info_dict': {
 101             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 102             'ext': 'mp4',
 103             'title': 'Раненный кенгуру забежал в аптеку',
 104             'description': 'http://www.ntdtv.ru ',
 105             'duration': 81,
 106             'uploader': 'NTDRussian',
 107             'uploader_id': '29790',
 108             'timestamp': 1381943602,
 109             'upload_date': '20131016',
 110             'age_limit': 0,
 111             'view_count': int,
 112             'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
 113             'category': ['Новости и СМИ'],
 114
 115         },
 116     }, {
 117         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
 118         'only_matching': True,
 119     }, {
 120         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
 121         'only_matching': True,
 122     }, {
 123         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
 124         'only_matching': True,
 125     }, {
 126         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
 127         'only_matching': True,
 128     }, {
 129         'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
 130         'md5': 'd106225f15d625538fe22971158e896f',
 131         'info_dict': {
 132             'id': '884fb55f07a97ab673c7d654553e0f48',
 133             'ext': 'mp4',
 134             'title': 'Яцуноками, Nioh2',
 135             'description': 'Nioh2: финал сражения с боссом Яцуноками',
 136             'duration': 15,
 137             'uploader': 'mexus',
 138             'uploader_id': '24222106',
 139             'timestamp': 1670646232,
 140             'upload_date': '20221210',
 141             'age_limit': 0,
 142             'view_count': int,
 143             'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
 144             'category': ['Видеоигры'],
 145         },
 146     }]
 147
 148     @classmethod
 149     def suitable(cls, url):
 150         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 151
 152     def _real_extract(self, url):
 153         video_id = self._match_id(url)
 154         query = parse_qs(url)
 155         info = self._download_and_extract_info(video_id, query)
 156         info['formats'] = self._download_and_extract_formats(video_id, query)
 157         return info
 158
 159
 160 class RutubeEmbedIE(RutubeBaseIE):
 161     IE_NAME = 'rutube:embed'
 162     IE_DESC = 'Rutube embedded videos'
 163     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 164
 165     _TESTS = [{
 166         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 167         'info_dict': {
 168             'id': 'a10e53b86e8f349080f718582ce4c661',
 169             'ext': 'mp4',
 170             'timestamp': 1387830582,
 171             'upload_date': '20131223',
 172             'uploader_id': '297833',
 173             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 174             'uploader': 'subziro89 ILya',
 175             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 176         },
 177         'params': {
 178             'skip_download': True,
 179         },
 180     }, {
 181         'url': 'http://rutube.ru/play/embed/8083783',
 182         'only_matching': True,
 183     }, {
 184         # private video
 185         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 186         'only_matching': True,
 187     }]
 188
 189     def _real_extract(self, url):
 190         embed_id = self._match_id(url)
 191         # Query may contain private videos token and should be passed to API
 192         # requests (see #19163)
 193         query = parse_qs(url)
 194         options = self._download_api_options(embed_id, query)
 195         video_id = options['effective_video']
 196         formats = self._extract_formats(options, video_id)
 197         info = self._download_and_extract_info(video_id, query)
 198         info.update({
 199             'extractor_key': 'Rutube',
 200             'formats': formats,
 201         })
 202         return info
 203
 204
 205 class RutubePlaylistBaseIE(RutubeBaseIE):
 206     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 207         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 208
 209     def _entries(self, playlist_id, *args, **kwargs):
 210         next_page_url = None
 211         for pagenum in itertools.count(1):
 212             page = self._download_json(
 213                 next_page_url or self._next_page_url(
 214                     pagenum, playlist_id, *args, **kwargs),
 215                 playlist_id, 'Downloading page %s' % pagenum)
 216
 217             results = page.get('results')
 218             if not results or not isinstance(results, list):
 219                 break
 220
 221             for result in results:
 222                 video_url = url_or_none(result.get('video_url'))
 223                 if not video_url:
 224                     continue
 225                 entry = self._extract_info(result, require_title=False)
 226                 entry.update({
 227                     '_type': 'url',
 228                     'url': video_url,
 229                     'ie_key': RutubeIE.ie_key(),
 230                 })
 231                 yield entry
 232
 233             next_page_url = page.get('next')
 234             if not next_page_url or not page.get('has_next'):
 235                 break
 236
 237     def _extract_playlist(self, playlist_id, *args, **kwargs):
 238         return self.playlist_result(
 239             self._entries(playlist_id, *args, **kwargs),
 240             playlist_id, kwargs.get('playlist_name'))
 241
 242     def _real_extract(self, url):
 243         return self._extract_playlist(self._match_id(url))
 244
 245
 246 class RutubeTagsIE(RutubePlaylistBaseIE):
 247     IE_NAME = 'rutube:tags'
 248     IE_DESC = 'Rutube tags'
 249     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 250     _TESTS = [{
 251         'url': 'http://rutube.ru/tags/video/1800/',
 252         'info_dict': {
 253             'id': '1800',
 254         },
 255         'playlist_mincount': 68,
 256     }]
 257
 258     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 259
 260
 261 class RutubeMovieIE(RutubePlaylistBaseIE):
 262     IE_NAME = 'rutube:movie'
 263     IE_DESC = 'Rutube movies'
 264     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 265
 266     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 267     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 268
 269     def _real_extract(self, url):
 270         movie_id = self._match_id(url)
 271         movie = self._download_json(
 272             self._MOVIE_TEMPLATE % movie_id, movie_id,
 273             'Downloading movie JSON')
 274         return self._extract_playlist(
 275             movie_id, playlist_name=movie.get('name'))
 276
 277
 278 class RutubePersonIE(RutubePlaylistBaseIE):
 279     IE_NAME = 'rutube:person'
 280     IE_DESC = 'Rutube person videos'
 281     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 282     _TESTS = [{
 283         'url': 'http://rutube.ru/video/person/313878/',
 284         'info_dict': {
 285             'id': '313878',
 286         },
 287         'playlist_mincount': 37,
 288     }]
 289
 290     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 291
 292
 293 class RutubePlaylistIE(RutubePlaylistBaseIE):
 294     IE_NAME = 'rutube:playlist'
 295     IE_DESC = 'Rutube playlists'
 296     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 297     _TESTS = [{
 298         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 299         'info_dict': {
 300             'id': '3097',
 301         },
 302         'playlist_count': 27,
 303     }, {
 304         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 305         'only_matching': True,
 306     }]
 307
 308     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 309
 310     @classmethod
 311     def suitable(cls, url):
 312         from ..utils import int_or_none, parse_qs
 313
 314         if not super(RutubePlaylistIE, cls).suitable(url):
 315             return False
 316         params = parse_qs(url)
 317         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 318
 319     def _next_page_url(self, page_num, playlist_id, item_kind):
 320         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 321
 322     def _real_extract(self, url):
 323         qs = parse_qs(url)
 324         playlist_kind = qs['pl_type'][0]
 325         playlist_id = qs['pl_id'][0]
 326         return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 327
 328
 329 class RutubeChannelIE(RutubePlaylistBaseIE):
 330     IE_NAME = 'rutube:channel'
 331     IE_DESC = 'Rutube channel'
 332     _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
 333     _TESTS = [{
 334         'url': 'https://rutube.ru/channel/639184/videos/',
 335         'info_dict': {
 336             'id': '639184',
 337         },
 338         'playlist_mincount': 133,
 339     }]
 340
 341     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'