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