yt_dlp/extractor/rutube.py

   1 import re
   2 import itertools
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_str,
   7 )
   8 from ..utils import (
   9     determine_ext,
  10     bool_or_none,
  11     int_or_none,
  12     parse_qs,
  13     try_get,
  14     unified_timestamp,
  15     url_or_none,
  16 )
  17
  18
  19 class RutubeBaseIE(InfoExtractor):
  20     def _download_api_info(self, video_id, query=None):
  21         if not query:
  22             query = {}
  23         query['format'] = 'json'
  24         return self._download_json(
  25             'http://rutube.ru/api/video/%s/' % video_id,
  26             video_id, 'Downloading video JSON',
  27             'Unable to download video JSON', query=query)
  28
  29     @staticmethod
  30     def _extract_info(video, video_id=None, require_title=True):
  31         title = video['title'] if require_title else video.get('title')
  32
  33         age_limit = video.get('is_adult')
  34         if age_limit is not None:
  35             age_limit = 18 if age_limit is True else 0
  36
  37         uploader_id = try_get(video, lambda x: x['author']['id'])
  38         category = try_get(video, lambda x: x['category']['name'])
  39
  40         return {
  41             'id': video.get('id') or video_id if video_id else video['id'],
  42             'title': title,
  43             'description': video.get('description'),
  44             'thumbnail': video.get('thumbnail_url'),
  45             'duration': int_or_none(video.get('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             'category': [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         }
  55
  56     def _download_and_extract_info(self, video_id, query=None):
  57         return self._extract_info(
  58             self._download_api_info(video_id, query=query), video_id)
  59
  60     def _download_api_options(self, video_id, query=None):
  61         if not query:
  62             query = {}
  63         query['format'] = 'json'
  64         return self._download_json(
  65             'http://rutube.ru/api/play/options/%s/' % video_id,
  66             video_id, 'Downloading options JSON',
  67             'Unable to download options JSON',
  68             headers=self.geo_verification_headers(), query=query)
  69
  70     def _extract_formats(self, options, video_id):
  71         formats = []
  72         for format_id, format_url in options['video_balancer'].items():
  73             ext = determine_ext(format_url)
  74             if ext == 'm3u8':
  75                 formats.extend(self._extract_m3u8_formats(
  76                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  77             elif ext == 'f4m':
  78                 formats.extend(self._extract_f4m_formats(
  79                     format_url, video_id, f4m_id=format_id, fatal=False))
  80             else:
  81                 formats.append({
  82                     'url': format_url,
  83                     'format_id': format_id,
  84                 })
  85         self._sort_formats(formats)
  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|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  97
  98     _TESTS = [{
  99         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 100         'md5': '1d24f180fac7a02f3900712e5a5764d6',
 101         'info_dict': {
 102             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 103             'ext': 'mp4',
 104             'title': 'Раненный кенгуру забежал в аптеку',
 105             'description': 'http://www.ntdtv.ru ',
 106             'duration': 81,
 107             'uploader': 'NTDRussian',
 108             'uploader_id': '29790',
 109             'timestamp': 1381943602,
 110             'upload_date': '20131016',
 111             'age_limit': 0,
 112         },
 113     }, {
 114         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
 115         'only_matching': True,
 116     }, {
 117         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
 118         'only_matching': True,
 119     }, {
 120         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
 121         'only_matching': True,
 122     }, {
 123         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
 124         'only_matching': True,
 125     }]
 126
 127     @classmethod
 128     def suitable(cls, url):
 129         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 130
 131     @staticmethod
 132     def _extract_urls(webpage):
 133         return [mobj.group('url') for mobj in re.finditer(
 134             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
 135             webpage)]
 136
 137     def _real_extract(self, url):
 138         video_id = self._match_id(url)
 139         info = self._download_and_extract_info(video_id)
 140         info['formats'] = self._download_and_extract_formats(video_id)
 141         return info
 142
 143
 144 class RutubeEmbedIE(RutubeBaseIE):
 145     IE_NAME = 'rutube:embed'
 146     IE_DESC = 'Rutube embedded videos'
 147     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 148
 149     _TESTS = [{
 150         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 151         'info_dict': {
 152             'id': 'a10e53b86e8f349080f718582ce4c661',
 153             'ext': 'mp4',
 154             'timestamp': 1387830582,
 155             'upload_date': '20131223',
 156             'uploader_id': '297833',
 157             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 158             'uploader': 'subziro89 ILya',
 159             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 160         },
 161         'params': {
 162             'skip_download': True,
 163         },
 164     }, {
 165         'url': 'http://rutube.ru/play/embed/8083783',
 166         'only_matching': True,
 167     }, {
 168         # private video
 169         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 170         'only_matching': True,
 171     }]
 172
 173     def _real_extract(self, url):
 174         embed_id = self._match_id(url)
 175         # Query may contain private videos token and should be passed to API
 176         # requests (see #19163)
 177         query = parse_qs(url)
 178         options = self._download_api_options(embed_id, query)
 179         video_id = options['effective_video']
 180         formats = self._extract_formats(options, video_id)
 181         info = self._download_and_extract_info(video_id, query)
 182         info.update({
 183             'extractor_key': 'Rutube',
 184             'formats': formats,
 185         })
 186         return info
 187
 188
 189 class RutubePlaylistBaseIE(RutubeBaseIE):
 190     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 191         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 192
 193     def _entries(self, playlist_id, *args, **kwargs):
 194         next_page_url = None
 195         for pagenum in itertools.count(1):
 196             page = self._download_json(
 197                 next_page_url or self._next_page_url(
 198                     pagenum, playlist_id, *args, **kwargs),
 199                 playlist_id, 'Downloading page %s' % pagenum)
 200
 201             results = page.get('results')
 202             if not results or not isinstance(results, list):
 203                 break
 204
 205             for result in results:
 206                 video_url = url_or_none(result.get('video_url'))
 207                 if not video_url:
 208                     continue
 209                 entry = self._extract_info(result, require_title=False)
 210                 entry.update({
 211                     '_type': 'url',
 212                     'url': video_url,
 213                     'ie_key': RutubeIE.ie_key(),
 214                 })
 215                 yield entry
 216
 217             next_page_url = page.get('next')
 218             if not next_page_url or not page.get('has_next'):
 219                 break
 220
 221     def _extract_playlist(self, playlist_id, *args, **kwargs):
 222         return self.playlist_result(
 223             self._entries(playlist_id, *args, **kwargs),
 224             playlist_id, kwargs.get('playlist_name'))
 225
 226     def _real_extract(self, url):
 227         return self._extract_playlist(self._match_id(url))
 228
 229
 230 class RutubeTagsIE(RutubePlaylistBaseIE):
 231     IE_NAME = 'rutube:tags'
 232     IE_DESC = 'Rutube tags'
 233     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 234     _TESTS = [{
 235         'url': 'http://rutube.ru/tags/video/1800/',
 236         'info_dict': {
 237             'id': '1800',
 238         },
 239         'playlist_mincount': 68,
 240     }]
 241
 242     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 243
 244
 245 class RutubeMovieIE(RutubePlaylistBaseIE):
 246     IE_NAME = 'rutube:movie'
 247     IE_DESC = 'Rutube movies'
 248     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 249     _TESTS = []
 250
 251     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 252     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 253
 254     def _real_extract(self, url):
 255         movie_id = self._match_id(url)
 256         movie = self._download_json(
 257             self._MOVIE_TEMPLATE % movie_id, movie_id,
 258             'Downloading movie JSON')
 259         return self._extract_playlist(
 260             movie_id, playlist_name=movie.get('name'))
 261
 262
 263 class RutubePersonIE(RutubePlaylistBaseIE):
 264     IE_NAME = 'rutube:person'
 265     IE_DESC = 'Rutube person videos'
 266     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 267     _TESTS = [{
 268         'url': 'http://rutube.ru/video/person/313878/',
 269         'info_dict': {
 270             'id': '313878',
 271         },
 272         'playlist_mincount': 37,
 273     }]
 274
 275     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 276
 277
 278 class RutubePlaylistIE(RutubePlaylistBaseIE):
 279     IE_NAME = 'rutube:playlist'
 280     IE_DESC = 'Rutube playlists'
 281     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 282     _TESTS = [{
 283         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 284         'info_dict': {
 285             'id': '3097',
 286         },
 287         'playlist_count': 27,
 288     }, {
 289         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 290         'only_matching': True,
 291     }]
 292
 293     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 294
 295     @classmethod
 296     def suitable(cls, url):
 297         from ..utils import int_or_none, parse_qs
 298
 299         if not super(RutubePlaylistIE, cls).suitable(url):
 300             return False
 301         params = parse_qs(url)
 302         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 303
 304     def _next_page_url(self, page_num, playlist_id, item_kind):
 305         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 306
 307     def _real_extract(self, url):
 308         qs = parse_qs(url)
 309         playlist_kind = qs['pl_type'][0]
 310         playlist_id = qs['pl_id'][0]
 311         return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 312
 313
 314 class RutubeChannelIE(RutubePlaylistBaseIE):
 315     IE_NAME = 'rutube:channel'
 316     IE_DESC = 'Rutube channel'
 317     _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
 318     _TESTS = [{
 319         'url': 'https://rutube.ru/channel/639184/videos/',
 320         'info_dict': {
 321             'id': '639184',
 322         },
 323         'playlist_mincount': 133,
 324     }]
 325
 326     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'