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         self._sort_formats(formats)
  85         return formats
  86
  87     def _download_and_extract_formats(self, video_id, query=None):
  88         return self._extract_formats(
  89             self._download_api_options(video_id, query=query), video_id)
  90
  91
  92 class RutubeIE(RutubeBaseIE):
  93     IE_NAME = 'rutube'
  94     IE_DESC = 'Rutube videos'
  95     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  96     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
  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     def _real_extract(self, url):
 132         video_id = self._match_id(url)
 133         info = self._download_and_extract_info(video_id)
 134         info['formats'] = self._download_and_extract_formats(video_id)
 135         return info
 136
 137
 138 class RutubeEmbedIE(RutubeBaseIE):
 139     IE_NAME = 'rutube:embed'
 140     IE_DESC = 'Rutube embedded videos'
 141     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 142
 143     _TESTS = [{
 144         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 145         'info_dict': {
 146             'id': 'a10e53b86e8f349080f718582ce4c661',
 147             'ext': 'mp4',
 148             'timestamp': 1387830582,
 149             'upload_date': '20131223',
 150             'uploader_id': '297833',
 151             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 152             'uploader': 'subziro89 ILya',
 153             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 154         },
 155         'params': {
 156             'skip_download': True,
 157         },
 158     }, {
 159         'url': 'http://rutube.ru/play/embed/8083783',
 160         'only_matching': True,
 161     }, {
 162         # private video
 163         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 164         'only_matching': True,
 165     }]
 166
 167     def _real_extract(self, url):
 168         embed_id = self._match_id(url)
 169         # Query may contain private videos token and should be passed to API
 170         # requests (see #19163)
 171         query = parse_qs(url)
 172         options = self._download_api_options(embed_id, query)
 173         video_id = options['effective_video']
 174         formats = self._extract_formats(options, video_id)
 175         info = self._download_and_extract_info(video_id, query)
 176         info.update({
 177             'extractor_key': 'Rutube',
 178             'formats': formats,
 179         })
 180         return info
 181
 182
 183 class RutubePlaylistBaseIE(RutubeBaseIE):
 184     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 185         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 186
 187     def _entries(self, playlist_id, *args, **kwargs):
 188         next_page_url = None
 189         for pagenum in itertools.count(1):
 190             page = self._download_json(
 191                 next_page_url or self._next_page_url(
 192                     pagenum, playlist_id, *args, **kwargs),
 193                 playlist_id, 'Downloading page %s' % pagenum)
 194
 195             results = page.get('results')
 196             if not results or not isinstance(results, list):
 197                 break
 198
 199             for result in results:
 200                 video_url = url_or_none(result.get('video_url'))
 201                 if not video_url:
 202                     continue
 203                 entry = self._extract_info(result, require_title=False)
 204                 entry.update({
 205                     '_type': 'url',
 206                     'url': video_url,
 207                     'ie_key': RutubeIE.ie_key(),
 208                 })
 209                 yield entry
 210
 211             next_page_url = page.get('next')
 212             if not next_page_url or not page.get('has_next'):
 213                 break
 214
 215     def _extract_playlist(self, playlist_id, *args, **kwargs):
 216         return self.playlist_result(
 217             self._entries(playlist_id, *args, **kwargs),
 218             playlist_id, kwargs.get('playlist_name'))
 219
 220     def _real_extract(self, url):
 221         return self._extract_playlist(self._match_id(url))
 222
 223
 224 class RutubeTagsIE(RutubePlaylistBaseIE):
 225     IE_NAME = 'rutube:tags'
 226     IE_DESC = 'Rutube tags'
 227     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 228     _TESTS = [{
 229         'url': 'http://rutube.ru/tags/video/1800/',
 230         'info_dict': {
 231             'id': '1800',
 232         },
 233         'playlist_mincount': 68,
 234     }]
 235
 236     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 237
 238
 239 class RutubeMovieIE(RutubePlaylistBaseIE):
 240     IE_NAME = 'rutube:movie'
 241     IE_DESC = 'Rutube movies'
 242     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 243
 244     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 245     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 246
 247     def _real_extract(self, url):
 248         movie_id = self._match_id(url)
 249         movie = self._download_json(
 250             self._MOVIE_TEMPLATE % movie_id, movie_id,
 251             'Downloading movie JSON')
 252         return self._extract_playlist(
 253             movie_id, playlist_name=movie.get('name'))
 254
 255
 256 class RutubePersonIE(RutubePlaylistBaseIE):
 257     IE_NAME = 'rutube:person'
 258     IE_DESC = 'Rutube person videos'
 259     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 260     _TESTS = [{
 261         'url': 'http://rutube.ru/video/person/313878/',
 262         'info_dict': {
 263             'id': '313878',
 264         },
 265         'playlist_mincount': 37,
 266     }]
 267
 268     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 269
 270
 271 class RutubePlaylistIE(RutubePlaylistBaseIE):
 272     IE_NAME = 'rutube:playlist'
 273     IE_DESC = 'Rutube playlists'
 274     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 275     _TESTS = [{
 276         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 277         'info_dict': {
 278             'id': '3097',
 279         },
 280         'playlist_count': 27,
 281     }, {
 282         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 283         'only_matching': True,
 284     }]
 285
 286     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 287
 288     @classmethod
 289     def suitable(cls, url):
 290         from ..utils import int_or_none, parse_qs
 291
 292         if not super(RutubePlaylistIE, cls).suitable(url):
 293             return False
 294         params = parse_qs(url)
 295         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 296
 297     def _next_page_url(self, page_num, playlist_id, item_kind):
 298         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 299
 300     def _real_extract(self, url):
 301         qs = parse_qs(url)
 302         playlist_kind = qs['pl_type'][0]
 303         playlist_id = qs['pl_id'][0]
 304         return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 305
 306
 307 class RutubeChannelIE(RutubePlaylistBaseIE):
 308     IE_NAME = 'rutube:channel'
 309     IE_DESC = 'Rutube channel'
 310     _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
 311     _TESTS = [{
 312         'url': 'https://rutube.ru/channel/639184/videos/',
 313         'info_dict': {
 314             'id': '639184',
 315         },
 316         'playlist_mincount': 133,
 317     }]
 318
 319     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'