yt_dlp/extractor/rutube.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import itertools
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_str,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     bool_or_none,
  14     int_or_none,
  15     parse_qs,
  16     try_get,
  17     unified_timestamp,
  18     url_or_none,
  19 )
  20
  21
  22 class RutubeBaseIE(InfoExtractor):
  23     def _download_api_info(self, video_id, query=None):
  24         if not query:
  25             query = {}
  26         query['format'] = 'json'
  27         return self._download_json(
  28             'http://rutube.ru/api/video/%s/' % video_id,
  29             video_id, 'Downloading video JSON',
  30             'Unable to download video JSON', query=query)
  31
  32     @staticmethod
  33     def _extract_info(video, video_id=None, require_title=True):
  34         title = video['title'] if require_title else video.get('title')
  35
  36         age_limit = video.get('is_adult')
  37         if age_limit is not None:
  38             age_limit = 18 if age_limit is True else 0
  39
  40         uploader_id = try_get(video, lambda x: x['author']['id'])
  41         category = try_get(video, lambda x: x['category']['name'])
  42
  43         return {
  44             'id': video.get('id') or video_id if video_id else video['id'],
  45             'title': title,
  46             'description': video.get('description'),
  47             'thumbnail': video.get('thumbnail_url'),
  48             'duration': int_or_none(video.get('duration')),
  49             'uploader': try_get(video, lambda x: x['author']['name']),
  50             'uploader_id': compat_str(uploader_id) if uploader_id else None,
  51             'timestamp': unified_timestamp(video.get('created_ts')),
  52             'category': [category] if category else None,
  53             'age_limit': age_limit,
  54             'view_count': int_or_none(video.get('hits')),
  55             'comment_count': int_or_none(video.get('comments_count')),
  56             'is_live': bool_or_none(video.get('is_livestream')),
  57         }
  58
  59     def _download_and_extract_info(self, video_id, query=None):
  60         return self._extract_info(
  61             self._download_api_info(video_id, query=query), video_id)
  62
  63     def _download_api_options(self, video_id, query=None):
  64         if not query:
  65             query = {}
  66         query['format'] = 'json'
  67         return self._download_json(
  68             'http://rutube.ru/api/play/options/%s/' % video_id,
  69             video_id, 'Downloading options JSON',
  70             'Unable to download options JSON',
  71             headers=self.geo_verification_headers(), query=query)
  72
  73     def _extract_formats(self, options, video_id):
  74         formats = []
  75         for format_id, format_url in options['video_balancer'].items():
  76             ext = determine_ext(format_url)
  77             if ext == 'm3u8':
  78                 formats.extend(self._extract_m3u8_formats(
  79                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  80             elif ext == 'f4m':
  81                 formats.extend(self._extract_f4m_formats(
  82                     format_url, video_id, f4m_id=format_id, fatal=False))
  83             else:
  84                 formats.append({
  85                     'url': format_url,
  86                     'format_id': format_id,
  87                 })
  88         self._sort_formats(formats)
  89         return formats
  90
  91     def _download_and_extract_formats(self, video_id, query=None):
  92         return self._extract_formats(
  93             self._download_api_options(video_id, query=query), video_id)
  94
  95
  96 class RutubeIE(RutubeBaseIE):
  97     IE_NAME = 'rutube'
  98     IE_DESC = 'Rutube videos'
  99     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
 100
 101     _TESTS = [{
 102         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 103         'md5': '1d24f180fac7a02f3900712e5a5764d6',
 104         'info_dict': {
 105             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 106             'ext': 'mp4',
 107             'title': 'Раненный кенгуру забежал в аптеку',
 108             'description': 'http://www.ntdtv.ru ',
 109             'duration': 81,
 110             'uploader': 'NTDRussian',
 111             'uploader_id': '29790',
 112             'timestamp': 1381943602,
 113             'upload_date': '20131016',
 114             'age_limit': 0,
 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
 130     @classmethod
 131     def suitable(cls, url):
 132         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 133
 134     @staticmethod
 135     def _extract_urls(webpage):
 136         return [mobj.group('url') for mobj in re.finditer(
 137             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
 138             webpage)]
 139
 140     def _real_extract(self, url):
 141         video_id = self._match_id(url)
 142         info = self._download_and_extract_info(video_id)
 143         info['formats'] = self._download_and_extract_formats(video_id)
 144         return info
 145
 146
 147 class RutubeEmbedIE(RutubeBaseIE):
 148     IE_NAME = 'rutube:embed'
 149     IE_DESC = 'Rutube embedded videos'
 150     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 151
 152     _TESTS = [{
 153         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 154         'info_dict': {
 155             'id': 'a10e53b86e8f349080f718582ce4c661',
 156             'ext': 'mp4',
 157             'timestamp': 1387830582,
 158             'upload_date': '20131223',
 159             'uploader_id': '297833',
 160             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 161             'uploader': 'subziro89 ILya',
 162             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 163         },
 164         'params': {
 165             'skip_download': True,
 166         },
 167     }, {
 168         'url': 'http://rutube.ru/play/embed/8083783',
 169         'only_matching': True,
 170     }, {
 171         # private video
 172         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 173         'only_matching': True,
 174     }]
 175
 176     def _real_extract(self, url):
 177         embed_id = self._match_id(url)
 178         # Query may contain private videos token and should be passed to API
 179         # requests (see #19163)
 180         query = parse_qs(url)
 181         options = self._download_api_options(embed_id, query)
 182         video_id = options['effective_video']
 183         formats = self._extract_formats(options, video_id)
 184         info = self._download_and_extract_info(video_id, query)
 185         info.update({
 186             'extractor_key': 'Rutube',
 187             'formats': formats,
 188         })
 189         return info
 190
 191
 192 class RutubePlaylistBaseIE(RutubeBaseIE):
 193     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 194         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 195
 196     def _entries(self, playlist_id, *args, **kwargs):
 197         next_page_url = None
 198         for pagenum in itertools.count(1):
 199             page = self._download_json(
 200                 next_page_url or self._next_page_url(
 201                     pagenum, playlist_id, *args, **kwargs),
 202                 playlist_id, 'Downloading page %s' % pagenum)
 203
 204             results = page.get('results')
 205             if not results or not isinstance(results, list):
 206                 break
 207
 208             for result in results:
 209                 video_url = url_or_none(result.get('video_url'))
 210                 if not video_url:
 211                     continue
 212                 entry = self._extract_info(result, require_title=False)
 213                 entry.update({
 214                     '_type': 'url',
 215                     'url': video_url,
 216                     'ie_key': RutubeIE.ie_key(),
 217                 })
 218                 yield entry
 219
 220             next_page_url = page.get('next')
 221             if not next_page_url or not page.get('has_next'):
 222                 break
 223
 224     def _extract_playlist(self, playlist_id, *args, **kwargs):
 225         return self.playlist_result(
 226             self._entries(playlist_id, *args, **kwargs),
 227             playlist_id, kwargs.get('playlist_name'))
 228
 229     def _real_extract(self, url):
 230         return self._extract_playlist(self._match_id(url))
 231
 232
 233 class RutubeChannelIE(RutubePlaylistBaseIE):
 234     IE_NAME = 'rutube:channel'
 235     IE_DESC = 'Rutube channels'
 236     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 237     _TESTS = [{
 238         'url': 'http://rutube.ru/tags/video/1800/',
 239         'info_dict': {
 240             'id': '1800',
 241         },
 242         'playlist_mincount': 68,
 243     }]
 244
 245     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 246
 247
 248 class RutubeMovieIE(RutubePlaylistBaseIE):
 249     IE_NAME = 'rutube:movie'
 250     IE_DESC = 'Rutube movies'
 251     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 252     _TESTS = []
 253
 254     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 255     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 256
 257     def _real_extract(self, url):
 258         movie_id = self._match_id(url)
 259         movie = self._download_json(
 260             self._MOVIE_TEMPLATE % movie_id, movie_id,
 261             'Downloading movie JSON')
 262         return self._extract_playlist(
 263             movie_id, playlist_name=movie.get('name'))
 264
 265
 266 class RutubePersonIE(RutubePlaylistBaseIE):
 267     IE_NAME = 'rutube:person'
 268     IE_DESC = 'Rutube person videos'
 269     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 270     _TESTS = [{
 271         'url': 'http://rutube.ru/video/person/313878/',
 272         'info_dict': {
 273             'id': '313878',
 274         },
 275         'playlist_mincount': 37,
 276     }]
 277
 278     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 279
 280
 281 class RutubePlaylistIE(RutubePlaylistBaseIE):
 282     IE_NAME = 'rutube:playlist'
 283     IE_DESC = 'Rutube playlists'
 284     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 285     _TESTS = [{
 286         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 287         'info_dict': {
 288             'id': '3097',
 289         },
 290         'playlist_count': 27,
 291     }, {
 292         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 293         'only_matching': True,
 294     }]
 295
 296     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 297
 298     @classmethod
 299     def suitable(cls, url):
 300         if not super(RutubePlaylistIE, cls).suitable(url):
 301             return False
 302         params = parse_qs(url)
 303         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 304
 305     def _next_page_url(self, page_num, playlist_id, item_kind):
 306         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 307
 308     def _real_extract(self, url):
 309         qs = parse_qs(url)
 310         playlist_kind = qs['pl_type'][0]
 311         playlist_id = qs['pl_id'][0]
 312         return self._extract_playlist(playlist_id, item_kind=playlist_kind)