Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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     compat_parse_qs,
  11     compat_urllib_parse_urlparse,
  12 )
  13 from ..utils import (
  14     determine_ext,
  15     bool_or_none,
  16     int_or_none,
  17     try_get,
  18     unified_timestamp,
  19     url_or_none,
  20 )
  21
  22
  23 class RutubeBaseIE(InfoExtractor):
  24     def _download_api_info(self, video_id, query=None):
  25         if not query:
  26             query = {}
  27         query['format'] = 'json'
  28         return self._download_json(
  29             'http://rutube.ru/api/video/%s/' % video_id,
  30             video_id, 'Downloading video JSON',
  31             'Unable to download video JSON', query=query)
  32
  33     @staticmethod
  34     def _extract_info(video, video_id=None, require_title=True):
  35         title = video['title'] if require_title else video.get('title')
  36
  37         age_limit = video.get('is_adult')
  38         if age_limit is not None:
  39             age_limit = 18 if age_limit is True else 0
  40
  41         uploader_id = try_get(video, lambda x: x['author']['id'])
  42         category = try_get(video, lambda x: x['category']['name'])
  43
  44         return {
  45             'id': video.get('id') or video_id if video_id else video['id'],
  46             'title': title,
  47             'description': video.get('description'),
  48             'thumbnail': video.get('thumbnail_url'),
  49             'duration': int_or_none(video.get('duration')),
  50             'uploader': try_get(video, lambda x: x['author']['name']),
  51             'uploader_id': compat_str(uploader_id) if uploader_id else None,
  52             'timestamp': unified_timestamp(video.get('created_ts')),
  53             'category': [category] if category else None,
  54             'age_limit': age_limit,
  55             'view_count': int_or_none(video.get('hits')),
  56             'comment_count': int_or_none(video.get('comments_count')),
  57             'is_live': bool_or_none(video.get('is_livestream')),
  58         }
  59
  60     def _download_and_extract_info(self, video_id, query=None):
  61         return self._extract_info(
  62             self._download_api_info(video_id, query=query), video_id)
  63
  64     def _download_api_options(self, video_id, query=None):
  65         if not query:
  66             query = {}
  67         query['format'] = 'json'
  68         return self._download_json(
  69             'http://rutube.ru/api/play/options/%s/' % video_id,
  70             video_id, 'Downloading options JSON',
  71             'Unable to download options JSON',
  72             headers=self.geo_verification_headers(), query=query)
  73
  74     def _extract_formats(self, options, video_id):
  75         formats = []
  76         for format_id, format_url in options['video_balancer'].items():
  77             ext = determine_ext(format_url)
  78             if ext == 'm3u8':
  79                 formats.extend(self._extract_m3u8_formats(
  80                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  81             elif ext == 'f4m':
  82                 formats.extend(self._extract_f4m_formats(
  83                     format_url, video_id, f4m_id=format_id, fatal=False))
  84             else:
  85                 formats.append({
  86                     'url': format_url,
  87                     'format_id': format_id,
  88                 })
  89         self._sort_formats(formats)
  90         return formats
  91
  92     def _download_and_extract_formats(self, video_id, query=None):
  93         return self._extract_formats(
  94             self._download_api_options(video_id, query=query), video_id)
  95
  96
  97 class RutubeIE(RutubeBaseIE):
  98     IE_NAME = 'rutube'
  99     IE_DESC = 'Rutube videos'
 100     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
 101
 102     _TESTS = [{
 103         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 104         'md5': '1d24f180fac7a02f3900712e5a5764d6',
 105         'info_dict': {
 106             'id': '3eac3b4561676c17df9132a9a1e62e3e',
 107             'ext': 'mp4',
 108             'title': 'Раненный кенгуру забежал в аптеку',
 109             'description': 'http://www.ntdtv.ru ',
 110             'duration': 81,
 111             'uploader': 'NTDRussian',
 112             'uploader_id': '29790',
 113             'timestamp': 1381943602,
 114             'upload_date': '20131016',
 115             'age_limit': 0,
 116         },
 117     }, {
 118         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
 119         'only_matching': True,
 120     }, {
 121         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
 122         'only_matching': True,
 123     }, {
 124         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
 125         'only_matching': True,
 126     }, {
 127         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
 128         'only_matching': True,
 129     }]
 130
 131     @classmethod
 132     def suitable(cls, url):
 133         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 134
 135     @staticmethod
 136     def _extract_urls(webpage):
 137         return [mobj.group('url') for mobj in re.finditer(
 138             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
 139             webpage)]
 140
 141     def _real_extract(self, url):
 142         video_id = self._match_id(url)
 143         info = self._download_and_extract_info(video_id)
 144         info['formats'] = self._download_and_extract_formats(video_id)
 145         return info
 146
 147
 148 class RutubeEmbedIE(RutubeBaseIE):
 149     IE_NAME = 'rutube:embed'
 150     IE_DESC = 'Rutube embedded videos'
 151     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 152
 153     _TESTS = [{
 154         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 155         'info_dict': {
 156             'id': 'a10e53b86e8f349080f718582ce4c661',
 157             'ext': 'mp4',
 158             'timestamp': 1387830582,
 159             'upload_date': '20131223',
 160             'uploader_id': '297833',
 161             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 162             'uploader': 'subziro89 ILya',
 163             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 164         },
 165         'params': {
 166             'skip_download': True,
 167         },
 168     }, {
 169         'url': 'http://rutube.ru/play/embed/8083783',
 170         'only_matching': True,
 171     }, {
 172         # private video
 173         'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
 174         'only_matching': True,
 175     }]
 176
 177     def _real_extract(self, url):
 178         embed_id = self._match_id(url)
 179         # Query may contain private videos token and should be passed to API
 180         # requests (see #19163)
 181         query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
 182         options = self._download_api_options(embed_id, query)
 183         video_id = options['effective_video']
 184         formats = self._extract_formats(options, video_id)
 185         info = self._download_and_extract_info(video_id, query)
 186         info.update({
 187             'extractor_key': 'Rutube',
 188             'formats': formats,
 189         })
 190         return info
 191
 192
 193 class RutubePlaylistBaseIE(RutubeBaseIE):
 194     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 195         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 196
 197     def _entries(self, playlist_id, *args, **kwargs):
 198         next_page_url = None
 199         for pagenum in itertools.count(1):
 200             page = self._download_json(
 201                 next_page_url or self._next_page_url(
 202                     pagenum, playlist_id, *args, **kwargs),
 203                 playlist_id, 'Downloading page %s' % pagenum)
 204
 205             results = page.get('results')
 206             if not results or not isinstance(results, list):
 207                 break
 208
 209             for result in results:
 210                 video_url = url_or_none(result.get('video_url'))
 211                 if not video_url:
 212                     continue
 213                 entry = self._extract_info(result, require_title=False)
 214                 entry.update({
 215                     '_type': 'url',
 216                     'url': video_url,
 217                     'ie_key': RutubeIE.ie_key(),
 218                 })
 219                 yield entry
 220
 221             next_page_url = page.get('next')
 222             if not next_page_url or not page.get('has_next'):
 223                 break
 224
 225     def _extract_playlist(self, playlist_id, *args, **kwargs):
 226         return self.playlist_result(
 227             self._entries(playlist_id, *args, **kwargs),
 228             playlist_id, kwargs.get('playlist_name'))
 229
 230     def _real_extract(self, url):
 231         return self._extract_playlist(self._match_id(url))
 232
 233
 234 class RutubeChannelIE(RutubePlaylistBaseIE):
 235     IE_NAME = 'rutube:channel'
 236     IE_DESC = 'Rutube channels'
 237     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 238     _TESTS = [{
 239         'url': 'http://rutube.ru/tags/video/1800/',
 240         'info_dict': {
 241             'id': '1800',
 242         },
 243         'playlist_mincount': 68,
 244     }]
 245
 246     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 247
 248
 249 class RutubeMovieIE(RutubePlaylistBaseIE):
 250     IE_NAME = 'rutube:movie'
 251     IE_DESC = 'Rutube movies'
 252     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 253     _TESTS = []
 254
 255     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 256     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 257
 258     def _real_extract(self, url):
 259         movie_id = self._match_id(url)
 260         movie = self._download_json(
 261             self._MOVIE_TEMPLATE % movie_id, movie_id,
 262             'Downloading movie JSON')
 263         return self._extract_playlist(
 264             movie_id, playlist_name=movie.get('name'))
 265
 266
 267 class RutubePersonIE(RutubePlaylistBaseIE):
 268     IE_NAME = 'rutube:person'
 269     IE_DESC = 'Rutube person videos'
 270     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 271     _TESTS = [{
 272         'url': 'http://rutube.ru/video/person/313878/',
 273         'info_dict': {
 274             'id': '313878',
 275         },
 276         'playlist_mincount': 37,
 277     }]
 278
 279     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 280
 281
 282 class RutubePlaylistIE(RutubePlaylistBaseIE):
 283     IE_NAME = 'rutube:playlist'
 284     IE_DESC = 'Rutube playlists'
 285     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 286     _TESTS = [{
 287         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 288         'info_dict': {
 289             'id': '3097',
 290         },
 291         'playlist_count': 27,
 292     }, {
 293         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 294         'only_matching': True,
 295     }]
 296
 297     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 298
 299     @classmethod
 300     def suitable(cls, url):
 301         if not super(RutubePlaylistIE, cls).suitable(url):
 302             return False
 303         params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
 304         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 305
 306     def _next_page_url(self, page_num, playlist_id, item_kind):
 307         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 308
 309     def _real_extract(self, url):
 310         qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
 311         playlist_kind = qs['pl_type'][0]
 312         playlist_id = qs['pl_id'][0]
 313         return self._extract_playlist(playlist_id, item_kind=playlist_kind)