Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rutube.py

   1 # encoding: 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     unified_strdate,
  14 )
  15
  16
  17 class RutubeIE(InfoExtractor):
  18     IE_NAME = 'rutube'
  19     IE_DESC = 'Rutube videos'
  20     _VALID_URL = r'https?://rutube\.ru/(?:video|play/embed)/(?P<id>[\da-z]{32})'
  21
  22     _TESTS = [{
  23         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
  24         'info_dict': {
  25             'id': '3eac3b4561676c17df9132a9a1e62e3e',
  26             'ext': 'mp4',
  27             'title': 'Раненный кенгуру забежал в аптеку',
  28             'description': 'http://www.ntdtv.ru ',
  29             'duration': 80,
  30             'uploader': 'NTDRussian',
  31             'uploader_id': '29790',
  32             'upload_date': '20131016',
  33             'age_limit': 0,
  34         },
  35         'params': {
  36             # It requires ffmpeg (m3u8 download)
  37             'skip_download': True,
  38         },
  39     }, {
  40         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         video = self._download_json(
  47             'http://rutube.ru/api/video/%s/?format=json' % video_id,
  48             video_id, 'Downloading video JSON')
  49
  50         # Some videos don't have the author field
  51         author = video.get('author') or {}
  52
  53         options = self._download_json(
  54             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
  55             video_id, 'Downloading options JSON')
  56
  57         formats = []
  58         for format_id, format_url in options['video_balancer'].items():
  59             ext = determine_ext(format_url)
  60             if ext == 'm3u8':
  61                 formats.extend(self._extract_m3u8_formats(
  62                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  63             elif ext == 'f4m':
  64                 formats.extend(self._extract_f4m_formats(
  65                     format_url, video_id, f4m_id=format_id, fatal=False))
  66             else:
  67                 formats.append({
  68                     'url': format_url,
  69                     'format_id': format_id,
  70                 })
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video['id'],
  75             'title': video['title'],
  76             'description': video['description'],
  77             'duration': video['duration'],
  78             'view_count': video['hits'],
  79             'formats': formats,
  80             'thumbnail': video['thumbnail_url'],
  81             'uploader': author.get('name'),
  82             'uploader_id': compat_str(author['id']) if author else None,
  83             'upload_date': unified_strdate(video['created_ts']),
  84             'age_limit': 18 if video['is_adult'] else 0,
  85         }
  86
  87
  88 class RutubeEmbedIE(InfoExtractor):
  89     IE_NAME = 'rutube:embed'
  90     IE_DESC = 'Rutube embedded videos'
  91     _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
  92
  93     _TESTS = [{
  94         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
  95         'info_dict': {
  96             'id': 'a10e53b86e8f349080f718582ce4c661',
  97             'ext': 'mp4',
  98             'upload_date': '20131223',
  99             'uploader_id': '297833',
 100             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 101             'uploader': 'subziro89 ILya',
 102             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 103         },
 104         'params': {
 105             'skip_download': 'Requires ffmpeg',
 106         },
 107     }, {
 108         'url': 'http://rutube.ru/play/embed/8083783',
 109         'only_matching': True,
 110     }]
 111
 112     def _real_extract(self, url):
 113         embed_id = self._match_id(url)
 114         webpage = self._download_webpage(url, embed_id)
 115
 116         canonical_url = self._html_search_regex(
 117             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 118             'Canonical URL')
 119         return self.url_result(canonical_url, 'Rutube')
 120
 121
 122 class RutubeChannelIE(InfoExtractor):
 123     IE_NAME = 'rutube:channel'
 124     IE_DESC = 'Rutube channels'
 125     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
 126     _TESTS = [{
 127         'url': 'http://rutube.ru/tags/video/1800/',
 128         'info_dict': {
 129             'id': '1800',
 130         },
 131         'playlist_mincount': 68,
 132     }]
 133
 134     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 135
 136     def _extract_videos(self, channel_id, channel_title=None):
 137         entries = []
 138         for pagenum in itertools.count(1):
 139             page = self._download_json(
 140                 self._PAGE_TEMPLATE % (channel_id, pagenum),
 141                 channel_id, 'Downloading page %s' % pagenum)
 142             results = page['results']
 143             if not results:
 144                 break
 145             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
 146             if not page['has_next']:
 147                 break
 148         return self.playlist_result(entries, channel_id, channel_title)
 149
 150     def _real_extract(self, url):
 151         mobj = re.match(self._VALID_URL, url)
 152         channel_id = mobj.group('id')
 153         return self._extract_videos(channel_id)
 154
 155
 156 class RutubeMovieIE(RutubeChannelIE):
 157     IE_NAME = 'rutube:movie'
 158     IE_DESC = 'Rutube movies'
 159     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 160     _TESTS = []
 161
 162     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 163     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 164
 165     def _real_extract(self, url):
 166         movie_id = self._match_id(url)
 167         movie = self._download_json(
 168             self._MOVIE_TEMPLATE % movie_id, movie_id,
 169             'Downloading movie JSON')
 170         movie_name = movie['name']
 171         return self._extract_videos(movie_id, movie_name)
 172
 173
 174 class RutubePersonIE(RutubeChannelIE):
 175     IE_NAME = 'rutube:person'
 176     IE_DESC = 'Rutube person videos'
 177     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 178     _TESTS = [{
 179         'url': 'http://rutube.ru/video/person/313878/',
 180         'info_dict': {
 181             'id': '313878',
 182         },
 183         'playlist_mincount': 37,
 184     }]
 185
 186     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'