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                 m3u8_formats = self._extract_m3u8_formats(
  62                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
  63                 if m3u8_formats:
  64                     formats.extend(m3u8_formats)
  65             elif ext == 'f4m':
  66                 f4m_formats = self._extract_f4m_formats(
  67                     format_url, video_id, f4m_id=format_id, fatal=False)
  68                 if f4m_formats:
  69                     formats.extend(f4m_formats)
  70             else:
  71                 formats.append({
  72                     'url': format_url,
  73                     'format_id': format_id,
  74                 })
  75         self._sort_formats(formats)
  76
  77         return {
  78             'id': video['id'],
  79             'title': video['title'],
  80             'description': video['description'],
  81             'duration': video['duration'],
  82             'view_count': video['hits'],
  83             'formats': formats,
  84             'thumbnail': video['thumbnail_url'],
  85             'uploader': author.get('name'),
  86             'uploader_id': compat_str(author['id']) if author else None,
  87             'upload_date': unified_strdate(video['created_ts']),
  88             'age_limit': 18 if video['is_adult'] else 0,
  89         }
  90
  91
  92 class RutubeEmbedIE(InfoExtractor):
  93     IE_NAME = 'rutube:embed'
  94     IE_DESC = 'Rutube embedded videos'
  95     _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
  96
  97     _TESTS = [{
  98         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
  99         'info_dict': {
 100             'id': 'a10e53b86e8f349080f718582ce4c661',
 101             'ext': 'mp4',
 102             'upload_date': '20131223',
 103             'uploader_id': '297833',
 104             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 105             'uploader': 'subziro89 ILya',
 106             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 107         },
 108         'params': {
 109             'skip_download': 'Requires ffmpeg',
 110         },
 111     }, {
 112         'url': 'http://rutube.ru/play/embed/8083783',
 113         'only_matching': True,
 114     }]
 115
 116     def _real_extract(self, url):
 117         embed_id = self._match_id(url)
 118         webpage = self._download_webpage(url, embed_id)
 119
 120         canonical_url = self._html_search_regex(
 121             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 122             'Canonical URL')
 123         return self.url_result(canonical_url, 'Rutube')
 124
 125
 126 class RutubeChannelIE(InfoExtractor):
 127     IE_NAME = 'rutube:channel'
 128     IE_DESC = 'Rutube channels'
 129     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
 130     _TESTS = [{
 131         'url': 'http://rutube.ru/tags/video/1800/',
 132         'info_dict': {
 133             'id': '1800',
 134         },
 135         'playlist_mincount': 68,
 136     }]
 137
 138     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 139
 140     def _extract_videos(self, channel_id, channel_title=None):
 141         entries = []
 142         for pagenum in itertools.count(1):
 143             page = self._download_json(
 144                 self._PAGE_TEMPLATE % (channel_id, pagenum),
 145                 channel_id, 'Downloading page %s' % pagenum)
 146             results = page['results']
 147             if not results:
 148                 break
 149             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
 150             if not page['has_next']:
 151                 break
 152         return self.playlist_result(entries, channel_id, channel_title)
 153
 154     def _real_extract(self, url):
 155         mobj = re.match(self._VALID_URL, url)
 156         channel_id = mobj.group('id')
 157         return self._extract_videos(channel_id)
 158
 159
 160 class RutubeMovieIE(RutubeChannelIE):
 161     IE_NAME = 'rutube:movie'
 162     IE_DESC = 'Rutube movies'
 163     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 164     _TESTS = []
 165
 166     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 167     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 168
 169     def _real_extract(self, url):
 170         movie_id = self._match_id(url)
 171         movie = self._download_json(
 172             self._MOVIE_TEMPLATE % movie_id, movie_id,
 173             'Downloading movie JSON')
 174         movie_name = movie['name']
 175         return self._extract_videos(movie_id, movie_name)
 176
 177
 178 class RutubePersonIE(RutubeChannelIE):
 179     IE_NAME = 'rutube:person'
 180     IE_DESC = 'Rutube person videos'
 181     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 182     _TESTS = [{
 183         'url': 'http://rutube.ru/video/person/313878/',
 184         'info_dict': {
 185             'id': '313878',
 186         },
 187         'playlist_mincount': 37,
 188     }]
 189
 190     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'