youtube_dl/extractor/rutv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none
  10 )
  11
  12
  13 class RUTVIE(InfoExtractor):
  14     IE_DESC = 'RUTV.RU'
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/
  18                         (?P<path>
  19                             flash\d+v/container\.swf\?id=|
  20                             iframe/(?P<type>swf|video|live)/id/|
  21                             index/iframe/cast_id/
  22                         )
  23                         (?P<id>\d+)
  24                     '''
  25
  26     _TESTS = [
  27         {
  28             'url': 'http://player.rutv.ru/flash2v/container.swf?id=774471&sid=kultura&fbv=true&isPlay=true&ssl=false&i=560&acc_video_id=episode_id/972347/video_id/978186/brand_id/31724',
  29             'info_dict': {
  30                 'id': '774471',
  31                 'ext': 'mp4',
  32                 'title': 'Монологи на все времена',
  33                 'description': 'md5:18d8b5e6a41fb1faa53819471852d5d5',
  34                 'duration': 2906,
  35             },
  36             'params': {
  37                 # m3u8 download
  38                 'skip_download': True,
  39             },
  40         },
  41         {
  42             'url': 'https://player.vgtrk.com/flash2v/container.swf?id=774016&sid=russiatv&fbv=true&isPlay=true&ssl=false&i=560&acc_video_id=episode_id/972098/video_id/977760/brand_id/57638',
  43             'info_dict': {
  44                 'id': '774016',
  45                 'ext': 'mp4',
  46                 'title': 'Чужой в семье Сталина',
  47                 'description': '',
  48                 'duration': 2539,
  49             },
  50             'params': {
  51                 # m3u8 download
  52                 'skip_download': True,
  53             },
  54         },
  55         {
  56             'url': 'http://player.rutv.ru/iframe/swf/id/766888/sid/hitech/?acc_video_id=4000',
  57             'info_dict': {
  58                 'id': '766888',
  59                 'ext': 'mp4',
  60                 'title': 'Вести.net: интернет-гиганты начали перетягивание программных "одеял"',
  61                 'description': 'md5:65ddd47f9830c4f42ed6475f8730c995',
  62                 'duration': 279,
  63             },
  64             'params': {
  65                 # m3u8 download
  66                 'skip_download': True,
  67             },
  68         },
  69         {
  70             'url': 'http://player.rutv.ru/iframe/video/id/771852/start_zoom/true/showZoomBtn/false/sid/russiatv/?acc_video_id=episode_id/970443/video_id/975648/brand_id/5169',
  71             'info_dict': {
  72                 'id': '771852',
  73                 'ext': 'mp4',
  74                 'title': 'Прямой эфир. Жертвы загадочной болезни: смерть от старости в 17 лет',
  75                 'description': 'md5:b81c8c55247a4bd996b43ce17395b2d8',
  76                 'duration': 3096,
  77             },
  78             'params': {
  79                 # m3u8 download
  80                 'skip_download': True,
  81             },
  82         },
  83         {
  84             'url': 'http://player.rutv.ru/iframe/live/id/51499/showZoomBtn/false/isPlay/true/sid/sochi2014',
  85             'info_dict': {
  86                 'id': '51499',
  87                 'ext': 'flv',
  88                 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
  89                 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
  90             },
  91             'skip': 'Translation has finished',
  92         },
  93         {
  94             'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
  95             'info_dict': {
  96                 'id': '21',
  97                 'ext': 'mp4',
  98                 'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  99                 'is_live': True,
 100             },
 101             'params': {
 102                 # m3u8 download
 103                 'skip_download': True,
 104             },
 105         },
 106         {
 107             'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/',
 108             'only_matching': True,
 109         },
 110     ]
 111
 112     @classmethod
 113     def _extract_url(cls, webpage):
 114         mobj = re.search(
 115             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
 116         if mobj:
 117             return mobj.group('url')
 118
 119         mobj = re.search(
 120             r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
 121             webpage)
 122         if mobj:
 123             return mobj.group('url')
 124
 125     def _real_extract(self, url):
 126         mobj = re.match(self._VALID_URL, url)
 127         video_id = mobj.group('id')
 128         video_path = mobj.group('path')
 129
 130         if re.match(r'flash\d+v', video_path):
 131             video_type = 'video'
 132         elif video_path.startswith('iframe'):
 133             video_type = mobj.group('type')
 134             if video_type == 'swf':
 135                 video_type = 'video'
 136         elif video_path.startswith('index/iframe/cast_id'):
 137             video_type = 'live'
 138
 139         is_live = video_type == 'live'
 140
 141         json_data = self._download_json(
 142             'http://player.rutv.ru/iframe/data%s/id/%s' % ('live' if is_live else 'video', video_id),
 143             video_id, 'Downloading JSON')
 144
 145         if json_data['errors']:
 146             raise ExtractorError('%s said: %s' % (self.IE_NAME, json_data['errors']), expected=True)
 147
 148         playlist = json_data['data']['playlist']
 149         medialist = playlist['medialist']
 150         media = medialist[0]
 151
 152         if media['errors']:
 153             raise ExtractorError('%s said: %s' % (self.IE_NAME, media['errors']), expected=True)
 154
 155         view_count = playlist.get('count_views')
 156         priority_transport = playlist['priority_transport']
 157
 158         thumbnail = media['picture']
 159         width = int_or_none(media['width'])
 160         height = int_or_none(media['height'])
 161         description = media['anons']
 162         title = media['title']
 163         duration = int_or_none(media.get('duration'))
 164
 165         formats = []
 166
 167         for transport, links in media['sources'].items():
 168             for quality, url in links.items():
 169                 preference = -1 if priority_transport == transport else -2
 170                 if transport == 'rtmp':
 171                     mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
 172                     if not mobj:
 173                         continue
 174                     fmt = {
 175                         'url': mobj.group('url'),
 176                         'play_path': mobj.group('playpath'),
 177                         'app': mobj.group('app'),
 178                         'page_url': 'http://player.rutv.ru',
 179                         'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
 180                         'rtmp_live': True,
 181                         'ext': 'flv',
 182                         'vbr': int(quality),
 183                         'preference': preference,
 184                     }
 185                 elif transport == 'm3u8':
 186                     formats.extend(self._extract_m3u8_formats(
 187                         url, video_id, 'mp4', preference=preference, m3u8_id='hls'))
 188                     continue
 189                 else:
 190                     fmt = {
 191                         'url': url
 192                     }
 193                 fmt.update({
 194                     'width': width,
 195                     'height': height,
 196                     'format_id': '%s-%s' % (transport, quality),
 197                 })
 198                 formats.append(fmt)
 199
 200         self._sort_formats(formats)
 201
 202         return {
 203             'id': video_id,
 204             'title': self._live_title(title) if is_live else title,
 205             'description': description,
 206             'thumbnail': thumbnail,
 207             'view_count': view_count,
 208             'duration': duration,
 209             'formats': formats,
 210             'is_live': is_live,
 211         }