yt_dlp/extractor/rutv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError, int_or_none, str_to_int
   5
   6
   7 class RUTVIE(InfoExtractor):
   8     IE_DESC = 'RUTV.RU'
   9     _VALID_URL = r'''(?x)
  10                     https?://
  11                         (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/
  12                         (?P<path>
  13                             flash\d+v/container\.swf\?id=|
  14                             iframe/(?P<type>swf|video|live)/id/|
  15                             index/iframe/cast_id/
  16                         )
  17                         (?P<id>\d+)
  18                     '''
  19     _EMBED_URLS = [
  20         r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1',
  21         r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
  22     ]
  23
  24     _TESTS = [
  25         {
  26             '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',
  27             'info_dict': {
  28                 'id': '774471',
  29                 'ext': 'mp4',
  30                 'title': 'Монологи на все времена',
  31                 'description': 'md5:18d8b5e6a41fb1faa53819471852d5d5',
  32                 'duration': 2906,
  33             },
  34             'params': {
  35                 # m3u8 download
  36                 'skip_download': True,
  37             },
  38         },
  39         {
  40             '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',
  41             'info_dict': {
  42                 'id': '774016',
  43                 'ext': 'mp4',
  44                 'title': 'Чужой в семье Сталина',
  45                 'description': '',
  46                 'duration': 2539,
  47             },
  48             'params': {
  49                 # m3u8 download
  50                 'skip_download': True,
  51             },
  52         },
  53         {
  54             'url': 'http://player.rutv.ru/iframe/swf/id/766888/sid/hitech/?acc_video_id=4000',
  55             'info_dict': {
  56                 'id': '766888',
  57                 'ext': 'mp4',
  58                 'title': 'Вести.net: интернет-гиганты начали перетягивание программных "одеял"',
  59                 'description': 'md5:65ddd47f9830c4f42ed6475f8730c995',
  60                 'duration': 279,
  61             },
  62             'params': {
  63                 # m3u8 download
  64                 'skip_download': True,
  65             },
  66         },
  67         {
  68             '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',
  69             'info_dict': {
  70                 'id': '771852',
  71                 'ext': 'mp4',
  72                 'title': 'Прямой эфир. Жертвы загадочной болезни: смерть от старости в 17 лет',
  73                 'description': 'md5:b81c8c55247a4bd996b43ce17395b2d8',
  74                 'duration': 3096,
  75             },
  76             'params': {
  77                 # m3u8 download
  78                 'skip_download': True,
  79             },
  80         },
  81         {
  82             'url': 'http://player.rutv.ru/iframe/live/id/51499/showZoomBtn/false/isPlay/true/sid/sochi2014',
  83             'info_dict': {
  84                 'id': '51499',
  85                 'ext': 'flv',
  86                 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
  87                 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
  88             },
  89             'skip': 'Translation has finished',
  90         },
  91         {
  92             'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
  93             'info_dict': {
  94                 'id': '21',
  95                 'ext': 'mp4',
  96                 'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  97                 'is_live': True,
  98             },
  99             'params': {
 100                 # m3u8 download
 101                 'skip_download': True,
 102             },
 103         },
 104         {
 105             'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/',
 106             'only_matching': True,
 107         },
 108     ]
 109
 110     def _real_extract(self, url):
 111         mobj = self._match_valid_url(url)
 112         video_id = mobj.group('id')
 113         video_path = mobj.group('path')
 114
 115         if re.match(r'flash\d+v', video_path):
 116             video_type = 'video'
 117         elif video_path.startswith('iframe'):
 118             video_type = mobj.group('type')
 119             if video_type == 'swf':
 120                 video_type = 'video'
 121         elif video_path.startswith('index/iframe/cast_id'):
 122             video_type = 'live'
 123
 124         is_live = video_type == 'live'
 125
 126         json_data = self._download_json(
 127             'http://player.vgtrk.com/iframe/data%s/id/%s' % ('live' if is_live else 'video', video_id),
 128             video_id, 'Downloading JSON')
 129
 130         if json_data['errors']:
 131             raise ExtractorError('%s said: %s' % (self.IE_NAME, json_data['errors']), expected=True)
 132
 133         playlist = json_data['data']['playlist']
 134         medialist = playlist['medialist']
 135         media = medialist[0]
 136
 137         if media['errors']:
 138             raise ExtractorError('%s said: %s' % (self.IE_NAME, media['errors']), expected=True)
 139
 140         view_count = int_or_none(playlist.get('count_views'))
 141         priority_transport = playlist['priority_transport']
 142
 143         thumbnail = media['picture']
 144         width = int_or_none(media['width'])
 145         height = int_or_none(media['height'])
 146         description = media['anons']
 147         title = media['title']
 148         duration = int_or_none(media.get('duration'))
 149
 150         formats = []
 151         subtitles = {}
 152
 153         for transport, links in media['sources'].items():
 154             for quality, url in links.items():
 155                 preference = -1 if priority_transport == transport else -2
 156                 if transport == 'rtmp':
 157                     mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
 158                     if not mobj:
 159                         continue
 160                     fmt = {
 161                         'url': mobj.group('url'),
 162                         'play_path': mobj.group('playpath'),
 163                         'app': mobj.group('app'),
 164                         'page_url': 'http://player.rutv.ru',
 165                         'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
 166                         'rtmp_live': True,
 167                         'ext': 'flv',
 168                         'vbr': str_to_int(quality),
 169                     }
 170                 elif transport == 'm3u8':
 171                     fmt, subs = self._extract_m3u8_formats_and_subtitles(
 172                         url, video_id, 'mp4', quality=preference, m3u8_id='hls')
 173                     formats.extend(fmt)
 174                     self._merge_subtitles(subs, target=subtitles)
 175                     continue
 176                 else:
 177                     fmt = {
 178                         'url': url
 179                     }
 180                 fmt.update({
 181                     'width': int_or_none(quality, default=height, invscale=width, scale=height),
 182                     'height': int_or_none(quality, default=height),
 183                     'format_id': '%s-%s' % (transport, quality),
 184                     'source_preference': preference,
 185                 })
 186                 formats.append(fmt)
 187
 188         return {
 189             'id': video_id,
 190             'title': title,
 191             'description': description,
 192             'thumbnail': thumbnail,
 193             'view_count': view_count,
 194             'duration': duration,
 195             'formats': formats,
 196             'subtitles': subtitles,
 197             'is_live': is_live,
 198             '_format_sort_fields': ('source', ),
 199         }