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

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