logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

rutv.py (8087B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .common import InfoExtractor
  7. from ..utils import (
  8.     ExtractorError,
  9.     int_or_none,
  10.     str_to_int
  11. )
  14. class RUTVIE(InfoExtractor):
  15.     IE_DESC = 'RUTV.RU'
  16.     _VALID_URL = r'''(?x)
  17.                     https?://
  18.                         (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/
  19.                         (?P<path>
  20.                             flash\d+v/container\.swf\?id=|
  21.                             iframe/(?P<type>swf|video|live)/id/|
  22.                             index/iframe/cast_id/
  23.                         )
  24.                         (?P<id>\d+)
  25.                     '''
  27.     _TESTS = [
  28.         {
  29.             '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',
  30.             'info_dict': {
  31.                 'id': '774471',
  32.                 'ext': 'mp4',
  33.                 'title': 'Монологи на все времена',
  34.                 'description': 'md5:18d8b5e6a41fb1faa53819471852d5d5',
  35.                 'duration': 2906,
  36.             },
  37.             'params': {
  38.                 # m3u8 download
  39.                 'skip_download': True,
  40.             },
  41.         },
  42.         {
  43.             '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',
  44.             'info_dict': {
  45.                 'id': '774016',
  46.                 'ext': 'mp4',
  47.                 'title': 'Чужой в семье Сталина',
  48.                 'description': '',
  49.                 'duration': 2539,
  50.             },
  51.             'params': {
  52.                 # m3u8 download
  53.                 'skip_download': True,
  54.             },
  55.         },
  56.         {
  57.             'url': 'http://player.rutv.ru/iframe/swf/id/766888/sid/hitech/?acc_video_id=4000',
  58.             'info_dict': {
  59.                 'id': '766888',
  60.                 'ext': 'mp4',
  61.                 'title': 'Вести.net: интернет-гиганты начали перетягивание программных "одеял"',
  62.                 'description': 'md5:65ddd47f9830c4f42ed6475f8730c995',
  63.                 'duration': 279,
  64.             },
  65.             'params': {
  66.                 # m3u8 download
  67.                 'skip_download': True,
  68.             },
  69.         },
  70.         {
  71.             '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',
  72.             'info_dict': {
  73.                 'id': '771852',
  74.                 'ext': 'mp4',
  75.                 'title': 'Прямой эфир. Жертвы загадочной болезни: смерть от старости в 17 лет',
  76.                 'description': 'md5:b81c8c55247a4bd996b43ce17395b2d8',
  77.                 'duration': 3096,
  78.             },
  79.             'params': {
  80.                 # m3u8 download
  81.                 'skip_download': True,
  82.             },
  83.         },
  84.         {
  85.             'url': 'http://player.rutv.ru/iframe/live/id/51499/showZoomBtn/false/isPlay/true/sid/sochi2014',
  86.             'info_dict': {
  87.                 'id': '51499',
  88.                 'ext': 'flv',
  89.                 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
  90.                 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
  91.             },
  92.             'skip': 'Translation has finished',
  93.         },
  94.         {
  95.             'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
  96.             'info_dict': {
  97.                 'id': '21',
  98.                 'ext': 'mp4',
  99.                 'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  100.                 'is_live': True,
  101.             },
  102.             'params': {
  103.                 # m3u8 download
  104.                 'skip_download': True,
  105.             },
  106.         },
  107.         {
  108.             'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/',
  109.             'only_matching': True,
  110.         },
  111.     ]
  113.     @classmethod
  114.     def _extract_url(cls, webpage):
  115.         mobj = re.search(
  116.             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
  117.         if mobj:
  118.             return mobj.group('url')
  120.         mobj = re.search(
  121.             r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
  122.             webpage)
  123.         if mobj:
  124.             return mobj.group('url')
  126.     def _real_extract(self, url):
  127.         mobj = re.match(self._VALID_URL, url)
  128.         video_id = mobj.group('id')
  129.         video_path = mobj.group('path')
  131.         if re.match(r'flash\d+v', video_path):
  132.             video_type = 'video'
  133.         elif video_path.startswith('iframe'):
  134.             video_type = mobj.group('type')
  135.             if video_type == 'swf':
  136.                 video_type = 'video'
  137.         elif video_path.startswith('index/iframe/cast_id'):
  138.             video_type = 'live'
  140.         is_live = video_type == 'live'
  142.         json_data = self._download_json(
  143.             'http://player.rutv.ru/iframe/data%s/id/%s' % ('live' if is_live else 'video', video_id),
  144.             video_id, 'Downloading JSON')
  146.         if json_data['errors']:
  147.             raise ExtractorError('%s said: %s' % (self.IE_NAME, json_data['errors']), expected=True)
  149.         playlist = json_data['data']['playlist']
  150.         medialist = playlist['medialist']
  151.         media = medialist[0]
  153.         if media['errors']:
  154.             raise ExtractorError('%s said: %s' % (self.IE_NAME, media['errors']), expected=True)
  156.         view_count = playlist.get('count_views')
  157.         priority_transport = playlist['priority_transport']
  159.         thumbnail = media['picture']
  160.         width = int_or_none(media['width'])
  161.         height = int_or_none(media['height'])
  162.         description = media['anons']
  163.         title = media['title']
  164.         duration = int_or_none(media.get('duration'))
  166.         formats = []
  168.         for transport, links in media['sources'].items():
  169.             for quality, url in links.items():
  170.                 preference = -1 if priority_transport == transport else -2
  171.                 if transport == 'rtmp':
  172.                     mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
  173.                     if not mobj:
  174.                         continue
  175.                     fmt = {
  176.                         'url': mobj.group('url'),
  177.                         'play_path': mobj.group('playpath'),
  178.                         'app': mobj.group('app'),
  179.                         'page_url': 'http://player.rutv.ru',
  180.                         'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
  181.                         'rtmp_live': True,
  182.                         'ext': 'flv',
  183.                         'vbr': str_to_int(quality),
  184.                         'preference': preference,
  185.                     }
  186.                 elif transport == 'm3u8':
  187.                     formats.extend(self._extract_m3u8_formats(
  188.                         url, video_id, 'mp4', preference=preference, m3u8_id='hls'))
  189.                     continue
  190.                 else:
  191.                     fmt = {
  192.                         'url': url
  193.                     }
  194.                 fmt.update({
  195.                     'width': width,
  196.                     'height': height,
  197.                     'format_id': '%s-%s' % (transport, quality),
  198.                 })
  199.                 formats.append(fmt)
  201.         self._sort_formats(formats)
  203.         return {
  204.             'id': video_id,
  205.             'title': self._live_title(title) if is_live else title,
  206.             'description': description,
  207.             'thumbnail': thumbnail,
  208.             'view_count': view_count,
  209.             'duration': duration,
  210.             'formats': formats,
  211.             'is_live': is_live,
  212.         }