yt_dlp/extractor/tvc.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     int_or_none,
   7 )
   8
   9
  10 class TVCIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
  12     _TEST = {
  13         'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702',
  14         'md5': 'bbc5ff531d1e90e856f60fc4b3afd708',
  15         'info_dict': {
  16             'id': '74622',
  17             'ext': 'mp4',
  18             'title': 'События. "События". Эфир от 22.05.2015 14:30',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'duration': 1122,
  21         },
  22     }
  23
  24     @classmethod
  25     def _extract_url(cls, webpage):
  26         mobj = re.search(
  27             r'<iframe[^>]+?src=(["\'])(?P<url>(?:http:)?//(?:www\.)?tvc\.ru/video/iframe/id/[^"]+)\1', webpage)
  28         if mobj:
  29             return mobj.group('url')
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         video = self._download_json(
  35             'http://www.tvc.ru/video/json/id/%s' % video_id, video_id)
  36
  37         formats = []
  38         for info in video.get('path', {}).get('quality', []):
  39             video_url = info.get('url')
  40             if not video_url:
  41                 continue
  42             format_id = self._search_regex(
  43                 r'cdnvideo/([^/]+?)(?:-[^/]+?)?/', video_url,
  44                 'format id', default=None)
  45             formats.append({
  46                 'url': video_url,
  47                 'format_id': format_id,
  48                 'width': int_or_none(info.get('width')),
  49                 'height': int_or_none(info.get('height')),
  50                 'tbr': int_or_none(info.get('bitrate')),
  51             })
  52         self._sort_formats(formats)
  53
  54         return {
  55             'id': video_id,
  56             'title': video['title'],
  57             'thumbnail': video.get('picture'),
  58             'duration': int_or_none(video.get('duration')),
  59             'formats': formats,
  60         }
  61
  62
  63 class TVCArticleIE(InfoExtractor):
  64     _VALID_URL = r'https?://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
  65     _TESTS = [{
  66         'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/',
  67         'info_dict': {
  68             'id': '74622',
  69             'ext': 'mp4',
  70             'title': 'События. "События". Эфир от 22.05.2015 14:30',
  71             'description': 'md5:ad7aa7db22903f983e687b8a3e98c6dd',
  72             'thumbnail': r're:^https?://.*\.jpg$',
  73             'duration': 1122,
  74         },
  75     }, {
  76         'url': 'http://www.tvc.ru/news/show/id/69944',
  77         'info_dict': {
  78             'id': '75399',
  79             'ext': 'mp4',
  80             'title': 'Эксперты: в столице встал вопрос о максимально безопасных остановках',
  81             'description': 'md5:f2098f71e21f309e89f69b525fd9846e',
  82             'thumbnail': r're:^https?://.*\.jpg$',
  83             'duration': 278,
  84         },
  85     }, {
  86         'url': 'http://www.tvc.ru/channel/brand/id/47/show/episodes#',
  87         'info_dict': {
  88             'id': '2185',
  89             'ext': 'mp4',
  90             'title': 'Ещё не поздно. Эфир от 03.08.2013',
  91             'description': 'md5:51fae9f3f8cfe67abce014e428e5b027',
  92             'thumbnail': r're:^https?://.*\.jpg$',
  93             'duration': 3316,
  94         },
  95     }]
  96
  97     def _real_extract(self, url):
  98         webpage = self._download_webpage(url, self._match_id(url))
  99         return {
 100             '_type': 'url_transparent',
 101             'ie_key': 'TVC',
 102             'url': self._og_search_video_url(webpage),
 103             'title': clean_html(self._og_search_title(webpage)),
 104             'description': clean_html(self._og_search_description(webpage)),
 105             'thumbnail': self._og_search_thumbnail(webpage),
 106         }