yt_dlp/extractor/volejtv.py

   1 from .common import InfoExtractor
   2
   3
   4 class VolejTVIE(InfoExtractor):
   5     _VALID_URL = r'https?://volej\.tv/video/(?P<id>\d+)'
   6     _TESTS = [{
   7         'url': 'https://volej.tv/video/725742/',
   8         'info_dict': {
   9             'id': '725742',
  10             'ext': 'mp4',
  11             'description': 'Zápas VK Královo Pole vs VK Prostějov 10.12.2022 v 19:00 na Volej.TV',
  12             'thumbnail': 'https://volej.tv/images/og/16/17186/og.png',
  13             'title': 'VK Královo Pole vs VK Prostějov',
  14         },
  15     }, {
  16         'url': 'https://volej.tv/video/725605/',
  17         'info_dict': {
  18             'id': '725605',
  19             'ext': 'mp4',
  20             'thumbnail': 'https://volej.tv/images/og/15/17185/og.png',
  21             'title': 'VK Lvi Praha vs VK Euro Sitex Příbram',
  22             'description': 'Zápas VK Lvi Praha vs VK Euro Sitex Příbram 11.12.2022 v 19:00 na Volej.TV',
  23         },
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29         json_data = self._search_json(
  30             r'<\s*!\[CDATA[^=]+=', webpage, 'CDATA', video_id)
  31         formats, subtitle = self._extract_m3u8_formats_and_subtitles(
  32             json_data['urls']['hls'], video_id)
  33         return {
  34             'id': video_id,
  35             'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
  36             'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
  37             'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
  38             'formats': formats,
  39             'subtitles': subtitle,
  40         }