yt_dlp/extractor/oftv.py

   1 from .common import InfoExtractor
   2 from .zype import ZypeIE
   3 from ..utils import traverse_obj
   4
   5
   6 class OfTVIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?of\.tv/video/(?P<id>\w+)'
   8     _TESTS = [{
   9         'url': 'https://of.tv/video/627d7d95b353db0001dadd1a',
  10         'md5': 'cb9cd5db3bb9ee0d32bfd7e373d6ef0a',
  11         'info_dict': {
  12             'id': '627d7d95b353db0001dadd1a',
  13             'ext': 'mp4',
  14             'title': 'E1: Jacky vs Eric',
  15             'thumbnail': r're:^https?://.*\.jpg',
  16             'average_rating': 0,
  17             'description': 'md5:dd16e3e2a8d27d922e7a989f85986853',
  18             'display_id': '',
  19             'duration': 1423,
  20             'timestamp': 1652391300,
  21             'upload_date': '20220512',
  22             'view_count': 0,
  23             'creator': 'This is Fire',
  24         },
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30         info = next(ZypeIE.extract_from_webpage(self._downloader, url, webpage))
  31         info['_type'] = 'url_transparent'
  32         info['creator'] = self._search_regex(r'<a[^>]+class=\"creator-name\"[^>]+>([^<]+)', webpage, 'creator')
  33         return info
  34
  35
  36 class OfTVPlaylistIE(InfoExtractor):
  37     _VALID_URL = r'https?://(?:www\.)?of\.tv/creators/(?P<id>[a-zA-Z0-9-]+)/?(?:$|[?#])'
  38     _TESTS = [{
  39         'url': 'https://of.tv/creators/this-is-fire/',
  40         'playlist_count': 8,
  41         'info_dict': {
  42             'id': 'this-is-fire',
  43         },
  44     }]
  45
  46     def _real_extract(self, url):
  47         playlist_id = self._match_id(url)
  48         webpage = self._download_webpage(url, playlist_id)
  49
  50         json_match = self._search_json(
  51             r'var\s*remaining_videos\s*=', webpage, 'oftv playlists', playlist_id, contains_pattern=r'\[.+\]')
  52
  53         return self.playlist_from_matches(
  54             traverse_obj(json_match, (..., 'discovery_url')), playlist_id)