yt_dlp/extractor/historicfilms.py

   1 from .common import InfoExtractor
   2 from ..utils import parse_duration
   3
   4
   5 class HistoricFilmsIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
   7     _TEST = {
   8         'url': 'http://www.historicfilms.com/tapes/4728',
   9         'md5': 'd4a437aec45d8d796a38a215db064e9a',
  10         'info_dict': {
  11             'id': '4728',
  12             'ext': 'mov',
  13             'title': 'Historic Films: GP-7',
  14             'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
  15             'thumbnail': r're:^https?://.*\.jpg$',
  16             'duration': 2096,
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22
  23         webpage = self._download_webpage(url, video_id)
  24
  25         tape_id = self._search_regex(
  26             [r'class="tapeId"[^>]*>([^<]+)<', r'tapeId\s*:\s*"([^"]+)"'],
  27             webpage, 'tape id')
  28
  29         title = self._og_search_title(webpage)
  30         description = self._og_search_description(webpage)
  31         thumbnail = self._html_search_meta(
  32             'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
  33         duration = parse_duration(self._html_search_meta(
  34             'duration', webpage, 'duration'))
  35
  36         video_url = f'http://www.historicfilms.com/video/{tape_id}_{video_id}_web.mov'
  37
  38         return {
  39             'id': video_id,
  40             'url': video_url,
  41             'title': title,
  42             'description': description,
  43             'thumbnail': thumbnail,
  44             'duration': duration,
  45         }