yt_dlp/extractor/dhm.py

   1 from .common import InfoExtractor
   2 from ..utils import parse_duration
   3
   4
   5 class DHMIE(InfoExtractor):
   6     _WORKING = False
   7     IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
   8     _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
   9
  10     _TESTS = [{
  11         'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
  12         'md5': '11c475f670209bf6acca0b2b7ef51827',
  13         'info_dict': {
  14             'id': 'the-marshallplan-at-work-in-west-germany',
  15             'ext': 'flv',
  16             'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
  17             'description': 'md5:1fabd480c153f97b07add61c44407c82',
  18             'duration': 660,
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20         },
  21     }, {
  22         'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
  23         'md5': '09890226332476a3e3f6f2cb74734aa5',
  24         'info_dict': {
  25             'id': 'rolle-1',
  26             'ext': 'flv',
  27             'title': 'ROLLE 1',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29         },
  30     }]
  31
  32     def _real_extract(self, url):
  33         playlist_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(url, playlist_id)
  36
  37         playlist_url = self._search_regex(
  38             r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
  39
  40         entries = self._extract_xspf_playlist(playlist_url, playlist_id)
  41
  42         title = self._search_regex(
  43             [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
  44             webpage, 'title').strip()
  45         description = self._html_search_regex(
  46             r'<p><strong>Description:</strong>(.+?)</p>',
  47             webpage, 'description', default=None)
  48         duration = parse_duration(self._search_regex(
  49             r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
  50             webpage, 'duration', default=None))
  51
  52         entries[0].update({
  53             'title': title,
  54             'description': description,
  55             'duration': duration,
  56         })
  57
  58         return self.playlist_result(entries, playlist_id)