yt_dlp/extractor/dhm.py

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