1 from __future__ import unicode_literals
3 from .common import InfoExtractor
10 class DHMIE(InfoExtractor):
11 IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
12 _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
15 'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
16 'md5': '11c475f670209bf6acca0b2b7ef51827',
18 'id': 'the-marshallplan-at-work-in-west-germany',
20 'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
21 'description': 'md5:1fabd480c153f97b07add61c44407c82',
23 'thumbnail': 're:^https?://.*\.jpg$',
26 'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
27 'md5': '09890226332476a3e3f6f2cb74734aa5',
32 'thumbnail': 're:^https?://.*\.jpg$',
36 def _real_extract(self, url):
37 playlist_id = self._match_id(url)
39 webpage = self._download_webpage(url, playlist_id)
41 playlist_url = self._search_regex(
42 r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
44 entries = self._extract_xspf_playlist(playlist_url, playlist_id)
46 title = self._search_regex(
47 [r'dc:title="([^"]+)"', r'<title> »([^<]+)</title>'],
48 webpage, 'title').strip()
49 description = self._html_search_regex(
50 r'<p><strong>Description:</strong>(.+?)</p>',
51 webpage, 'description', default=None)
52 duration = parse_duration(self._search_regex(
53 r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
54 webpage, 'duration', default=None))
58 'description': description,
62 return self.playlist_result(entries, playlist_id)