You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

59 lines
2.0 KiB

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