Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dhm.py

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