_ Git - youtube-dl/blob - youtube_dl/extractor/dhm.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     xpath_text,
   6     parse_duration,
   7 )
   8
   9
  10 class DHMIE(InfoExtractor):
  11     IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
  12     _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
  13
  14     _TESTS = [{
  15         'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
  16         'md5': '11c475f670209bf6acca0b2b7ef51827',
  17         'info_dict': {
  18             'id': 'the-marshallplan-at-work-in-west-germany',
  19             'ext': 'flv',
  20             'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
  21             'description': 'md5:1fabd480c153f97b07add61c44407c82',
  22             'duration': 660,
  23             'thumbnail': 're:^https?://.*\.jpg$',
  24         },
  25     }, {
  26         'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
  27         'md5': '09890226332476a3e3f6f2cb74734aa5',
  28         'info_dict': {
  29             'id': 'rolle-1',
  30             'ext': 'flv',
  31             'title': 'ROLLE 1',
  32             'thumbnail': 're:^https?://.*\.jpg$',
  33         },
  34     }]
  35
  36     def _real_extract(self, url):
  37         playlist_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, playlist_id)
  40
  41         playlist_url = self._search_regex(
  42             r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
  43
  44         entries = self._extract_xspf_playlist(playlist_url, playlist_id)
  45
  46         title = self._search_regex(
  47             [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</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))
  55
  56         entries[0].update({
  57             'title': title,
  58             'description': description,
  59             'duration': duration,
  60         })
  61
  62         return self.playlist_result(entries, playlist_id)