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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import remove_end
   6
   7
   8 class TelegraafIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html'
  10     _TEST = {
  11         'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html',
  12         'md5': '83245a9779bcc4a24454bfd53c65b6dc',
  13         'info_dict': {
  14             'id': '24353229',
  15             'ext': 'mp4',
  16             'title': 'Tikibad ontruimd wegens brand',
  17             'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  18             'thumbnail': 're:^https?://.*\.jpg$',
  19             'duration': 33,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         playlist_id = self._match_id(url)
  25
  26         webpage = self._download_webpage(url, playlist_id)
  27
  28         playlist_url = self._search_regex(
  29             r"iframe\.loadPlayer\('([^']+)'", webpage, 'player')
  30
  31         entries = self._extract_xspf_playlist(playlist_url, playlist_id)
  32         title = remove_end(self._og_search_title(webpage), ' - VIDEO')
  33         description = self._og_search_description(webpage)
  34
  35         return self.playlist_result(entries, playlist_id, title, description)