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

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9 class BpbIE(InfoExtractor):
  10         IE_NAME = 'Bundeszentrale für politische Bildung'
  11         _VALID_URL = r'http://www\.bpb\.de/mediathek/.*'
  12
  13         _TEST = {
  14                 'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
  15                 'md5': '0792086e8e2bfbac9cdf27835d5f2093',
  16                 'info_dict': {
  17                         'id': '12490',
  18                         'ext': 'mp4',
  19                         'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
  20                         'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.'
  21                 }
  22         }
  23
  24         def _real_extract(self, url):
  25                 webpage = self._download_webpage(url, '')
  26
  27                 title = self._html_search_regex(r'<h2 class="white">(.*?)</h2>', webpage, 'title')
  28
  29                 video_id = self._html_search_regex(r'http://film\.bpb\.de/player/dokument_(?P<video_id>[0-9]+)\.mp4', webpage, 'video_id')
  30
  31                 url = 'http://film.bpb.de/player/dokument_' + video_id + '.mp4'
  32
  33                 description = self._og_search_description(webpage)
  34
  35                 return {
  36                         'id': video_id,
  37                         'url': url,
  38                         'title': title,
  39                         'description': description,
  40                         'ext': 'mp4'
  41                 }