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

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5
   6
   7 class PBSIE(InfoExtractor):
   8     _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
   9
  10     _TEST = {
  11         u'url': u'http://video.pbs.org/video/2365006249/',
  12         u'file': u'2365006249.mp4',
  13         u'md5': 'ce1888486f0908d555a8093cac9a7362',
  14         u'info_dict': {
  15             u'title': u'A More Perfect Union',
  16             u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
  17             u'duration': 3190,
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
  25         info_page = self._download_webpage(info_url, video_id)
  26         info =json.loads(info_page)
  27         return {'id': video_id,
  28                 'title': info['title'],
  29                 'url': info['alternate_encoding']['url'],
  30                 'ext': 'mp4',
  31                 'description': info['program'].get('description'),
  32                 'thumbnail': info.get('image_url'),
  33                 'duration': info.get('duration'),
  34                 }