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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class BreakIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
  11     _TESTS = [{
  12         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
  13         'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
  14         'info_dict': {
  15             'id': '2468056',
  16             'ext': 'mp4',
  17             'title': 'When Girls Act Like D-Bags',
  18         }
  19     }, {
  20         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
  21         'only_matching': True,
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(
  27             'http://www.break.com/embed/%s' % video_id, video_id)
  28         info = json.loads(self._search_regex(
  29             r'var embedVars = ({.*})\s*?</script>',
  30             webpage, 'info json', flags=re.DOTALL))
  31         video_url = info['videoUri']
  32         youtube_id = info.get('youtubeId')
  33         if youtube_id:
  34             return self.url_result(youtube_id, 'Youtube')
  35
  36         final_url = video_url + '?' + info['AuthToken']
  37         return {
  38             'id': video_id,
  39             'url': final_url,
  40             'title': info['contentName'],
  41             'thumbnail': info['thumbUri'],
  42         }