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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import find_xpath_attr, compat_str
   5
   6
   7 class NBCNewsIE(InfoExtractor):
   8     _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
   9
  10     _TEST = {
  11         u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
  12         u'file': u'52753292.flv',
  13         u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
  14         u'info_dict': {
  15             u'title': u'Crew emerges after four-month Mars food study',
  16             u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group('id')
  23         all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
  24         info = all_info.find('video')
  25
  26         return {'id': video_id,
  27                 'title': info.find('headline').text,
  28                 'ext': 'flv',
  29                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
  30                 'description': compat_str(info.find('caption').text),
  31                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
  32                 }