youtube_dl/extractor/nbc.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5 from ..utils import find_xpath_attr, compat_str
   6
   7
   8 class NBCNewsIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
  10
  11     _TEST = {
  12         u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
  13         u'file': u'52753292.flv',
  14         u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
  15         u'info_dict': {
  16             u'title': u'Crew emerges after four-month Mars food study',
  17             u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
  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_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
  25         info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
  26
  27         return {'id': video_id,
  28                 'title': info.find('headline').text,
  29                 'ext': 'flv',
  30                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
  31                 'description': compat_str(info.find('caption').text),
  32                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
  33                 }