2 from __future__ import unicode_literals
6 from .common import InfoExtractor
9 class InaIE(InfoExtractor):
10 _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
12 'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
13 'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
17 'title': 'François Hollande "Je crois que c\'est clair"',
21 def _real_extract(self, url):
22 mobj = re.match(self._VALID_URL, url)
24 video_id = mobj.group('id')
25 mrss_url = 'http://player.ina.fr/notices/%s.mrss' % video_id
26 info_doc = self._download_xml(mrss_url, video_id)
28 self.report_extraction(video_id)
30 video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
35 'title': info_doc.find('.//title').text,