Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ina.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class InaIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
  13         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
  14         'info_dict': {
  15             'id': 'I12055569',
  16             'ext': 'mp4',
  17             'title': 'François Hollande "Je crois que c\'est clair"',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23
  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)
  27
  28         self.report_extraction(video_id)
  29
  30         video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
  31
  32         return {
  33             'id': video_id,
  34             'url': video_url,
  35             'title': info_doc.find('.//title').text,
  36         }