youtube_dl/extractor/rmcdecouverte.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .brightcove import BrightcoveLegacyIE
   6 from ..compat import (
   7     compat_parse_qs,
   8     compat_urlparse,
   9 )
  10
  11
  12 class RMCDecouverteIE(InfoExtractor):
  13     _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)'
  14
  15     _TEST = {
  16         'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET',
  17         'info_dict': {
  18             'id': '5419055995001',
  19             'ext': 'mp4',
  20             'title': 'UN DELICIEUX PROJET',
  21             'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5',
  22             'uploader_id': '1969646226001',
  23             'upload_date': '20170502',
  24             'timestamp': 1493745308,
  25         },
  26         'params': {
  27             'skip_download': True,
  28         },
  29         'skip': 'only available for a week',
  30     }
  31     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s'
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         webpage = self._download_webpage(url, video_id)
  36         brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
  37         if brightcove_legacy_url:
  38             brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
  39                 brightcove_legacy_url).query)['@videoPlayer'][0]
  40         else:
  41             brightcove_id = self._search_regex(
  42                 r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
  43         return self.url_result(
  44             self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew',
  45             brightcove_id)