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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import unescapeHTML
   6
   7
   8 class VODPlatformIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/(?P<id>[^/?#]+)'
  10     _TESTS = [{
  11         # from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar
  12         'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw',
  13         'md5': '1db2b7249ce383d6be96499006e951fc',
  14         'info_dict': {
  15             'id': 'RufMcytHDolTH1MuKHY9Fw',
  16             'ext': 'mp4',
  17             'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"',
  18         }
  19     }, {
  20         'url': 'http://embed.kwikmotion.com/embed/RufMcytHDolTH1MuKHY9Fw',
  21         'only_matching': True,
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = unescapeHTML(self._og_search_title(webpage))
  29         hidden_inputs = self._hidden_inputs(webpage)
  30
  31         formats = self._extract_wowza_formats(
  32             hidden_inputs.get('HiddenmyhHlsLink') or hidden_inputs['HiddenmyDashLink'], video_id, skip_protocols=['f4m', 'smil'])
  33         self._sort_formats(formats)
  34
  35         return {
  36             'id': video_id,
  37             'title': title,
  38             'thumbnail': hidden_inputs.get('HiddenThumbnail') or self._og_search_thumbnail(webpage),
  39             'formats': formats,
  40         }