_ Git - youtube-dl/blob - youtube_dl/extractor/voicerepublic.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..compat import (
   7     compat_urllib_request,
   8 )
   9
  10
  11 class VoiceRepublicIE(InfoExtractor):
  12     _VALID_URL = r'https?://voicerepublic\.com/talks/(?P<id>[0-9a-z-]+)'
  13     _TEST = {
  14         'url': 'https://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
  15         'md5': '0554a24d1657915aa8e8f84e15dc9353',
  16         'info_dict': {
  17             'id': '2296',
  18             'ext': 'm4a',
  19             'title': 'Watching the Watchers: Building a Sousveillance State',
  20             'thumbnail': 'https://voicerepublic.com/system/flyer/2296.png',
  21             'description': 'md5:715ba964958afa2398df615809cfecb1',
  22             'creator': 'M. C. McGrath',
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         display_id = self._match_id(url)
  28         req = compat_urllib_request.Request(url)
  29         # Older versions of Firefox get redirected to an "upgrade browser" page
  30         req.add_header('User-Agent', 'youtube-dl')
  31         webpage = self._download_webpage(req, display_id)
  32         thumbnail = self._og_search_thumbnail(webpage)
  33         video_id = self._search_regex(r'/(\d+)\.png', thumbnail, 'id')
  34
  35         if '<div class=\'vr-player jp-jplayer\'' in webpage:
  36             formats = [{
  37                 'url': 'https://voicerepublic.com/vrmedia/{}-clean.{}'.format(video_id, ext),
  38                 'ext': ext,
  39                 'format_id': ext,
  40                 'vcodec': 'none',
  41             } for ext in ['m4a', 'mp3', 'ogg']]
  42             self._sort_formats(formats)
  43         else:
  44             # Audio is still queued for processing
  45             formats = []
  46
  47         return {
  48             'id': video_id,
  49             'title': self._og_search_title(webpage),
  50             'formats': formats,
  51             'url': self._og_search_url(webpage),
  52             'thumbnail': thumbnail,
  53             'description': self._og_search_description(webpage),
  54             'creator': self._search_regex(r'<meta content=\'([^\']*?)\' name=\'author\'>', webpage, 'author', fatal=False),
  55         }