_ 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 from ..compat import compat_urllib_request
   6 from ..utils import ExtractorError
   7
   8
   9 class VoiceRepublicIE(InfoExtractor):
  10     _VALID_URL = r'https?://voicerepublic\.com/talks/(?P<id>[0-9a-z-]+)'
  11     _TEST = {
  12         'url': 'https://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
  13         'md5': '0554a24d1657915aa8e8f84e15dc9353',
  14         'info_dict': {
  15             'id': '2296',
  16             'ext': 'm4a',
  17             'title': 'Watching the Watchers: Building a Sousveillance State',
  18             'thumbnail': 'https://voicerepublic.com/system/flyer/2296.png',
  19             'description': 'md5:715ba964958afa2398df615809cfecb1',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         display_id = self._match_id(url)
  25         req = compat_urllib_request.Request(url)
  26         # Older versions of Firefox get redirected to an "upgrade browser" page
  27         req.add_header('User-Agent', 'youtube-dl')
  28         webpage = self._download_webpage(req, display_id)
  29         thumbnail = self._og_search_thumbnail(webpage)
  30         video_id = self._search_regex(r'/(\d+)\.png', thumbnail, 'id')
  31
  32         if '<a>Queued for processing, please stand by...</a>' in webpage:
  33             raise ExtractorError('Audio is still queued for processing')
  34
  35         formats = [{
  36             'url': 'https://voicerepublic.com/vrmedia/{}-clean.{}'.format(video_id, ext),
  37             'ext': ext,
  38             'format_id': ext,
  39             'vcodec': 'none',
  40         } for ext in ['m4a', 'mp3', 'ogg']]
  41         self._sort_formats(formats)
  42
  43         return {
  44             'id': video_id,
  45             'title': self._og_search_title(webpage),
  46             'formats': formats,
  47             'url': self._og_search_url(webpage),
  48             'thumbnail': thumbnail,
  49             'description': self._og_search_description(webpage),
  50         }