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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_request
   8 from ..utils import ExtractorError
   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         }
  23     }
  24
  25     def _real_extract(self, url):
  26         display_id = self._match_id(url)
  27         req = compat_urllib_request.Request(url)
  28         # Older versions of Firefox get redirected to an "upgrade browser" page
  29         req.add_header('User-Agent', 'youtube-dl')
  30         webpage = self._download_webpage(req, display_id)
  31         thumbnail = self._og_search_thumbnail(webpage)
  32         video_id = self._search_regex(r'/(\d+)\.png', thumbnail, 'id')
  33
  34         if '<a>Queued for processing, please stand by...</a>' in webpage:
  35             raise ExtractorError('Audio is still queued for processing')
  36
  37         formats = [{
  38             'url': 'https://voicerepublic.com' + path,
  39             'ext': ext,
  40             'format_id': ext,
  41             'vcodec': 'none',
  42         } for ext, path in re.findall(r"data-([^=]+)='(/[^']+\.\1)'", webpage)]
  43         self._sort_formats(formats)
  44
  45         return {
  46             'id': video_id,
  47             'title': self._og_search_title(webpage),
  48             'formats': formats,
  49             'url': self._og_search_url(webpage),
  50             'thumbnail': thumbnail,
  51             'description': self._og_search_description(webpage),
  52         }