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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     ExtractorError,
   7     determine_ext,
   8     int_or_none,
   9     urljoin,
  10 )
  11
  12
  13 class VoiceRepublicIE(InfoExtractor):
  14     _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
  15     _TESTS = [{
  16         'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
  17         'md5': 'b9174d651323f17783000876347116e3',
  18         'info_dict': {
  19             'id': '2296',
  20             'display_id': 'watching-the-watchers-building-a-sousveillance-state',
  21             'ext': 'm4a',
  22             'title': 'Watching the Watchers: Building a Sousveillance State',
  23             'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
  24             'duration': 1556,
  25             'view_count': int,
  26         }
  27     }, {
  28         'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         display_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(url, display_id)
  36
  37         if '>Queued for processing, please stand by...<' in webpage:
  38             raise ExtractorError(
  39                 'Audio is still queued for processing', expected=True)
  40
  41         talk = self._parse_json(self._search_regex(
  42             r'initialSnapshot\s*=\s*({.+?});',
  43             webpage, 'talk'), display_id)['talk']
  44         title = talk['title']
  45         formats = [{
  46             'url': urljoin(url, talk_url),
  47             'format_id': format_id,
  48             'ext': determine_ext(talk_url) or format_id,
  49             'vcodec': 'none',
  50         } for format_id, talk_url in talk['media_links'].items()]
  51         self._sort_formats(formats)
  52
  53         return {
  54             'id': compat_str(talk.get('id') or display_id),
  55             'display_id': display_id,
  56             'title': title,
  57             'description': talk.get('teaser'),
  58             'thumbnail': talk.get('image_url'),
  59             'duration': int_or_none(talk.get('archived_duration')),
  60             'view_count': int_or_none(talk.get('play_count')),
  61             'formats': formats,
  62         }