1 from __future__ import unicode_literals
3 from .common import InfoExtractor
4 from ..compat import compat_str
13 class VoiceRepublicIE(InfoExtractor):
14 _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
16 'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
17 'md5': 'b9174d651323f17783000876347116e3',
20 'display_id': 'watching-the-watchers-building-a-sousveillance-state',
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.',
28 'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state',
29 'only_matching': True,
32 def _real_extract(self, url):
33 display_id = self._match_id(url)
35 webpage = self._download_webpage(url, display_id)
37 if '>Queued for processing, please stand by...<' in webpage:
39 'Audio is still queued for processing', expected=True)
41 talk = self._parse_json(self._search_regex(
42 r'initialSnapshot\s*=\s*({.+?});',
43 webpage, 'talk'), display_id)['talk']
46 'url': urljoin(url, talk_url),
47 'format_id': format_id,
48 'ext': determine_ext(talk_url) or format_id,
50 } for format_id, talk_url in talk['media_links'].items()]
51 self._sort_formats(formats)
54 'id': compat_str(talk.get('id') or display_id),
55 'display_id': display_id,
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')),