]>
Commit | Line | Data |
---|---|---|
c6ddbdb6 D |
1 | from __future__ import unicode_literals |
2 | ||
3 | from .common import InfoExtractor | |
be96f992 | 4 | from ..compat import compat_str |
a6762c4a S |
5 | from ..utils import ( |
6 | ExtractorError, | |
7 | determine_ext, | |
8 | int_or_none, | |
be96f992 | 9 | urljoin, |
a6762c4a | 10 | ) |
c6ddbdb6 D |
11 | |
12 | ||
13 | class VoiceRepublicIE(InfoExtractor): | |
a6762c4a S |
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', | |
c16f8a46 | 17 | 'md5': 'b9174d651323f17783000876347116e3', |
c6ddbdb6 D |
18 | 'info_dict': { |
19 | 'id': '2296', | |
a6762c4a | 20 | 'display_id': 'watching-the-watchers-building-a-sousveillance-state', |
c6ddbdb6 D |
21 | 'ext': 'm4a', |
22 | 'title': 'Watching the Watchers: Building a Sousveillance State', | |
c16f8a46 | 23 | 'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.', |
be96f992 | 24 | 'duration': 1556, |
a6762c4a | 25 | 'view_count': int, |
c6ddbdb6 | 26 | } |
a6762c4a S |
27 | }, { |
28 | 'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state', | |
29 | 'only_matching': True, | |
30 | }] | |
c6ddbdb6 D |
31 | |
32 | def _real_extract(self, url): | |
33 | display_id = self._match_id(url) | |
a6762c4a | 34 | |
be96f992 | 35 | webpage = self._download_webpage(url, display_id) |
c6ddbdb6 | 36 | |
a6762c4a S |
37 | if '>Queued for processing, please stand by...<' in webpage: |
38 | raise ExtractorError( | |
39 | 'Audio is still queued for processing', expected=True) | |
f03a8a3c | 40 | |
be96f992 RA |
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()] | |
f03a8a3c | 51 | self._sort_formats(formats) |
c6ddbdb6 D |
52 | |
53 | return { | |
be96f992 | 54 | 'id': compat_str(talk.get('id') or display_id), |
a6762c4a S |
55 | 'display_id': display_id, |
56 | 'title': title, | |
be96f992 RA |
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')), | |
a6762c4a | 61 | 'formats': formats, |
c6ddbdb6 | 62 | } |