]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/closertotruth.py
3 from .common
import InfoExtractor
6 class CloserToTruthIE(InfoExtractor
):
8 _VALID_URL
= r
'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
10 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
13 'display_id': 'solutions-the-mind-body-problem',
15 'title': 'Solutions to the Mind-Body Problem?',
16 'upload_date': '20140221',
17 'timestamp': 1392956007,
18 'uploader_id': 'CTTXML'
21 'skip_download': True,
24 'url': 'http://closertotruth.com/episodes/how-do-brains-work',
27 'display_id': 'how-do-brains-work',
29 'title': 'How do Brains Work?',
30 'upload_date': '20140221',
31 'timestamp': 1392956024,
32 'uploader_id': 'CTTXML'
35 'skip_download': True,
38 'url': 'http://closertotruth.com/interviews/1725',
43 'playlist_mincount': 2,
46 def _real_extract(self
, url
):
47 display_id
= self
._match
_id
(url
)
49 webpage
= self
._download
_webpage
(url
, display_id
)
51 partner_id
= self
._search
_regex
(
52 r
'<script[^>]+src=["\'].*?
\b(?
:partner_id|p
)/(\d
+)',
53 webpage, 'kaltura partner_id
')
55 title = self._html_extract_title(webpage, 'video title
')
57 select = self._search_regex(
58 r'(?s
)<select
[^
>]+id="select-version"[^
>]*>(.+?
)</select
>',
59 webpage, 'select version
', default=None)
63 for mobj in re.finditer(
64 r'<option
[^
>]+value
=(["\'])(?P<id>[0-9a-z_]+)(?:#.+?)?\1[^>]*>(?P<title>[^<]+)',
66 entry_id = mobj.group('id')
67 if entry_id in entry_ids:
69 entry_ids.add(entry_id)
71 '_type': 'url_transparent',
72 'url': 'kaltura:%s:%s' % (partner_id, entry_id),
74 'title': mobj.group('title'),
77 return self.playlist_result(entries, display_id, title)
79 entry_id = self._search_regex(
80 r'<a[^>]+id=(["\'])embed
-kaltura\
1[^
>]+data
-kaltura
=(["\'])(?P<id>[0-9a-z_]+)\2',
81 webpage, 'kaltura entry_id', group='id')
84 '_type': 'url_transparent',
85 'display_id': display_id,
86 'url': 'kaltura:%s:%s' % (partner_id, entry_id),