]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/scivee.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from ..utils
import int_or_none
9 class SciVeeIE(InfoExtractor
):
10 _VALID_URL
= r
'https?://(?:www\.)?scivee\.tv/node/(?P<id>\d+)'
13 'url': 'http://www.scivee.tv/node/62352',
14 'md5': 'b16699b74c9e6a120f6772a44960304f',
18 'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
19 'description': 'md5:81f1710638e11a481358fab1b11059d7',
21 'skip': 'Not accessible from Travis CI server',
24 def _real_extract(self
, url
):
25 mobj
= re
.match(self
._VALID
_URL
, url
)
26 video_id
= mobj
.group('id')
28 # annotations XML is malformed
29 annotations
= self
._download
_webpage
(
30 'http://www.scivee.tv/assets/annotations/%s' % video_id
, video_id
, 'Downloading annotations')
32 title
= self
._html
_search
_regex
(r
'<title>([^<]+)</title>', annotations
, 'title')
33 description
= self
._html
_search
_regex
(r
'<abstract>([^<]+)</abstract>', annotations
, 'abstract', fatal
=False)
34 filesize
= int_or_none(self
._html
_search
_regex
(
35 r
'<filesize>([^<]+)</filesize>', annotations
, 'filesize', fatal
=False))
39 'url': 'http://www.scivee.tv/assets/audio/%s' % video_id
,
44 'url': 'http://www.scivee.tv/assets/video/%s' % video_id
,
54 'description': description
,
55 'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id
,