]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ndtv.py
255f608783edad0aa3838de028dd8ea07d9ae1b0
1 from __future__
import unicode_literals
3 from .common
import InfoExtractor
11 class NDTVIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?ndtv\.com/video/(?:[^/]+/)+[^/?^&]+-(?P<id>\d+)'
15 'url': 'http://www.ndtv.com/video/news/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal-300710',
16 'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
20 'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
21 'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
22 'upload_date': '20131208',
24 'thumbnail': r
're:https?://.*\.jpg',
28 def _real_extract(self
, url
):
29 video_id
= self
._match
_id
(url
)
30 webpage
= self
._download
_webpage
(url
, video_id
)
32 title
= remove_end(self
._og
_search
_title
(webpage
), ' - NDTV')
34 filename
= self
._search
_regex
(
35 r
"__filename='([^']+)'", webpage
, 'video filename')
36 video_url
= 'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % filename
38 duration
= int_or_none(self
._search
_regex
(
39 r
"__duration='([^']+)'", webpage
, 'duration', fatal
=False))
41 upload_date
= unified_strdate(self
._html
_search
_meta
(
42 'publish-date', webpage
, 'upload date', fatal
=False))
44 description
= remove_end(self
._og
_search
_description
(webpage
), ' (Read more)')
50 'description': description
,
51 'thumbnail': self
._og
_search
_thumbnail
(webpage
),
53 'upload_date': upload_date
,