]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/behindkink.py
2 from __future__
import unicode_literals
6 from . common
import InfoExtractor
7 from .. utils
import url_basename
10 class BehindKinkIE ( InfoExtractor
):
11 _VALID_URL
= r
'(?:http://)(?:www\.)?behindkink\.com/(?P<year>[0-9] {4} )/(?P<month>[0-9] {2} )/(?P<day>[0-9] {2} )/(?P<id>[^/?_]+)'
13 'url' : 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/' ,
14 'md5' : '41ad01222b8442089a55528fec43ec01' ,
18 'title' : 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!' ,
19 'description' : 'The adult industry voice was finally heard as Assembly Bill 1576 remained \xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...' ,
20 'upload_date' : '20140814' ,
21 'thumbnail' : 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg' ,
26 def _real_extract ( self
, url
):
27 mobj
= re
. match ( self
._ VALID
_U RL
, url
)
28 display_id
= mobj
. group ( 'id' )
29 year
= mobj
. group ( 'year' )
30 month
= mobj
. group ( 'month' )
31 day
= mobj
. group ( 'day' )
32 upload_date
= year
+ month
+ day
34 webpage_url
= 'http://www.behindkink.com/' + year
+ '/' + month
+ '/' + day
+ '/' + display_id
35 webpage
= self
._ download
_ webpage
( webpage_url
, display_id
)
37 self
. report_extraction ( display_id
)
38 video_url
= self
._ search
_ regex
(
39 r
"'file':\s*'([^']+)'" ,
42 video_id
= url_basename ( video_url
)
43 video_id
= video_id
. split ( '_' )[ 0 ]
44 self
. report_extraction ( video_id
)
50 'title' : self
._ og
_ search
_ title
( webpage
),
51 'display_id' : display_id
,
52 'thumbnail' : self
._ og
_ search
_ thumbnail
( webpage
),
53 'description' : self
._ og
_ search
_ description
( webpage
),
54 'upload_date' : upload_date
,