]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hornbunny.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
13 class HornBunnyIE(InfoExtractor
):
14 _VALID_URL
= r
'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
16 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
17 'md5': '95e40865aedd08eff60272b704852ad7',
21 'title': 'panty slut jerk off instruction',
27 def _real_extract(self
, url
):
28 mobj
= re
.match(self
._VALID
_URL
, url
)
29 video_id
= mobj
.group('id')
31 webpage
= self
._download
_webpage
(
32 url
, video_id
, note
='Downloading initial webpage')
33 title
= self
._html
_search
_regex
(
34 r
'class="title">(.*?)</h2>', webpage
, 'title')
35 redirect_url
= self
._html
_search
_regex
(
36 r
'pg&settings=(.*?)\|0"\);', webpage
, 'title')
37 webpage2
= self
._download
_webpage
(redirect_url
, video_id
)
38 video_url
= self
._html
_search
_regex
(
39 r
'flvMask:(.*?);', webpage2
, 'video_url')
41 duration
= parse_duration(self
._search
_regex
(
42 r
'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
43 webpage
, 'duration', fatal
=False))
44 view_count
= int_or_none(self
._search
_regex
(
45 r
'<strong>Views:</strong>\s*(\d+)</div>',
46 webpage
, 'view count', fatal
=False))
54 'view_count': view_count
,