]>
jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/pornoxo.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
11 class PornoXOIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
14 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
15 'md5': '582f28ecbaa9e6e24cb90f50f524ce87',
19 'title': 'Striptease From Sexy Secretary!',
20 'display_id': 'striptease-from-sexy-secretary',
21 'description': 'md5:0ee35252b685b3883f4a1d38332f9980',
22 'categories': list, # NSFW
23 'thumbnail': r
're:https?://.*\.jpg$',
28 def _real_extract(self
, url
):
29 mobj
= re
.match(self
._VALID
_URL
, url
)
30 video_id
, display_id
= mobj
.groups()
32 webpage
= self
._download
_webpage
(url
, video_id
)
33 video_data
= self
._extract
_jwplayer
_data
(webpage
, video_id
, require_title
=False)
35 title
= self
._html
_search
_regex
(
36 r
'<title>([^<]+)\s*-\s*PornoXO', webpage
, 'title')
38 view_count
= str_to_int(self
._html
_search
_regex
(
39 r
'[vV]iews:\s*([0-9,]+)', webpage
, 'view count', fatal
=False))
41 categories_str
= self
._html
_search
_regex
(
42 r
'<meta name="description" content=".*featuring\s*([^"]+)"',
43 webpage
, 'categories', fatal
=False)
45 None if categories_str
is None
46 else categories_str
.split(','))
51 'display_id': display_id
,
52 'description': self
._html
_search
_meta
('description', webpage
),
53 'categories': categories
,
54 'view_count': view_count
,