]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hellporno.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
13 class HellPornoIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
16 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
17 'md5': '1fee339c610d2049699ef2aa699439f1',
20 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
22 'title': 'Dixie is posing with naked ass very erotic',
23 'thumbnail': r
're:https?://.*\.jpg$',
27 'url': 'http://hellporno.net/v/186271/',
28 'only_matching': True,
31 def _real_extract(self
, url
):
32 display_id
= self
._match
_id
(url
)
34 webpage
= self
._download
_webpage
(url
, display_id
)
36 title
= remove_end(self
._html
_search
_regex
(
37 r
'<title>([^<]+)</title>', webpage
, 'title'), ' - Hell Porno')
39 flashvars
= self
._parse
_json
(self
._search
_regex
(
40 r
'var\s+flashvars\s*=\s*({.+?});', webpage
, 'flashvars'),
41 display_id
, transform_source
=js_to_json
)
43 video_id
= flashvars
.get('video_id')
44 thumbnail
= flashvars
.get('preview_url')
45 ext
= determine_ext(flashvars
.get('postfix'), 'mp4')
48 for video_url_key
in ['video_url', 'video_alt_url']:
49 video_url
= flashvars
.get(video_url_key
)
52 video_text
= flashvars
.get('%s_text' % video_url_key
)
56 'format_id': video_text
,
58 m
= re
.search(r
'^(?P<height>\d+)[pP]', video_text
)
60 fmt
['height'] = int(m
.group('height'))
62 self
._sort
_formats
(formats
)
64 categories
= self
._html
_search
_meta
(
65 'keywords', webpage
, 'categories', default
='').split(',')
69 'display_id': display_id
,
71 'thumbnail': thumbnail
,
72 'categories': categories
,