]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/pornhd.py
1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
14 class PornHdIE(InfoExtractor
):
15 _VALID_URL
= r
'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
17 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
18 'md5': '956b8ca569f7f4d8ec563e2c41598441',
21 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
23 'title': 'Sierra loves doing laundry',
24 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
25 'thumbnail': 're:^https?://.*\.jpg',
31 def _real_extract(self
, url
):
32 mobj
= re
.match(self
._VALID
_URL
, url
)
33 video_id
= mobj
.group('id')
34 display_id
= mobj
.group('display_id')
36 webpage
= self
._download
_webpage
(url
, display_id
or video_id
)
38 title
= self
._html
_search
_regex
(
39 r
'<title>(.+) porn HD.+?</title>', webpage
, 'title')
40 description
= self
._html
_search
_regex
(
41 r
'<div class="description">([^<]+)</div>', webpage
, 'description', fatal
=False)
42 view_count
= int_or_none(self
._html
_search
_regex
(
43 r
'(\d+) views\s*</span>', webpage
, 'view count', fatal
=False))
44 thumbnail
= self
._search
_regex
(
45 r
"'poster'\s*:\s*'([^']+)'", webpage
, 'thumbnail', fatal
=False)
47 quality
= qualities(['sd', 'hd'])
48 sources
= json
.loads(js_to_json(self
._search
_regex
(
49 r
"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage
, 'sources')))
51 for container
, s
in sources
.items():
52 for qname
, video_url
in s
.items():
55 'container': container
,
56 'format_id': '%s-%s' % (container
, qname
),
57 'quality': quality(qname
),
59 self
._sort
_formats
(formats
)
63 'display_id': display_id
,
65 'description': description
,
66 'thumbnail': thumbnail
,
67 'view_count': view_count
,