4 from .common
import InfoExtractor
6 compat_urllib_parse_urlparse
,
10 class XTubeIE(InfoExtractor
):
11 _VALID_URL
= r
'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
13 u
'url': u
'http://www.xtube.com/watch.php?v=kVTUy_G222_',
14 u
'file': u
'kVTUy_G222_.mp4',
15 u
'md5': u
'092fbdd3cbe292c920ef6fc6a8a9cdab',
17 u
"title": u
"strange erotica",
18 u
"description": u
"surreal gay themed erotica...almost an ET kind of thing",
19 u
"uploader": u
"greenshowers",
24 def _real_extract(self
, url
):
25 mobj
= re
.match(self
._VALID
_URL
, url
)
26 video_id
= mobj
.group('videoid')
27 url
= 'http://www.' + mobj
.group('url')
29 req
= compat_urllib_request
.Request(url
)
30 req
.add_header('Cookie', 'age_verified=1')
31 webpage
= self
._download
_webpage
(req
, video_id
)
33 video_title
= self
._html
_search
_regex
(r
'<div class="p_5px[^>]*>([^<]+)', webpage
, u
'title')
34 video_uploader
= self
._html
_search
_regex
(r
'so_s\.addVariable\("owner_u", "([^"]+)', webpage
, u
'uploader', fatal
=False)
35 video_description
= self
._html
_search
_regex
(r
'<p class="video_description">([^<]+)', webpage
, u
'description', default
=None)
36 video_url
= self
._html
_search
_regex
(r
'var videoMp4 = "([^"]+)', webpage
, u
'video_url').replace('\\/', '/')
37 path
= compat_urllib_parse_urlparse(video_url
).path
38 extension
= os
.path
.splitext(path
)[1][1:]
39 format
= path
.split('/')[5].split('_')[:2]
42 format
= "-".join(format
)
47 'uploader': video_uploader
,
48 'description': video_description
,