1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
8 compat_urllib_parse_urlparse
,
12 class XTubeIE(InfoExtractor
):
13 _VALID_URL
= r
'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
15 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
16 'file': 'kVTUy_G222_.mp4',
17 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
19 "title": "strange erotica",
20 "description": "surreal gay themed erotica...almost an ET kind of thing",
21 "uploader": "greenshowers",
26 def _real_extract(self
, url
):
27 mobj
= re
.match(self
._VALID
_URL
, url
)
28 video_id
= mobj
.group('videoid')
29 url
= 'http://www.' + mobj
.group('url')
31 req
= compat_urllib_request
.Request(url
)
32 req
.add_header('Cookie', 'age_verified=1')
33 webpage
= self
._download
_webpage
(req
, video_id
)
35 video_title
= self
._html
_search
_regex
(r
'<div class="p_5px[^>]*>([^<]+)', webpage
, 'title')
36 video_uploader
= self
._html
_search
_regex
(r
'so_s\.addVariable\("owner_u", "([^"]+)', webpage
, 'uploader', fatal
=False)
37 video_description
= self
._html
_search
_regex
(r
'<p class="video_description">([^<]+)', webpage
, 'description', fatal
=False)
38 video_url
= self
._html
_search
_regex
(r
'var videoMp4 = "([^"]+)', webpage
, 'video_url').replace('\\/', '/')
39 path
= compat_urllib_parse_urlparse(video_url
).path
40 extension
= os
.path
.splitext(path
)[1][1:]
41 format
= path
.split('/')[5].split('_')[:2]
44 format
= "-".join(format
)
49 'uploader': video_uploader
,
50 'description': video_description
,