1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unescapeHTML,
determine_ext,
ExtractorError,
)
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?P<url>(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html(?:\?.*)?)'
_TEST = {
u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
u'file': u'1509445.flv',
u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
u'info_dict': {
u"upload_date": u"20121014",
u"uploader_id": u"Ruseful2011",
u"title": u"FemaleAgent Shy beauty takes the bait"
}
}
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mrss_url = 'http://' + mobj.group('url')
webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0:
video_url = compat_urllib_parse.unquote(mobj.group('file'))
else:
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title')
# Only a few videos have an description
mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
if mobj:
video_description = unescapeHTML(mobj.group('description'))
else:
video_description = None
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj:
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
video_upload_date = None
self._downloader.report_warning(u'Unable to extract upload date')
video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
webpage, u'uploader id', default=u'anonymous')
video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
'url': video_url,
'ext': determine_ext(video_url),
'title': video_title,
'description': video_description,
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail
}]
|
