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
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class EmpflixIE(InfoExtractor):
_VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
'md5': 'b1bc15b6412d33902d6e5952035fcabc',
'info_dict': {
'id': '33051',
'ext': 'mp4',
'title': 'Amateur Finger Fuck',
'description': 'Amateur solo finger fucking.',
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
video_title = self._html_search_regex(
r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
video_description = self._html_search_regex(
r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
cfg_url = self._html_search_regex(
r'flashvars\.config = escape\("([^"]+)"',
webpage, 'flashvars.config')
# XML is malformed
cfg_xml = self._download_webpage(
cfg_url, video_id, note='Downloading metadata')
formats = [
{
'url': item[1],
'format_id': item[0],
} for item in re.findall(
r'<item>\s*<res>([^>]+)</res>\s*<videoLink>([^<]+)</videoLink>\s*</item>', cfg_xml)
]
return {
'id': video_id,
'title': video_title,
'description': video_description,
'formats': formats,
'age_limit': age_limit,
}
|
