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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_duration,
parse_resolution,
str_to_int,
)
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)'
_TESTS = [{
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
'id': '3vvn',
'ext': 'mp4',
'title': 'fantasy solo',
'description': 'dillion harper masturbates on a bed',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'silly2587',
'age_limit': 18,
}
}, {
# 480p only
'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
'only_matching': True,
}, {
# no uploader
'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
'only_matching': True,
}, {
# mobile page
'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
'only_matching': True,
}, {
# 4k
'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
'only_matching': True,
}, {
'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
'only_matching': True,
}, {
'url': 'https://m.spankbang.com/3vvn/play',
'only_matching': True,
}, {
'url': 'https://spankbang.com/2y3td/embed/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
video_id, headers={'Cookie': 'country=US'})
if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
formats = []
for mobj in re.finditer(
r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
webpage):
format_id, format_url = mobj.group('id', 'url')
f = parse_resolution(format_id)
f.update({
'url': format_url,
'format_id': format_id,
})
formats.append(f)
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
description = self._search_regex(
r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*><img[^>]+>([^<]+)',
webpage, 'uploader', default=None)
duration = parse_duration(self._search_regex(
r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'formats': formats,
'age_limit': age_limit,
}
|
