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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
orderedSet,
parse_duration,
parse_resolution,
str_to_int,
url_or_none,
urlencode_postdata,
)
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
_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 = []
def extract_format(format_id, format_url):
f_url = url_or_none(format_url)
if not f_url:
return
f = parse_resolution(format_id)
f.update({
'url': f_url,
'format_id': format_id,
})
formats.append(f)
STREAM_URL_PREFIX = 'stream_url_'
for mobj in re.finditer(
r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
% STREAM_URL_PREFIX, webpage):
extract_format(mobj.group('id', 'url'))
if not formats:
stream_key = self._search_regex(
r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'stream key', group='value')
sb_csrf_session = self._get_cookies(
'https://spankbang.com')['sb_csrf_session'].value
stream = self._download_json(
'https://spankbang.com/api/videos/stream', video_id,
'Downloading stream JSON', data=urlencode_postdata({
'id': stream_key,
'data': 0,
'sb_csrf_session': sb_csrf_session,
}), headers={
'Referer': url,
'X-CSRFToken': sb_csrf_session,
})
for format_id, format_url in stream.items():
if format_id.startswith(STREAM_URL_PREFIX):
extract_format(
format_id[len(STREAM_URL_PREFIX):], format_url)
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,
}
class SpankBangPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
_TEST = {
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
'info_dict': {
'id': 'ug0k',
'title': 'Big Ass Titties',
},
'playlist_mincount': 50,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
entries = [self.url_result(
'https://spankbang.com/%s/video' % video_id,
ie=SpankBangIE.ie_key(), video_id=video_id)
for video_id in orderedSet(re.findall(
r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
title = self._html_search_regex(
r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
fatal=False)
return self.playlist_result(entries, playlist_id, title)
|
