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
|
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
js_to_json,
parse_filesize,
str_to_int,
)
class PornComIE(InfoExtractor):
_VALID_URL = r'https?://(?:[a-zA-Z]+\.)?porn\.com/videos/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.porn.com/videos/teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec-2603339',
'md5': '3f30ce76267533cd12ba999263156de7',
'info_dict': {
'id': '2603339',
'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec',
'ext': 'mp4',
'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 551,
'view_count': int,
'age_limit': 18,
'categories': list,
'tags': list,
},
}, {
'url': 'http://se.porn.com/videos/marsha-may-rides-seth-on-top-of-his-thick-cock-2658067',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
config = self._parse_json(
self._search_regex(
(r'=\s*({.+?})\s*;\s*v1ar\b',
r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='),
webpage, 'config', default='{}'),
display_id, transform_source=js_to_json, fatal=False)
if config:
title = config['title']
formats = [{
'url': stream['url'],
'format_id': stream.get('id'),
'height': int_or_none(self._search_regex(
r'^(\d+)[pP]', stream.get('id') or '', 'height', default=None))
} for stream in config['streams'] if stream.get('url')]
thumbnail = (compat_urlparse.urljoin(
config['thumbCDN'], config['poster'])
if config.get('thumbCDN') and config.get('poster') else None)
duration = int_or_none(config.get('length'))
else:
title = self._search_regex(
(r'<title>([^<]+)</title>', r'<h1[^>]*>([^<]+)</h1>'),
webpage, 'title')
formats = [{
'url': compat_urlparse.urljoin(url, format_url),
'format_id': '%sp' % height,
'height': int(height),
'filesize_approx': parse_filesize(filesize),
} for format_url, height, filesize in re.findall(
r'<a[^>]+href="(/download/[^"]+)">[^<]*?(\d+)p<span[^>]*>(\d+\s*[a-zA-Z]+)<',
webpage)]
thumbnail = None
duration = None
view_count = str_to_int(self._search_regex(
(r'Views:\s*</span>\s*<span>\s*([\d,.]+)',
r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage,
'view count', fatal=False))
def extract_list(kind):
s = self._search_regex(
(r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(),
r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()),
webpage, kind, fatal=False)
return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'formats': formats,
'age_limit': 18,
'categories': extract_list('categories'),
'tags': extract_list('tags'),
}
|
