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
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unified_strdate,
str_to_int,
int_or_none,
parse_duration,
)
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TESTS = [
{
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
'info_dict': {
'id': '1509445',
'ext': 'mp4',
'title': 'FemaleAgent Shy beauty takes the bait',
'upload_date': '20121014',
'uploader_id': 'Ruseful2011',
'duration': 893,
'age_limit': 18,
}
},
{
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
'info_dict': {
'id': '2221348',
'ext': 'mp4',
'title': 'Britney Spears Sexy Booty',
'upload_date': '20130914',
'uploader_id': 'jojo747400',
'duration': 200,
'age_limit': 18,
}
},
{
'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
'info_dict': {
'id': '2272726',
'ext': 'mp4',
'title': 'Amber slayed by the Knight',
'upload_date': '20131009',
'uploader_id': 'amberblank',
'duration': 149,
'age_limit': 18,
}
},
{
"url": "https://xhamster.com/movies/1444747/hotkinkyjo_amp_asian_girl_elbow_deep_anal_fisting_and_footing.html",
'info_dict': {
"id": "1444747",
'ext': 'mp4',
"title": "HOTKINKYJO & ASIAN GIRL ELBOW DEEP ANAL FISTING AND FOOTING",
"upload_date": "20120922",
"uploader_id": "alex1981",
"duration": 80,
"age_limit": 18,
}
}
]
def _real_extract(self, url):
def extract_video_url(webpage):
mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
if mp4 is None:
raise ExtractorError('Unable to extract media URL')
else:
return mp4.group(1)
def is_hd(webpage):
return '<div class=\'icon iconHD\'' in webpage
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
seo = mobj.group('seo')
proto = mobj.group('proto')
mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
webpage = self._download_webpage(mrss_url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
# Only a few videos have an description
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
description = mobj.group(1) if mobj else None
upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
webpage, 'upload date', fatal=False)
if upload_date:
upload_date = unified_strdate(upload_date)
uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
webpage, 'uploader id', default='anonymous')
thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
webpage, 'duration', fatal=False))
view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
if view_count:
view_count = str_to_int(view_count)
mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
comment_count = mobj.group('commentcount') if mobj else 0
age_limit = self._rta_search(webpage)
hd = is_hd(webpage)
video_url = extract_video_url(webpage)
formats = [{
'url': video_url,
'format_id': 'hd' if hd else 'sd',
'preference': 1,
}]
if not hd:
mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
if is_hd(webpage):
video_url = extract_video_url(webpage)
formats.append({
'url': video_url,
'format_id': 'hd',
'preference': 2,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'upload_date': upload_date,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'like_count': int_or_none(like_count),
'dislike_count': int_or_none(dislike_count),
'comment_count': int_or_none(comment_count),
'age_limit': age_limit,
'formats': formats,
}
|
