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
172
173
174
175
176
177
|
from __future__ import unicode_literals
import itertools
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
orderedSet,
parse_duration,
sanitized_Request,
str_to_int,
)
class XTubeIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
xtube:|
https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-)
)
(?P<id>[^/?&#]+)
'''
_TESTS = [{
# old URL schema
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
'info_dict': {
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'view_count': int,
'comment_count': int,
'age_limit': 18,
}
}, {
# FLV videos with duplicated formats
'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
'md5': 'a406963eb349dd43692ec54631efd88b',
'info_dict': {
'id': '9299752',
'display_id': 'A-Super-Run-Part-1-YT',
'ext': 'flv',
'title': 'A Super Run - Part 1 (YT)',
'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
'uploader': 'tshirtguy59',
'duration': 579,
'view_count': int,
'comment_count': int,
'age_limit': 18,
},
}, {
# new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
'only_matching': True,
}, {
'url': 'xtube:625837',
'only_matching': True,
}, {
'url': 'xtube:kVTUy_G222_',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
if not display_id:
display_id = video_id
if video_id.isdigit() and len(video_id) < 11:
url_pattern = 'http://www.xtube.com/video-watch/-%s'
else:
url_pattern = 'http://www.xtube.com/watch.php?v=%s'
webpage = self._download_webpage(
url_pattern % video_id, display_id, headers={
'Cookie': 'age_verified=1; cookiesAccepted=1',
})
sources = self._parse_json(self._search_regex(
r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
webpage, 'sources', group='sources'), video_id,
transform_source=js_to_json)
formats = []
for format_id, format_url in sources.items():
formats.append({
'url': format_url,
'format_id': format_id,
'height': int_or_none(format_id),
})
self._remove_duplicate_formats(formats)
self._sort_formats(formats)
title = self._search_regex(
(r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
webpage, 'title', group='title')
description = self._search_regex(
r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
uploader = self._search_regex(
(r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
webpage, 'uploader', fatal=False)
duration = parse_duration(self._search_regex(
r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'>Comments? \(([\d,\.]+)\)<',
webpage, 'comment count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
'age_limit': 18,
'formats': formats,
}
class XTubeUserIE(InfoExtractor):
IE_DESC = 'XTube user profile'
_VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
_TEST = {
'url': 'http://www.xtube.com/profile/greenshowers-4056496',
'info_dict': {
'id': 'greenshowers-4056496',
'age_limit': 18,
},
'playlist_mincount': 155,
}
def _real_extract(self, url):
user_id = self._match_id(url)
entries = []
for pagenum in itertools.count(1):
request = sanitized_Request(
'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
headers={
'Cookie': 'popunder=4',
'X-Requested-With': 'XMLHttpRequest',
'Referer': url,
})
page = self._download_json(
request, user_id, 'Downloading videos JSON page %d' % pagenum)
html = page.get('html')
if not html:
break
for video_id in orderedSet([video_id for _, video_id in re.findall(
r'data-plid=(["\'])(.+?)\1', html)]):
entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
page_count = int_or_none(page.get('pageCount'))
if not page_count or pagenum == page_count:
break
playlist = self.playlist_result(entries, user_id)
playlist['age_limit'] = 18
return playlist
|
