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
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
str_to_int,
)
class VpornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
_TEST = {
'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
'md5': 'facf37c1b86546fa0208058546842c55',
'info_dict': {
'id': '497944',
'display_id': 'violet-on-her-th-birthday',
'ext': 'mp4',
'title': 'Violet on her 19th birthday',
'description': 'Violet dances in front of the camera which is sure to get you horny.',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'kileyGrope',
'categories': ['Masturbation', 'Teen'],
'duration': 393,
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(
r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
description = self._html_search_regex(
r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
if thumbnail:
thumbnail = 'http://www.vporn.com' + thumbnail
uploader = self._html_search_regex(
r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>',
webpage, 'uploader', fatal=False)
categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex(
r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False))
view_count = str_to_int(self._html_search_regex(
r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex(
r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._html_search_regex(
r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
formats = []
for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage):
video_url = video[1]
fmt = {
'url': video_url,
'format_id': video[0],
}
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
if m:
fmt.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
'vbr': int(m.group('vbr')),
})
formats.append(fmt)
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'categories': categories,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'age_limit': 18,
'formats': formats,
}
|
