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
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
NO_DEFAULT,
str_to_int,
)
class DrTuberIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
'display_id': 'hot-perky-blonde-naked-golf',
'ext': 'mp4',
'title': 'hot perky blonde naked golf',
'like_count': int,
'comment_count': int,
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}, {
'url': 'http://www.drtuber.com/embed/489939',
'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') or video_id
webpage = self._download_webpage(
'http://www.drtuber.com/video/%s' % video_id, display_id)
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
(r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
webpage, 'title')
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
def extract_count(id_, name, default=NO_DEFAULT):
return str_to_int(self._html_search_regex(
r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
webpage, '%s count' % name, default=default, fatal=False))
like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
comment_count = extract_count('comments_count', 'comment')
cats_str = self._search_regex(
r'<div[^>]+class="categories_list">(.+?)</div>',
webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(
r'<a title="([^"]+)"', cats_str)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'categories': categories,
'age_limit': self._rta_search(webpage),
}
|
