]>
Commit | Line | Data |
---|---|---|
1 | from __future__ import unicode_literals | |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..utils import str_to_int | |
7 | ||
8 | ||
9 | class DrTuberIE(InfoExtractor): | |
10 | _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)' | |
11 | _TEST = { | |
12 | 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', | |
13 | 'md5': '93e680cf2536ad0dfb7e74d94a89facd', | |
14 | 'info_dict': { | |
15 | 'id': '1740434', | |
16 | 'ext': 'mp4', | |
17 | 'title': 'Hot Perky Blonde Naked Golf', | |
18 | 'like_count': int, | |
19 | 'dislike_count': int, | |
20 | 'comment_count': int, | |
21 | 'categories': list, # NSFW | |
22 | 'thumbnail': 're:https?://.*\.jpg$', | |
23 | 'age_limit': 18, | |
24 | } | |
25 | } | |
26 | ||
27 | def _real_extract(self, url): | |
28 | mobj = re.match(self._VALID_URL, url) | |
29 | video_id = mobj.group('id') | |
30 | display_id = mobj.group('display_id') | |
31 | ||
32 | webpage = self._download_webpage(url, display_id) | |
33 | ||
34 | video_url = self._html_search_regex( | |
35 | r'<source src="([^"]+)"', webpage, 'video URL') | |
36 | ||
37 | title = self._html_search_regex( | |
38 | r'<title>([^<]+)\s*-\s*Free', webpage, 'title') | |
39 | ||
40 | thumbnail = self._html_search_regex( | |
41 | r'poster="([^"]+)"', | |
42 | webpage, 'thumbnail', fatal=False) | |
43 | ||
44 | like_count = str_to_int(self._html_search_regex( | |
45 | r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', | |
46 | webpage, 'like count', fatal=False)) | |
47 | dislike_count = str_to_int(self._html_search_regex( | |
48 | r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', | |
49 | webpage, 'like count', fatal=False)) | |
50 | comment_count = str_to_int(self._html_search_regex( | |
51 | r'<span class="comments_count">([\d,\.]+)</span>', | |
52 | webpage, 'comment count', fatal=False)) | |
53 | ||
54 | cats_str = self._html_search_regex( | |
55 | r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) | |
56 | categories = None if cats_str is None else cats_str.split(' ') | |
57 | ||
58 | return { | |
59 | 'id': video_id, | |
60 | 'display_id': display_id, | |
61 | 'url': video_url, | |
62 | 'title': title, | |
63 | 'thumbnail': thumbnail, | |
64 | 'like_count': like_count, | |
65 | 'dislike_count': dislike_count, | |
66 | 'comment_count': comment_count, | |
67 | 'categories': categories, | |
68 | 'age_limit': self._rta_search(webpage), | |
69 | } |