]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/worldstarhiphop.py
[pornhub] Extract categories and tags (closes #10499)
[youtube-dl] / youtube_dl / extractor / worldstarhiphop.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class WorldStarHipHopIE(InfoExtractor):
9     _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?v=(?P<id>.*)'
10     _TESTS = [{
11         'url': 'http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO',
12         'md5': '9d04de741161603bf7071bbf4e883186',
13         'info_dict': {
14             'id': 'wshh6a7q1ny0G34ZwuIO',
15             'ext': 'mp4',
16             'title': 'KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!'
17         }
18     }, {
19         'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
20         'md5': 'dc1c76c83ecc4190bb1eb143899b87d3',
21         'info_dict': {
22             'id': 'wshh6a7q1ny0G34ZwuIO',
23             'ext': 'mp4',
24             'title': 'KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!'
25         }
26     }]
27
28     def _real_extract(self, url):
29         video_id = self._match_id(url)
30         webpage = self._download_webpage(url, video_id)
31
32         m_vevo_id = re.search(r'videoId=(.*?)&amp?', webpage)
33         if m_vevo_id is not None:
34             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
35
36         video_url = self._search_regex(
37             [r'so\.addVariable\("file","(.*?)"\)',
38              r'<div class="artlist">\s*<a[^>]+href="([^"]+)">'],
39             webpage, 'video URL')
40
41         if 'youtube' in video_url:
42             return self.url_result(video_url, ie='Youtube')
43
44         video_title = self._html_search_regex(
45             [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
46              r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
47             webpage, 'title')
48
49         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
50         thumbnail = self._html_search_regex(
51             r'rel="image_src" href="(.*)" />', webpage, 'thumbnail',
52             default=None)
53         if not thumbnail:
54             _title = r'candytitles.*>(.*)</span>'
55             mobj = re.search(_title, webpage)
56             if mobj is not None:
57                 video_title = mobj.group(1)
58
59         return {
60             'id': video_id,
61             'url': video_url,
62             'title': video_title,
63             'thumbnail': thumbnail,
64         }