aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/worldstarhiphop.py
blob: a93928f3c4d653b217e90d24275e7a641cdb7760 (plain)
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
import re

from .common import InfoExtractor


class WorldStarHipHopIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
    _TEST = {
        "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
        "file": "wshh6a7q1ny0G34ZwuIO.mp4",
        "md5": "9d04de741161603bf7071bbf4e883186",
        "info_dict": {
            "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
        }
    }


    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url)
        video_id = m.group('id')

        webpage_src = self._download_webpage(url, video_id)

        video_url = self._search_regex(r'videoId=(.*?)&amp?',
            webpage_src, u'video URL', fatal=False)
        
        if video_url:
            self.to_screen(u'Vevo video detected:')
            return self.url_result('vevo:%s' % video_url, ie='Vevo')

        video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
            webpage_src, u'video URL')

        if video_url == None:
            video_url = self._search_regex(r'videoId=(.*?)&amp?',
                webpage_src, u'video URL')
            self.to_screen(u'Vevo video detected:')
            vevo_id = 'vevo:%s' % video_url
            return self.url_result(vevo_id, ie='Vevo')

        if 'youtube' in video_url:
            self.to_screen(u'Youtube video detected:')
            return self.url_result(video_url, ie='Youtube')

        if 'mp4' in video_url:
            ext = 'mp4'
        else:
            ext = 'flv'

        video_title = self._html_search_regex(r"<title>(.*)</title>",
            webpage_src, u'title')

        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
        thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
            webpage_src, u'thumbnail', fatal=False)

        if not thumbnail:
            _title = r"""candytitles.*>(.*)</span>"""
            mobj = re.search(_title, webpage_src)
            if mobj is not None:
                video_title = mobj.group(1)

        results = [{
                    'id': video_id,
                    'url' : video_url,
                    'title' : video_title,
                    'thumbnail' : thumbnail,
                    'ext' : ext,
                    }]
        return results