]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/worldstarhiphop.py
5b9779c05853ab815aa56d710476356c56c8449b
[youtubedl] / youtube_dl / extractor / worldstarhiphop.py
1 import re
2
3 from .common import InfoExtractor
4
5
6 class WorldStarHipHopIE(InfoExtractor):
7 _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
8 _TEST = {
9 "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
10 "file": "wshh6a7q1ny0G34ZwuIO.mp4",
11 "md5": "9d04de741161603bf7071bbf4e883186",
12 "info_dict": {
13 "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
14 }
15 }
16
17
18 def _real_extract(self, url):
19 m = re.match(self._VALID_URL, url)
20 video_id = m.group('id')
21
22 webpage_src = self._download_webpage(url, video_id)
23
24 video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
25 webpage_src, u'video URL')
26
27 if 'youtube' in video_url:
28 self.to_screen(u'Youtube video detected:')
29 return self.url_result(video_url, ie='Youtube')
30
31 if 'mp4' in video_url:
32 ext = 'mp4'
33 else:
34 ext = 'flv'
35
36 video_title = self._html_search_regex(r"<title>(.*)</title>",
37 webpage_src, u'title')
38
39 # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
40 thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
41 webpage_src, u'thumbnail', fatal=False)
42
43 if not thumbnail:
44 _title = r"""candytitles.*>(.*)</span>"""
45 mobj = re.search(_title, webpage_src)
46 if mobj is not None:
47 video_title = mobj.group(1)
48
49 results = [{
50 'id': video_id,
51 'url' : video_url,
52 'title' : video_title,
53 'thumbnail' : thumbnail,
54 'ext' : ext,
55 }]
56 return results