]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/worldstarhiphop.py
Imported Upstream version 2014.08.05
[youtubedl] / 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/video\.php\?v=(?P<id>.*)'
10 _TEST = {
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": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
17 }
18 }
19
20 def _real_extract(self, url):
21 m = re.match(self._VALID_URL, url)
22 video_id = m.group('id')
23
24 webpage_src = self._download_webpage(url, video_id)
25
26 m_vevo_id = re.search(r'videoId=(.*?)&amp?',
27 webpage_src)
28 if m_vevo_id is not None:
29 return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
30
31 video_url = self._search_regex(
32 r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL')
33
34 if 'youtube' in video_url:
35 return self.url_result(video_url, ie='Youtube')
36
37 video_title = self._html_search_regex(
38 r"<title>(.*)</title>", webpage_src, 'title')
39
40 # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
41 thumbnail = self._html_search_regex(
42 r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail',
43 fatal=False)
44 if not thumbnail:
45 _title = r"""candytitles.*>(.*)</span>"""
46 mobj = re.search(_title, webpage_src)
47 if mobj is not None:
48 video_title = mobj.group(1)
49
50 return {
51 'id': video_id,
52 'url': video_url,
53 'title': video_title,
54 'thumbnail': thumbnail,
55 }
56