63 lines
2.1 KiB

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