Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/breakcom.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class BreakIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
   8     _TEST = {
   9         u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
  10         u'file': u'2468056.mp4',
  11         u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
  12         u'info_dict': {
  13             u"title": u"When Girls Act Like D-Bags"
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         video_id = mobj.group(1).split("-")[-1]
  20         webpage = self._download_webpage(url, video_id)
  21         video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
  22         key = re.search(r"icon: '(.+?)',",webpage).group(1)
  23         final_url = str(video_url)+"?"+str(key)
  24         thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
  25         title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
  26         ext = video_url.split('.')[-1]
  27         return [{
  28             'id':        video_id,
  29             'url':       final_url,
  30             'ext':       ext,
  31             'title':     title,
  32             'thumbnail': thumbnail_url,
  33         }]