youtube_dl/extractor/hotnewhiphop.py

   1 import re
   2 import base64
   3
   4 from .common import InfoExtractor
   5
   6
   7 class HotNewHipHopIE(InfoExtractor):
   8     _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
   9     _TEST = {
  10         u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html",
  11         u'file': u'1435540.mp3',
  12         u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
  13         u'info_dict': {
  14             u"title": u"Freddie Gibbs - Lay It Down"
  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_base64 = self._search_regex(r'data-path="(.*?)"',
  25             webpage_src, u'video URL', fatal=False)
  26
  27         if video_url_base64 == None:
  28             video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
  29                 u'video URL')
  30             return self.url_result(video_url, ie='Youtube')
  31
  32         video_url = base64.b64decode(video_url_base64).decode('utf-8')
  33
  34         video_title = self._html_search_regex(r"<title>(.*)</title>",
  35             webpage_src, u'title')
  36
  37         results = [{
  38                     'id': video_id,
  39                     'url' : video_url,
  40                     'title' : video_title,
  41                     'thumbnail' : self._og_search_thumbnail(webpage_src),
  42                     'ext' : 'mp3',
  43                     }]
  44         return results