_ Git - youtube-dl/blob - 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
  10     def _real_extract(self, url):
  11         m = re.match(self._VALID_URL, url)
  12         video_id = m.group('id')
  13
  14         webpage_src = self._download_webpage(url, video_id)
  15
  16         video_url_base64 = self._search_regex(r'data-path="(.*?)"',
  17             webpage_src, u'video URL', fatal=False)
  18
  19         if video_url_base64 == None:
  20             video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
  21                 u'video URL')
  22             return self.url_result(video_url, ie='Youtube')
  23
  24         video_url = base64.b64decode(video_url_base64).decode('utf-8')
  25
  26         video_title = self._html_search_regex(r"<title>(.*)</title>",
  27             webpage_src, u'title')
  28
  29         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  30         thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
  31             webpage_src, u'thumbnail', fatal=False)
  32
  33         results = [{
  34                     'id': video_id,
  35                     'url' : video_url,
  36                     'title' : video_title,
  37                     'thumbnail' : thumbnail,
  38                     'ext' : 'mp3',
  39                     }]
  40         return results