_ 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     IE_NAME = u'HotNewHipHop'
  10
  11     def _real_extract(self, url):
  12         m = re.match(self._VALID_URL, url)
  13         video_id = m.group('id')
  14
  15         webpage_src = self._download_webpage(url, video_id)
  16
  17         video_url_base64 = self._search_regex(r'data-path="(.*?)"',
  18             webpage_src, u'video URL', fatal=False)
  19
  20         if video_url_base64 == None:
  21             video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
  22                 u'video URL')
  23             return self.url_result(video_url, ie='Youtube')
  24
  25         video_url = base64.b64decode(video_url_base64)
  26
  27         video_title = self._html_search_regex(r"<title>(.*)</title>",
  28             webpage_src, u'title')
  29
  30         #"og:image" content=
  31         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  32         thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
  33             webpage_src, u'thumbnail', fatal=False)
  34
  35         results = [{
  36                     'id': video_id,
  37                     'url' : video_url,
  38                     'title' : video_title,
  39                     'thumbnail' : thumbnail,
  40                     'ext' : 'mp3',
  41                     }]
  42         return results