_ 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         print video_id
  18
  19         video_url_base64 = self._search_regex(r'data-path="(.*?)"',
  20             webpage_src, u'video URL')
  21
  22         video_url = base64.b64decode(video_url_base64)
  23
  24         video_title = self._html_search_regex(r"<title>(.*)</title>",
  25             webpage_src, u'title')
  26
  27         #"og:image" content=
  28         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  29         thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
  30             webpage_src, u'thumbnail', fatal=False)
  31
  32         results = [{
  33                     'id': video_id,
  34                     'url' : video_url,
  35                     'title' : video_title,
  36                     'thumbnail' : thumbnail,
  37                     'ext' : 'mp3',
  38                     }]
  39         return results