youtube_dl/extractor/hotnewhiphop.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_parse
   7 from ..utils import (
   8     ExtractorError,
   9     HEADRequest,
  10     sanitized_Request,
  11 )
  12
  13
  14 class HotNewHipHopIE(InfoExtractor):
  15     _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
  16     _TEST = {
  17         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
  18         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
  19         'info_dict': {
  20             'id': '1435540',
  21             'ext': 'mp3',
  22             'title': 'Freddie Gibbs - Lay It Down'
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         video_url_base64 = self._search_regex(
  31             r'data-path="(.*?)"', webpage, 'video URL', default=None)
  32
  33         if video_url_base64 is None:
  34             video_url = self._search_regex(
  35                 r'"contentUrl" content="(.*?)"', webpage, 'content URL')
  36             return self.url_result(video_url, ie='Youtube')
  37
  38         reqdata = compat_urllib_parse.urlencode([
  39             ('mediaType', 's'),
  40             ('mediaId', video_id),
  41         ])
  42         r = sanitized_Request(
  43             'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
  44         r.add_header('Content-Type', 'application/x-www-form-urlencoded')
  45         mkd = self._download_json(
  46             r, video_id, note='Requesting media key',
  47             errnote='Could not download media key')
  48         if 'mediaKey' not in mkd:
  49             raise ExtractorError('Did not get a media key')
  50
  51         redirect_url = base64.b64decode(video_url_base64).decode('utf-8')
  52         redirect_req = HEADRequest(redirect_url)
  53         req = self._request_webpage(
  54             redirect_req, video_id,
  55             note='Resolving final URL', errnote='Could not resolve final URL')
  56         video_url = req.geturl()
  57         if video_url.endswith('.html'):
  58             raise ExtractorError('Redirect failed')
  59
  60         video_title = self._og_search_title(webpage).strip()
  61
  62         return {
  63             'id': video_id,
  64             'url': video_url,
  65             'title': video_title,
  66             'thumbnail': self._og_search_thumbnail(webpage),
  67         }