youtube_dl/extractor/hotnewhiphop.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_b64decode
   5 from ..utils import (
   6     ExtractorError,
   7     HEADRequest,
   8     sanitized_Request,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class HotNewHipHopIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
  15     _TEST = {
  16         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
  17         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
  18         'info_dict': {
  19             'id': '1435540',
  20             'ext': 'mp3',
  21             'title': 'Freddie Gibbs - Lay It Down'
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27         webpage = self._download_webpage(url, video_id)
  28
  29         video_url_base64 = self._search_regex(
  30             r'data-path="(.*?)"', webpage, 'video URL', default=None)
  31
  32         if video_url_base64 is None:
  33             video_url = self._search_regex(
  34                 r'"contentUrl" content="(.*?)"', webpage, 'content URL')
  35             return self.url_result(video_url, ie='Youtube')
  36
  37         reqdata = urlencode_postdata([
  38             ('mediaType', 's'),
  39             ('mediaId', video_id),
  40         ])
  41         r = sanitized_Request(
  42             'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
  43         r.add_header('Content-Type', 'application/x-www-form-urlencoded')
  44         mkd = self._download_json(
  45             r, video_id, note='Requesting media key',
  46             errnote='Could not download media key')
  47         if 'mediaKey' not in mkd:
  48             raise ExtractorError('Did not get a media key')
  49
  50         redirect_url = compat_b64decode(video_url_base64).decode('utf-8')
  51         redirect_req = HEADRequest(redirect_url)
  52         req = self._request_webpage(
  53             redirect_req, video_id,
  54             note='Resolving final URL', errnote='Could not resolve final URL')
  55         video_url = req.geturl()
  56         if video_url.endswith('.html'):
  57             raise ExtractorError('Redirect failed')
  58
  59         video_title = self._og_search_title(webpage).strip()
  60
  61         return {
  62             'id': video_id,
  63             'url': video_url,
  64             'title': video_title,
  65             'thumbnail': self._og_search_thumbnail(webpage),
  66         }