yt_dlp/extractor/hotnewhiphop.py

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