yt_dlp/extractor/hotnewhiphop.py

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