yt_dlp/extractor/hotnewhiphop.py

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