youtube_dl/extractor/hotnewhiphop.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import base64
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10     ExtractorError,
  11     HEADRequest,
  12 )
  13
  14
  15 class HotNewHipHopIE(InfoExtractor):
  16     _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
  17     _TEST = {
  18         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
  19         'file': '1435540.mp3',
  20         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
  21         'info_dict': {
  22             'title': 'Freddie Gibbs - Lay It Down'
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         m = re.match(self._VALID_URL, url)
  28         video_id = m.group('id')
  29
  30         webpage_src = self._download_webpage(url, video_id)
  31
  32         video_url_base64 = self._search_regex(
  33             r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False)
  34
  35         if video_url_base64 is None:
  36             video_url = self._search_regex(
  37                 r'"contentUrl" content="(.*?)"', webpage_src, u'video URL')
  38             return self.url_result(video_url, ie='Youtube')
  39
  40         reqdata = compat_urllib_parse.urlencode([
  41             ('mediaType', 's'),
  42             ('mediaId', video_id),
  43         ])
  44         r = compat_urllib_request.Request(
  45             'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
  46         r.add_header('Content-Type', 'application/x-www-form-urlencoded')
  47         mkd = self._download_json(
  48             r, video_id, note='Requesting media key',
  49             errnote='Could not download media key')
  50         if 'mediaKey' not in mkd:
  51             raise ExtractorError('Did not get a media key')
  52
  53         redirect_url = base64.b64decode(video_url_base64).decode('utf-8')
  54         redirect_req = HEADRequest(redirect_url)
  55         req = self._request_webpage(
  56             redirect_req, video_id,
  57             note='Resolving final URL', errnote='Could not resolve final URL')
  58         video_url = req.geturl()
  59         if video_url.endswith('.html'):
  60             raise ExtractorError('Redirect failed')
  61
  62         video_title = self._og_search_title(webpage_src).strip()
  63
  64         return {
  65             'id': video_id,
  66             'url': video_url,
  67             'title': video_title,
  68             'thumbnail': self._og_search_thumbnail(webpage_src),
  69         }