youtube_dl/extractor/mixcloud.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     unified_strdate,
   8     compat_urllib_parse,
   9     ExtractorError,
  10 )
  11
  12
  13 class MixcloudIE(InfoExtractor):
  14     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
  15     IE_NAME = 'mixcloud'
  16
  17     _TEST = {
  18         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  19         'info_dict': {
  20             'id': 'dholbach-cryptkeeper',
  21             'ext': 'mp3',
  22             'title': 'Cryptkeeper',
  23             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  24             'uploader': 'Daniel Holbach',
  25             'uploader_id': 'dholbach',
  26             'upload_date': '20111115',
  27         },
  28     }
  29
  30     def check_urls(self, url_list):
  31         """Returns 1st active url from list"""
  32         for url in url_list:
  33             try:
  34                 # We only want to know if the request succeed
  35                 # don't download the whole file
  36                 self._request_webpage(url, None, False)
  37                 return url
  38             except ExtractorError:
  39                 url = None
  40
  41         return None
  42
  43     def _get_url(self, template_url):
  44         return self.check_urls(template_url % i for i in range(30))
  45
  46     def _real_extract(self, url):
  47         mobj = re.match(self._VALID_URL, url)
  48         uploader = mobj.group(1)
  49         cloudcast_name = mobj.group(2)
  50         track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
  51
  52         webpage = self._download_webpage(url, track_id)
  53
  54         api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
  55         info = self._download_json(
  56             api_url, track_id, 'Downloading cloudcast info')
  57
  58         preview_url = self._search_regex(
  59             r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
  60         song_url = preview_url.replace('/previews/', '/c/originals/')
  61         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
  62         final_song_url = self._get_url(template_url)
  63         if final_song_url is None:
  64             self.to_screen('Trying with m4a extension')
  65             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  66             final_song_url = self._get_url(template_url)
  67         if final_song_url is None:
  68             raise ExtractorError(u'Unable to extract track url')
  69
  70         return {
  71             'id': track_id,
  72             'title': info['name'],
  73             'url': final_song_url,
  74             'description': info.get('description'),
  75             'thumbnail': info['pictures'].get('extra_large'),
  76             'uploader': info['user']['name'],
  77             'uploader_id': info['user']['username'],
  78             'upload_date': unified_strdate(info['created_time']),
  79             'view_count': info['play_count'],
  80         }