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