youtube_dl/extractor/mixcloud.py

   1 import json
   2 import re
   3 import socket
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_http_client,
   8     compat_urllib_error,
   9     compat_urllib_request,
  10     unified_strdate,
  11 )
  12
  13
  14 class MixcloudIE(InfoExtractor):
  15     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
  16     IE_NAME = u'mixcloud'
  17
  18     _TEST = {
  19         u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/',
  20         u'file': u'dholbach-cryptkeeper.mp3',
  21         u'info_dict': {
  22             u'title': u'Cryptkeeper',
  23             u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  24             u'uploader': u'Daniel Holbach',
  25             u'uploader_id': u'dholbach',
  26             u'upload_date': u'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                 compat_urllib_request.urlopen(url)
  35                 return url
  36             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error):
  37                 url = None
  38
  39         return None
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43
  44         uploader = mobj.group(1)
  45         cloudcast_name = mobj.group(2)
  46         track_id = '-'.join((uploader, cloudcast_name))
  47         api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
  48         webpage = self._download_webpage(url, track_id)
  49         json_data = self._download_webpage(api_url, track_id,
  50             u'Downloading cloudcast info')
  51         info = json.loads(json_data)
  52
  53         preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
  54         song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
  55         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
  56         final_song_url = self.check_urls(template_url % i for i in range(30))
  57
  58         return {
  59             'id': track_id,
  60             'title': info['name'],
  61             'url': final_song_url,
  62             'ext': 'mp3',
  63             'description': info['description'],
  64             'thumbnail': info['pictures'].get('extra_large'),
  65             'uploader': info['user']['name'],
  66             'uploader_id': info['user']['username'],
  67             'upload_date': unified_strdate(info['created_time']),
  68             'view_count': info['play_count'],
  69         }