Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mixcloud.py

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