youtube_dl/extractor/exfm.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5
   6
   7 class ExfmIE(InfoExtractor):
   8     IE_NAME = u'exfm'
   9     IE_DESC = u'ex.fm'
  10     _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
  11     _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
  12     _TESTS = [
  13         {
  14             u'url': u'http://ex.fm/song/eh359',
  15             u'file': u'44216187.mp3',
  16             u'md5': u'e45513df5631e6d760970b14cc0c11e7',
  17             u'info_dict': {
  18                 u"title": u"Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive",
  19                 u"uploader": u"deadjournalist",
  20                 u'upload_date': u'20120424',
  21                 u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
  22             },
  23             u'note': u'Soundcloud song',
  24             u'skip': u'The site is down too often',
  25         },
  26         {
  27             u'url': u'http://ex.fm/song/wddt8',
  28             u'file': u'wddt8.mp3',
  29             u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
  30             u'info_dict': {
  31                 u'title': u'Safe and Sound',
  32                 u'uploader': u'Capital Cities',
  33             },
  34             u'skip': u'The site is down too often',
  35         },
  36     ]
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         song_id = mobj.group(1)
  41         info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
  42         webpage = self._download_webpage(info_url, song_id)
  43         info = json.loads(webpage)
  44         song_url = info['song']['url']
  45         if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
  46             self.to_screen('Soundcloud song detected')
  47             return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
  48         return [{
  49             'id':          song_id,
  50             'url':         song_url,
  51             'ext':         'mp3',
  52             'title':       info['song']['title'],
  53             'thumbnail':   info['song']['image']['large'],
  54             'uploader':    info['song']['artist'],
  55             'view_count':  info['song']['loved_count'],
  56         }]