youtube_dl/extractor/newgrounds.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import determine_ext
   6
   7
   8 class NewgroundsIE(InfoExtractor):
   9     _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
  10     _TEST = {
  11         u'url': u'http://www.newgrounds.com/audio/listen/549479',
  12         u'file': u'549479.mp3',
  13         u'md5': u'fe6033d297591288fa1c1f780386f07a',
  14         u'info_dict': {
  15             u"title": u"B7 - BusMode",
  16             u"uploader": u"Burn7",
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         music_id = mobj.group('id')
  23         webpage = self._download_webpage(url, music_id)
  24
  25         title = self._html_search_regex(r',"name":"([^"]+)",', webpage, u'music title')
  26         uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, u'music uploader')
  27
  28         music_url_json_string = self._html_search_regex(r'({"url":"[^"]+"),', webpage, u'music url') + '}'
  29         music_url_json = json.loads(music_url_json_string)
  30         music_url = music_url_json['url']
  31
  32         return {
  33             'id':       music_id,
  34             'title':    title,
  35             'url':      music_url,
  36             'uploader': uploader,
  37             'ext':      determine_ext(music_url),
  38         }