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