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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class NewgroundsIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.newgrounds.com/audio/listen/549479',
  13         'md5': 'fe6033d297591288fa1c1f780386f07a',
  14         'info_dict': {
  15             'id': '549479',
  16             'ext': 'mp3',
  17             'title': 'B7 - BusMode',
  18             'uploader': 'Burn7',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         music_id = mobj.group('id')
  25         webpage = self._download_webpage(url, music_id)
  26
  27         title = self._html_search_regex(
  28             r',"name":"([^"]+)",', webpage, 'music title')
  29         uploader = self._html_search_regex(
  30             r',"artist":"([^"]+)",', webpage, 'music uploader')
  31
  32         music_url_json_string = self._html_search_regex(
  33             r'({"url":"[^"]+"),', webpage, 'music url') + '}'
  34         music_url_json = json.loads(music_url_json_string)
  35         music_url = music_url_json['url']
  36
  37         return {
  38             'id': music_id,
  39             'title': title,
  40             'url': music_url,
  41             'uploader': uploader,
  42         }