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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class NewgroundsIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
   8     _TESTS = [{
   9         'url': 'https://www.newgrounds.com/audio/listen/549479',
  10         'md5': 'fe6033d297591288fa1c1f780386f07a',
  11         'info_dict': {
  12             'id': '549479',
  13             'ext': 'mp3',
  14             'title': 'B7 - BusMode',
  15             'uploader': 'Burn7',
  16         }
  17     }, {
  18         'url': 'https://www.newgrounds.com/portal/view/673111',
  19         'md5': '3394735822aab2478c31b1004fe5e5bc',
  20         'info_dict': {
  21             'id': '673111',
  22             'ext': 'mp4',
  23             'title': 'Dancin',
  24             'uploader': 'Squirrelman82',
  25         },
  26     }]
  27
  28     def _real_extract(self, url):
  29         media_id = self._match_id(url)
  30         webpage = self._download_webpage(url, media_id)
  31
  32         title = self._html_search_regex(
  33             r'<title>([^>]+)</title>', webpage, 'title')
  34
  35         uploader = self._html_search_regex(
  36             r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
  37
  38         music_url = self._parse_json(self._search_regex(
  39             r'"url":("[^"]+"),', webpage, ''), media_id)
  40
  41         return {
  42             'id': media_id,
  43             'title': title,
  44             'url': music_url,
  45             'uploader': uploader,
  46         }