_ Git - youtube-dl/blob - youtube_dl/extractor/auengine.py

   1 import os.path
   2 import re
   3 import urllib
   4 import urlparse
   5
   6 from .common import InfoExtractor
   7
   8 class AuengineIE(InfoExtractor):
   9     _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
  10
  11     def _real_extract(self, url):
  12         mobj = re.match(self._VALID_URL, url)
  13         video_id = mobj.group(1)
  14         webpage = self._download_webpage(url, video_id)
  15         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
  16                 webpage, u'title')
  17         title = title.strip()
  18         links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
  19         links = [urllib.unquote(l) for l in links]
  20         for link in links:
  21             root, pathext = os.path.splitext(urlparse.urlparse(link).path)
  22             if pathext == '.png':
  23                 thumbnail = link
  24             elif pathext == '.mp4':
  25                 url = link
  26                 ext = pathext
  27         if ext == title[-len(ext):]:
  28             title = title[:-len(ext)]
  29         ext = ext[1:]
  30         return [{
  31             'id':        video_id,
  32             'url':       url,
  33             'ext':       ext,
  34             'title':     title,
  35             'thumbnail': thumbnail,
  36         }]