simplerss/src/TagStrip.py

   1 # -*- coding: utf-8 -*-
   2
   3 import re
   4
   5 class TagStrip():
   6         convertables = {
   7                 "&#228;": u"�",
   8                 "&auml;": u"�",
   9                 "&#252;": u"�",
  10                 "&uuml;": u"�",
  11                 "&#246;": u"�",
  12                 "&ouml;": u"�",
  13                 "&#196;": u"�",
  14                 "&Auml;": u"�",
  15                 "&#220;": u"�",
  16                 "&Uuml;": u"�",
  17                 "&#214;": u"�",
  18                 "&Ouml;": u"�",
  19                 "&#223;": u"�",
  20                 "&szlig;": u"�",
  21                 "&#038;": u"&",
  22                 "&#8230;": u"...",
  23                 "&#8211;": u"-",
  24                 "&#160;": u" ",
  25
  26                 "&lt;": u"<",
  27                 "&gt;": u">",
  28                 "&nbsp;": u" ",
  29                 "&amp;": u"&",
  30                 "&quot;": u"\"",
  31         }
  32
  33         def strip(self, html):
  34                 # Convert htmlspecialchars
  35                 for escaped, unescaped in self.convertables.iteritems():
  36                         html = html.replace(escaped, unescaped)
  37
  38                 # Strip everything of form <a>CONTENT</a>, but keep CONTENT (elements with content)
  39                 html = re.sub('<(?P<tag>.*?)>(?P<content>.*?)</(?P=tag)>', '\g<content>', html)
  40
  41                 # Strip everything of form <a /> (elements without conent)
  42                 html = re.sub('<(.*?) />', '', html)
  43                 return html