Wiki Navigation

Strip white characters among html tags in your pages with CherryPy

import re

class StripWhiteChars(object):
    """
    Stripping all "white characters" among html tags.

    Author: Jaroslaw Zabiello (http://zabiello.com)
    Version: 2004-11-26    
    """
    omitTags = ['xmp', 'pre', 'script', 'style', 'textarea', 'code']
    
    def __init__(self):
        # new object style: http://python.org/doc/newstyle.html
        super(StripWhiteChars, self).__init__() 
        self.mark = []
        for tag in self.omitTags:
            pattern = '<'+tag+r'[^>]*?>.*?</'+tag+'>'
            record = {'tag': tag, 'regex': re.compile(pattern, re.IGNORECASE|re.MULTILINE|re.DOTALL),}        
            self.mark.append(record)
        self.regexStrip = re.compile(r'(<[^>]+?>)[\s]+?(<[^>]+?>)', re.MULTILINE|re.DOTALL)

    def strip(self, html):
        marked = {}
        for dic in self.mark:
            found = dic['regex'].findall(html)
            for i in xrange(len(found)):
                replaced = '@@@STRIPPED%s%d@@@' % (dic['tag'], i)
                html = html.replace(found[i], replaced)
                marked[replaced] = found[i]
        while self.regexStrip.search(html):
            html = self.regexStrip.sub(r'\1\2', html)
        for replaced, source in marked.iteritems():
            html = html.replace(replaced, source)
        return html
        
if __name__=='__main__':
    # test:
    html = '''
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="pl">
<head>
<title>To jest test</title>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-2" />
<meta name="language" content="pl" />
<meta name="robots" content="all" />
<style type="text/css" media="all">@import "/styles/glowna.css";</style>
<script type="text/javascript" src="/scripts/funkcje.js"> </script>
</head>
<body id>
<div id="accessibility">goto  [<a href="#menu">part one</a>] [<a href="#search">part two</a>]</div>

<div id="container">
        <script language="JavaScript">
            <!--
            document.write('<code>  to   jest  test</code>')
            //-->
            </script>            <code>
            To jest
            jakis  kod
            </code>          <script>
            <!--
                document.write('to jest script2')
            //-->
            </script>
            <table border=0>
                <tr>
                    <td>
                        <A HREF="http://python.org">
                        <font color="red">Python HomePage</font>
                        </A>
                    </td>
                </tr>
            </table>
</div>
        </body>
    </html>
    '''
    test = StripWhiteChars()
    print test.strip(html)

It can be added to CherryPy as filter:

from cherrypy import cpg
from cherrypy.lib.filter.basefilter import BaseOutputFilter

class StripWhiteCharsFilter(BaseOutputFilter):
    """Filter stripping all white-chars among html tags"""
    def __init__(self):
        super(StripWhiteCharsFilter, self).__init__()
        self.obj = StripWhiteChars()
    def beforeResponse(self):
        cpg.response.body = [self.obj.strip(''.join(cpg.response.body))]

testhtml = '<html>.....</html>'

class Root(object):
    """main"""

    _cpFilterList = [StripWhiteCharsFilter()]

    def index(self, **kwargs):
        return testhtml
    index.exposed = True

cpg.root = Root()
cpg.server.start(configFile = 'Root.conf')

Download in other formats:

Plain Text