Das deutsche Python-Forum

Code: Alles auswählen

class StrippingParser(sgmllib.SGMLParser):
    # These are the HTML tags that we will leave intact
    valid_tags = ()
    tolerate_missing_closing_tags = ()
    from htmlentitydefs import entitydefs # replace entitydefs from sgmllib

    def __init__(self):
        sgmllib.SGMLParser.__init__(self)
        self.result = []
        self.endTagList = []

    def handle_data(self, data):
        self.result.append(data)

    def handle_charref(self, name):
        self.result.append("&#%s;" % name)

    #def handle_entityref(self, name):
    #    x = ';' * self.entitydefs.has_key(name)
    #    self.result.append("&%s%s" % (name, x))

    def unknown_starttag(self, tag, attrs):
        """ Delete all tags except for legal ones. """
        # print "%s, %s, %s" % (self, tag, attrs)
        if tag in self.valid_tags:
            self.result.append('<' + tag)
            for k, v in attrs:
                if string.lower(k[0:2]) != 'on' and string.lower(
                    v[0:10]) != 'javascript':
                    self.result.append(' %s="%s"' % (k, v))
            self.result.append('>')
            #print "DEBUG: unknown_starttag: %s" % (tag)
            if tag not in self.tolerate_missing_closing_tags:
                endTag = '</%s>' % tag
                self.endTagList.insert(0,endTag)

    def unknown_endtag(self, tag):
        if tag in self.valid_tags:
            # We don't ensure proper nesting of opening/closing tags
            #print "DEBUG: unknown_endtag: %s" % (tag)
            endTag = '</%s>' % tag
            self.result.append(endTag)
            if tag not in self.tolerate_missing_closing_tags:
                self.endTagList.remove(endTag)

    def cleanup(self):
        """ Append missing closing tags. """
        self.result.extend(self.endTagList)

Code: Alles auswählen

def makeplain(html):
    from re import sub
    return re.sub(r'<(.*?)>(?uism)', '', html)