gistfile1.py

# Note htmlFilter is WiP (Work in Progress) ;-)
import cgi

buf_re = {
    'basicTags': re.compile( \
        r'<(' \
            r'/?(b|c(ite|ode)|d([dlt]|el)|em|h[0-6]|i(ns)?|li|marquee|ol|p|' \
            r's(mall|tr(ike|ong)|u[bp])?|t(able|[dhrt])|u[lm]?)|[bh]r'
        r')\s*>'),
    'closingComplexTags': re.compile('</(a)&\s*gt;'),
    'optSpaces': re.compile(r'\s*'),
}

def htmlFilter(content):
    # 1.  Escape
    content = cgi.escape(content)

    # 2.  Find basic tags
    # 2.1 Basic tags without attributes
    content = buf_re['basicTags'].sub(r'<\1>', content)
    # 2.2 Special cases
    content = content \
        .replace('\n', '<br>') \
        .replace('&lt;!--', '<!--') \
        .replace('--&gt;', '-->')
    return content