Convert special characters in text to HTML entities.

htmlescape.py

#!/usr/bin/env python

"""
Convert special characters in text to HTML entities.
NOW WITH ADDED UNICODE SUPPORT!

Usage:

$ echo "<b>foo <i>bar</i></b>" | htmlescape.py
"""

import codecs
import sys


def html_escape(text):
    """
    Convert special characters in text to HTML entities.
    """
    
    html_escape_table = {
        u"&": u"&amp;",
        u'"': u"&quot;",
        u"'": u"&apos;",
        u">": u"&gt;",
        u"<": u"&lt;",
    }

    # Convert to unicode
    text = unicode(text)

    return (u"".join(html_escape_table.get(char, char) for char in text))

if __name__ == "__main__":
    # Write UTF-8 to stdout
    sys.stdout = codecs.getwriter("utf-8")(sys.stdout)
    
    # Read and decode from stdin, so text is a unicode object
    text = raw_input().strip().decode(sys.stdin.encoding or "utf-8")
    print >> sys.stdout, html_escape(text)