#!/usr/bin/env python2.4
# $Id: detag,v 1.1 2006-03-22 10:15:36-06 annis Exp annis $
# $Source: /u/annis/talks_articles/pythontut/RCS/detag,v $

"""Remove HTML tags from a document.

I didn't construct this regular expression myself, but lifted from
a web page somewhere.

Usage: detag < file.html
"""

import sys
import re


detag = re.compile(r"""</?(\w+)(\s*\w*\s*=\s*("[^"]*"|'[^']'|[^>]*))*|/?>""", re.MULTILINE)

for line in sys.stdin.readlines():
    print detag.sub("", line),


# EOF