#!/usr/bin/env python2.4
# $Id: find404,v 1.1 2006/03/22 18:31:47 annis Exp $
# $Source: /u/annis/talks_articles/pythontut/RCS/find404,v $

"""Find 404 errors in web logs.

find404 < log
"""

import sys
import re

# 152.1.119.190 - - [22/Mar/2006:12:15:59 -0600]
# "GET /favicon.ico HTTP/1.1" 404 283 "-" "Mozilla/5.0 
# (X11; U; Linux i686; en-US; rv:1.8.0.1)
# Gecko/20060124 Firefox/1.5.0.1"

err = re.compile(r"""[\d\.]*\s.+\s+.\s\[(.*)\]\s"(.*)"\s(\d+).*""")

for line in sys.stdin.readlines():
    match = err.search(line)
    if match and match.group(3) == "404":
        print '%s: %s "%s"' % (match.group(3), match.group(1), match.group(2))


# EOF