python 分割apache日志

#!/usr/bin/env python

import sys

import re

log_line_re = re.compile(r'''(?P<remote_host>\S+) #IP ADDRESS

\s+ #whitespace

\S+ #remote logname

\s+ #whitespace

\S+ #remote user

\s+ #whitespace

(?P<time>\[[^\[\]]+\]) #time

\s+ #whitespace

(?P<request>"[^"]+") #first line of request

\s+ #whitespace

(?P<status>\d+)

\s+ #whitespace

(?P<bytes_sent>-|\d+)

\s* #whitespace

''', re.VERBOSE)

line ='192.168.1.37 - - [22/Jul/2010:14:51:56 +0800] "GET /xampp/head.php HTTP/1.1" 200 1362'

m = log_line_re.match(line)

groupdict = m.groupdict()

print  groupdict

[root@test ~]# python log1 

{'status': '200', 'remote_host': '192.168.1.37', 'request': '"GET /xampp/head.php HTTP/1.1"', 'bytes_sent': '1362', 'time': '[22/Jul/2010:14:51:56 +0800]'}

使用apachelog模块 http://pypi.python.org/pypi/apachelog/1.0

#!/usr/bin/env python

import apachelog

p=apachelog.parser(apachelog.formats['common'])

for line in open('/opt/lampp/logs/access_log'):

           try:

               data = p.parse(line)

               print data

           except:

              sys.stderr.write("Unable to parse %s" % line)

{'%l': '-', '%>s': '200', '%h': '192.168.1.38', '%b': '5573', '%u': '-', '%t': '[22/Jul/2010:16:02:27 +0800]', '%r': 'GET /admin/ListUserlist.php HTTP/1.1'}