python统计日志ip访问数脚本

import re
tudou@Gyyx
f=open("/tmp/a.log","r")
arr={}
lines = f.readlines()
for line in lines:
    ipaddress=re.compile(r'^#(((2[0-4]\d|25[0-5]|[01]?\d\d?)\.){3}(2[0-4]\d|25[0-5]|[01]?\d\d?))')
    match=ipaddress.match(line)
    if match:
        ip = match.group(1)
        if(arr.has_key(ip)):
            arr[ip]+=1
        else:
            arr.setdefault(ip,1)
        
f.close()
for key in arr:
    print key+"->"+str(arr[key])

日志格式为

#111.172.249.84 - - [12/Dec/2011:05:33:36 +0800] "GET /images/i/goTop.png HTTP/1.0" 200 486 "http://wh.xxxx.com/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"
#111.172.249.84 - - [12/Dec/2011:05:33:36 +0800] "GET /images/i/goTop.png HTTP/1.0" 200 486 "http://wh.xxxx.com/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"
#111.172.249.85 - - [12/Dec/2011:05:33:36 +0800] "GET /images/i/goTop.png HTTP/1.0" 200 486 "http://wh.xxxx.com/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"
#111.172.249.86 - - [12/Dec/2011:05:33:36 +0800] "GET /images/i/goTop.png HTTP/1.0" 200 486 "http://wh.xxxx.com/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"

输出结果

111.172.249.86->1
111.172.249.84->2
111.172.249.85->1

注释：python字段的setdefault用法为获取信息，如果获取不到的时候就按照他的参数设置该值

>>> a={}
>>> a['key']='123'
>>> print (a)
{'key': '123'}
>>> print (a.setdefault('key','456'))  #显示a这个字典的'key'值的内容,因为字典有，所以不会去设置它
123

>>> print (a.setdefault('key1','456')) #显示a这个字典的'key1'值的内容，因为字典没有，所以设置为456了
456
>>> a
{'key1': '456', 'key': '123'}