python脚本统计日志独立ip

rthtge

题目：
    有如下log文件，请打印出独立IP，并统计独立IP数，打印出访问最多的前5个ip及访问次数：
log文件www.log内容类似如下格式:

1 2 3 4 5 6

125.78.48.67 - - [25/Dec/2014:15:31:20 +0800] "GET /logo.jpg HTTP/1.1" 200 5183 "-" "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" 101.226.166.226 - - [25/Dec/2014:15:31:21 +0800] "GET " 302 26 "-" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1; 360Spider" 101.226.166.226 - - [25/Dec/2014:15:31:21 +0800] "GET " "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1; 360Spider" 125.78.48.67 - - [25/Dec/2014:15:31:20 +0800] "GET /topbanner.jpg HTTP/1.1" 200 51794 "-" "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" 118.192.170.7 - - [25/Dec/2014:15:31:09 +0800] "GET HTTP/1.1" 200 34381 "-" "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36 SE 2.X MetaSr 1.0" 118.192.170.7 - - [25/Dec/2014:15:31:22 +0800] "GET HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36 SE 2.X MetaSr 1.0"

--- 刚学python，写的很烂，code:

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30

#!/usr/bin/env python import re re1 = r'^\d+\.\d+\.\d+\.\d+' reg = re.compile(re1) fp = open('www.log') f_content = fp.readlines() fp.close() a = [] for lines in f_content:     ip = re.findall(reg,lines)     a.append(ip[0]) b = list(set(a)) b1 = [] for i in range(len(b)):     a1 = []     a1.append(a.count(b))     a1.append(b)     b1.append(a1) b1.sort(reverse=True) k = 1 for j in b1:     print j[0],j[1]     if k == 5:         break     k += 1

--- shell 只需一条命令：

1	awk '{print $1}' www.log |sort|uniq -c|sort -nr|head -n5

--- 改良了下python代码：

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41

#!/usr/bin/env python #coding:utf-8 import re import sys def getIP():     log = raw_input('请输入要查询的日志文件名，包括扩展名：')     re1 = r'^\d+\.\d+\.\d+\.\d+'     reg = re.compile(re1)           fp = open(log)     f_content = fp.readlines()     fp.close()           a = []           for lines in f_content:         ip = re.findall(reg,lines)         a.append(ip[0])           b = list(set(a))           b1 = []           for i in range(len(b)):         a1 = []         a1.append(a.count(b))         a1.append(b)         b1.append(a1)           b1.sort(reverse=True)     k = 1     num = raw_input('请输入一个数字要查询前几个ip:')     num = int(num)     for j in b1:         print j[0],j[1]         if k == num:             break         k += 1 if __name__ == '__main__':     getIP()