python分析nginx访问日志

先上正文：

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
class CountPatt(object):
    def __init__(self, patt):
        self.patt = re.compile(patt)
        self.result = {}
    def count_patt(self, fname):     #正则匹配
        with open(fname) as fobj:
            for line in fobj:
                match = self.patt.search(line)
                if match:
                    key = match.group()
                    self.result[key] = self.result.get(key, 0) + 1       #self.result.get(key, 0) + 1,get方式获取key的值，如果没
有默认返回0

        return self.result

    def sort(self):                 #
        result = []
        alist = self.result.items()    #将字典以列表的方式返回
        print(alist)
        for i in xrange(len(alist)):
            greater = alist[0]
            for item in alist[1:]:
                if greater[1] < item[1]:
                    greater = item
            result.append(greater)
            alist.remove(greater)
        return result


if __name__ == "__main__":
    httpd_log = '/tmp/access.log'
    ip_pattern = r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}'
    browser_pattern = r'Chrome|Safari|Firefox'
    a = CountPatt(ip_pattern)
    print a.count_patt(httpd_log)
    print a.sort()

涉及到的一点细节,dict.get(key[, value]) 语法，后面的value当key的值不存在，就会返回该默认的value值：

[root@esearch-prod-component-010177210122 /home/liujiangbo] 03:41:26 0
# python
Python 2.6.6 (r266:84292, Aug 18 2016, 15:13:37) 
[GCC 4.4.7 20120313 (Red Hat 4.4.7-17)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> result = {}
>>> result[111]=result.get(111,0)+1
>>> print(result)
{111: 1}

Python 字典(Dictionary) items() 函数以列表返回可遍历的(键, 值) 元组数组，语法：dict.items()

>>> print(result.items())
[(111, 1)]
>>> result = {}

这样可能看的不够明显，看下面：

#!/usr/bin/python
# coding=utf-8
 
dict = {'Google': 'www.google.com', 'Runoob': 'www.runoob.com', 'taobao': 'www.taobao.com'}
 
print "字典值 : %s" %  dict.items()
 
# 遍历字典列表
for key,values in  dict.items():
    print key,values

执行结果：

字典值 : [('Google', 'www.google.com'), ('taobao', 'www.taobao.com'), ('Runoob', 'www.runoob.com')]
Google www.google.com
taobao www.taobao.com
Runoob www.runoob.com