分析apache访问日志

最新推荐文章于 2021-05-11 22:00:59 发布

niubihonghong1111

最新推荐文章于 2021-05-11 22:00:59 发布

阅读量225

点赞数

本文链接：https://blog.csdn.net/niubihonghong1111/article/details/82013810

版权

(1)
import re

def count_patt(fname, patt):
patt_dict = {}
cpatt = re.compile(patt)

with open(fname) as fobj:
    for line in fobj:
        m = cpatt.search(line)
        if m:
            key = m.group()
            patt_dict[key] = patt_dict.get(key, 0) + 1

return patt_dict

if name == ‘main‘:
fname = ‘access_log’
ip = ‘^(\d+.){3}\d+’
print(count_patt(fname, ip))
# awk ‘{print $1}’ access_log | sort | uniq -c | sort -nr br = ‘Firefox|MSIE|Chrome’ print(count_patt(fname, br)) shell = ‘bash$ |nologin$’
print(count_patt(‘/etc/passwd’, shell))

(2)
import re
from collections import Counter

class CountPatt:
def init(self, fname):
self.fname = fname

def count_patt(self, patt):
    cpatt = re.compile(patt)
    patt_obj = Counter()
    with open(self.fname) as fobj:
        for line in fobj:
            m = cpatt.search(line)
            if m:
                item = m.group()
                patt_obj.update([item])
    return patt_obj

if name == ‘main‘:
fname = ‘access_log’
ip = ‘^(\d+.){3}\d+’
web_log = CountPatt(fname)
a = web_log.count_patt(ip)
print(a)
print(a.most_common(3))
b = web_log.count_patt(‘Firefox|MSIE|Chrome’)
print(b)
print(b.most_common(5))