Linux分析httpd access-log(访问日志)获取最多访问的前10个IP

日志分析可以获得很多有用的信息，现在来试试最基本的，获取最多访问的前10个IP地址及访问次数。

既然是统计，那么awk是必不可少的，好用而高效。

命令如下：

awk '{nums[$1]+=1;} END{for(i in nums){print nums[i],i}}' access_log | sort | tail

首先用awk统计出来一个列表，然后用sort进行排序，最后用tail获取最后的10个。

以上参数可以略作修改显示更多的数据，比如将tail加上-n参数等，另外日志格式不同命令也可能需要稍作修改。

1. access_log日志文件在/etc/httpd/logs目录下

cd /etc/httpd/logs

2.查看access_log日志文件

cat access_log

# 内容如下：

192.168.178.1 - - [04/Feb/2023:10:29:09 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:10 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:10 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:11 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:11 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:11 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:11 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:11 +0800] "GET / HTTP/1.1" 304 - "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
192.168.178.1 - - [04/Feb/2023:10:29:56 +0800] "-" 408 - "-" "-"
192.168.178.151 - - [04/Feb/2023:10:43:40 +0800] "GET / HTTP/1.1" 200 20 "-" "curl/7.61.1"
192.168.178.151 - - [04/Feb/2023:10:43:43 +0800] "GET / HTTP/1.1" 200 20 "-" "curl/7.61.1"
192.168.178.151 - - [04/Feb/2023:10:43:46 +0800] "GET / HTTP/1.1" 200 20 "-" "curl/7.61.1"

3.awk获取访问前10位的ip地址

awk '{nums[$1]+=1;} END{for(i in nums){print nums[i],i}}' access_log | sort | tail

# {nums[$1]+=1} 将第一列的值作为数组的下标，数组的内容存储IP地址出现的次数

# END{for(i in nums){print nums[i],i}} END在主代码块和数据读取之后执行，循环数组的下标，输出数组的值和下标

# sort 排序

# tail 输出内容的前10行

4.其他功能命令：

查看日志中访问次数最多的前10个IP
#cat access_log |cut -d ' ' -f 1 | sort |uniq -c | sort -nr | awk '{print $0 }' | head -n 10 | less
 查看日志中出现100次以上的IP
#cat access_log |cut -d ' ' -f 1 | sort |uniq -c | awk '{if ($1 > 100) print $0}'｜sort -nr | less
查看最近访问量最高的文件
#cat access_log | tail -10000 | awk '{print $7}' | sort | uniq -c | sort -nr | less
 查看日志中访问超过100次的页面
#cat access_log | cut -d ' ' -f 7 | sort |uniq -c | awk '{if ($1 > 100) print $0}' | less
 统计某url，一天的访问次数
#cat access_log | grep '12/Aug/2009' | grep '/images/index/e1.gif' | wc | awk '{print $1}'
 前五天的访问次数最多的网页
#cat access_log | awk '{print $7}' | uniq -c | sort -n -r | head -20
 从日志里查看该ip在干嘛
#cat access_log | grep 218.66.36.119 | awk '{print $1"\t"$7}' | sort | uniq -c | sort -nr | less
 列出传输时间超过 30 秒的文件
#cat access_log | awk '($NF > 30){print $7}' | sort -n | uniq -c | sort -nr | head -20
 列出最最耗时的页面(超过60秒的)
#cat access_log | awk '($NF > 60 && $7~/\.php/){print $7}' | sort -n | uniq -c | sort -nr | head -100