Apache 日志分析shell脚本

查看access.log文件访问的状态码：

[root@localhost logs]# cat access.log | awk -F '" ' '{print $2}'|cut-d " " -f 1| awk '{++S[$1]} END {for (key in S) print S[key],key}'

6181 200

400 400

421 304

37 206

1642 404

19 405

1、查看当天有多少个IP访问：

awk '{print $1}' |sort|uniq|wc -l

2、查看某一个页面被访问的次数：

grep "/index.php"   | wc -l

3、查看每一个IP访问了多少个页面：

awk '{++S[$1]} END {for (a in S) print a,S[a]}'

4、将每个IP访问的页面数进行从大到小 排序 并显示前10名：

awk '{++S[$1]} END {for (a in S) print S[a],a}'  | sort -rn | head -10

5、查看某一个IP访问了哪些页面：

grep ^111.111.111.111 | awk '{print $1,$7}'

6、去掉搜索引擎统计当天的页面：

awk '{print $12,$1}' | grep ^\"Mozilla | awk '{print $2}' |sort | uniq | wc -l

7、查看2009年6月21日14时这一个小时内有多少IP访问:

awk '{print $4,$1}' | grep 21/Jun/2009:14 | awk '{print $2}'| sort | uniq | wc -l                   

20.2.1.1. 刪除日志

刪除一个月前的日志

rm -f /www/logs/access.log.$(date -d '-1 month'+'%Y-%m')*                             

20.2.1.2. 统计爬虫

grep -E 'Googlebot|Baiduspider' /www/logs/www.example.com/access.2011-02-23.log | awk '{ print $1 }' |sort | uniq     

20.2.1.3. 统计浏览器

cat /www/logs/example.com/access.2010-09-20.log | grep -v-E 'MSIE|Firefox|Chrome|Opera|Safari|Gecko|Maxthon' | sort | uniq -c | sort -r-n | head -n 100    

20.2.1.4. IP 统计

# grep '22/May/2012' /tmp/myid.access.log | awk '{print$1}' | awk -F'.' '{print $1"."$2"."$3"."$4}' |sort | uniq -c | sort -r -n | head -n 10

2206219.136.134.13

1497182.34.15.248

1431211.140.143.100

1431119.145.149.106

142761.183.15.179

1427 218.6.8.189

1422124.232.150.171

1421106.187.47.224

142061.160.220.252

1418114.80.201.18   

[root@feelingirldress wwwlogs]# cat  feelingirldress.com-access_log | awk '{print$1}' | awk -F'.' '{print $1"."$2"."$3"."$4}' |sort | uniq -c | sort -r -n | head -n 10

49778 27.154.242.206

39241141.8.142.140

37615107.183.138.90

2825047.75.35.191

1565166.249.93.20

1519166.249.93.21

13928104.52.37.70

1381466.249.93.22

1363995.108.213.3

1074146.229.168.144

[root@feelingirldress wwwlogs]#cat lover-beauty.com-access_log| grep "SemrushBot" | awk '{print $1}' | awk -F'.' '{print$1"."$2"."$3"."$4}' | sort | uniq -c | sort -r -n

1722346.229.168.144

1712046.229.168.139

1710746.229.168.141

1709846.229.168.149

1702546.229.168.143

1683946.229.168.142

1677146.229.168.140

1534646.229.168.145

1433546.229.168.132

1432046.229.168.130

统计网段

# cat /www/logs/www/access.2010-09-20.log | awk '{print$1}' | awk -F'.' '{print $1"."$2"."$3".0"}' |sort | uniq -c | sort -r -n | head -n 200                         

压缩文件处理

zcat www.example.com.access.log-20130627.gz | grep '/xml/data.json' | awk '{print $1}' | awk -F'.''{print $1"."$2"."$3"."$4}' | sort | uniq -c |sort -r -n | head -n 20                         

20.2.1.5. 统计域名

# cat /www/logs/access.2011-07-27.log |awk '{print $2}'|sort|uniq -c|sort-rn|more                                 

20.2.1.6. HTTP Status

# cat /www/logs/access.2011-07-27.log |awk '{print $9}'|sort|uniq -c|sort-rn|more

5056585 304

1125579 200

7602 400

5 301                              

20.2.1.7. URL 统计

cat /www/logs/access.2011-07-27.log |awk '{print $7}'|sort|uniq -c|sort-rn|more                        

20.2.1.8. 文件流量统计

cat /www/logs/access.2011-08-03.log |awk'{sum[$7]+=$10}END{for(i in sum){print sum[i],i}}'|sort -rn|more

grep ' 200 ' /www/logs/access.2011-08-03.log |awk'{sum[$7]+=$10}END{for(i in sum){print sum[i],i}}'|sort -rn|more                        

20.2.1.9. URL 访问量统计

# cat www.access.log | awk '{print $7}' | egrep '\?|&' | sort | uniq -c |sort -rn | more                                 

20.2.1.10. 脚本运行速度

查出运行速度最慢的脚本

grep -v 0$ access.2010-11-05.log | awk -F '\" ''{print $4" " $1}' web.log | awk '{print $1" "$8}' | sort-n -k 1 -r | uniq > /tmp/slow_url.txt                                  

20.2.1.11. IP, URL 抽取

# tail -f/www/logs/www.365wine.com/access.2012-01-04.log | grep '/test.html' | awk'{print $1" "$7}'