最近访问ftp所在的服务器时反应有点慢,于是想看看ftp是否有被爬虫爬过,然后随手写了一个简易版的日志分析工具,用来分析每日用户的来源地址及访问量。由于没有做日志切割,此脚本只是在访问日志中统计前一日的数据,想要统计更多的数据可以稍作修改。
#!/bin/bash
cat << EOF
------------------------------------
日志分析小工具
------------------------------------
EOF
LANG=en_US
Usage() {
echo "Usage: $0 Logfile"
}
if [ $# -eq 0 ] ;then
Usage
exit 0
else
Log=$1
fi
Tmpfile=$(mktemp)
Year=$(date |awk '{print $6}')
Mon=$(date |awk '{print $2}')
Day=$(date |awk '{print $3}')
echo -e "\n\033[31m-------the ${Year}-${Mon}-${Yesterday} log statistics as shown:--------\033[0m"
echo -e "\n\033[32m the UV in total yesterday:\033[0m\n"
cat $Log| awk '{print $7}'|wc -l
echo -e "\n\033[32m Most of the time yesterday:\033[0m\n"
cat $Log |awk '{print $4}' |cut -c 14-18 |sort|uniq -c | sort -nr | head -10
echo -e "\n\033[32m Most of the page yesterday:\033[0m\n"
cat $Log |awk '{print $11}' |sort |uniq -c |sort -rn |head -10
echo -e "\n\033[32m Most of the ip yesterday:\033[0m\n"
cat $Log| awk '{print $1}' | sort |uniq -c |sort -rn |head -10 > $Tmpfile
cat $Tmpfile | while read line;
do
num=$(echo $line|awk '{print $1}')
echo -n "访问次数:$num "
ip=$(echo $line|awk '{print $2}')
curl -s ip.cn?ip=$ip
done
执行结果如下所示: