shell分析nginx日志

日志格式如下：

 

log_format  iptables   '"$remote_addr" "$time_local" "$request_uri" "$http_user_agent" "$http_referer"';

"218.22.202.130"  "12/Jun/2012:17:20:34 +0800"    "/chanke/19/19060321.htm"      "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Tride  nt/5.0)"  "http://www.baidu.com/s?word=%BF"

第一列是访问ip   第二列是访问时间   第三列uri，第四列是user-agent，第五列是referer 

 

#!/bin/bash

    if [ $# -eq 0 ]; then
        echo "Error: please specify logfile."
        exit 0
    else
        LOG=$1
    fi
    if [ ! -f $1 ]; then
    　 echo "Sorry, sir, I can't find this  log file, pls try again!"
    exit 0
    fi
 ################################
    echo "Most of the ip:"
    echo "-------------------------------------------"
    awk '{ print $1 }' $LOG| sort| uniq -c| sort -nr| head -10
    echo
    echo
###################
    echo "Most of the time:"
    echo "--------------------------------------------"
    awk '{ print $2 }' $LOG| cut -c 14-18| sort| uniq -c| sort -nr| head -10
    echo
    echo
#######################
    echo "Most of the page:"
    echo "--------------------------------------------"
    awk '{print $4}' $LOG| sed 's/^.*\(.cn*\)\"/\1/g'| sort| uniq -c| sort -rn| head -10
    echo
    echo
#####################3
    echo "Most of the time / Most of the ip:"
    echo "--------------------------------------------"
        awk '{ print $2 }' $LOG| cut -c 14-18| sort -n| uniq -c| sort -nr| head -10 > timelog
    for i in `awk '{ print $2 }' timelog`
    do
       num=`grep $i timelog| awk '{ print $1 }' `
       echo "$i $num"
       ip=`grep $i $LOG| awk '{ print $1}'| sort -n| uniq -c| sort -nr| head -10`
       echo "$ip"
       echo
    done
    rm -f timelog