#!/bin/bash
log_path=/home/www.jb51.net/log/access.log.1
domain="jb51.net"
email="log@jb51.net"
maketime=`date +%Y-%m-%d" "%H":"%M`
logdate=`date -d "yesterday" +%Y-%m-%d`
total_visit=`wc -l ${log_path} | awk '{print $1}'`
total_bandwidth=`awk -v total=0 '{total+=$10}END{print total/1024/1024}' ${log_path}`
total_unique=`awk '{ip[$1]++}END{print asort(ip)}' ${log_path}`
ip_pv=`awk '{ip[$1]++}END{for (k in ip){print ip[k],k}}' ${log_path} | sort -rn | head -20`
url_num=`awk '{url[$7]++}END{for (k in url){print url[k],k}}' ${log_path} | sort -rn | head -20`
referer=`awk -v domain=$domain '$11 !~ /http:\/\/[^/]*'"$domain"'/{url[$11]++}END{for (k in url){print url[k],k}}' ${log_path} | sort -rn | head -20`
notfound=`awk '$9 == 404 {url[$7]++}END{for (k in url){print url[k],k}}' ${log_path} | sort -rn | head -20`
spider=`awk -F'"' '$6 ~ /Baiduspider/ {spider["baiduspider"]++} $6 ~ /Googlebot/ {spider["googlebot"]++}END{for (k in spider){print k,spider[k]}}'  ${log_path}`
search=`awk -F'"' '$4 ~ /http:\/\/www\.baidu\.com/ {search["baidu_search"]++} $4 ~ /http:\/\/www\.google\.com/ {search["google_search"]++}END{for (k in search){print k,search[k]}}' ${log_path}`
echo -e "概況\n報告生成時間：${maketime}\n總訪問量:${total_visit}\n總帶寬:${total_bandwidth}M\n獨立訪客:${total_unique}\n\n訪問IP統(tǒng)計\n${ip_pv}\n\n訪問url統(tǒng)計\n${url_num}\n\n來源頁面統(tǒng)計\n${referer}\n\n404統(tǒng)計\n${notfound}\n\n蜘蛛統(tǒng)計\n${spider}\n\n搜索引擎來源統(tǒng)計\n${search}" | mail -s "$domain $logdate log statistics" ${email}