tjefferson

// use client userAagent's lowercase to match these:

Wechat: /micromessenger/,
QQBrowser: /qqbrowser/,
UC: /ubrowser|ucbrowser|ucweb/,
Shoujibaidu: /baiduboxapp|baiduhd|bidubrowser|baidubrowser/,
SamsungBrowser: /samsungbrowser/,
MiuiBrowser: /miuibrowser/,
Sogou : /sogoumobilebrowser|sogousearch/,
Explorer2345 : /2345explorer|2345chrome|mb2345browser/,

tjefferson

#!/bin/bash
set -o nounset
set -o errexit

IFS=$'\n'
dt=$(date -d'yesterday' '+%Y%m%d') #每天读取前一天的日志
logfile="/var/log/nginx/access.log-${dt}.gz" #nginx access.log日志

#读取日志并将User Agent信息中包含爬虫标识的过滤出来进行解析操作
zcat ${logfile} | awk -F'"' 'tolower($6)~/bot|spider|yahoo! slurp/ && $2~/GET/ {print $0}' | \

tjefferson

<script>
var browserName = "Other";
var ua = window.navigator.userAgent;
browserRegExp = {
	Sogou : /SE\s2\.X|SogouMobileBrowser/,
	Explorer2345 : /2345Explorer|2345chrome|Mb2345Browser/,
	Liebao : /LBBROWSER/,
	Wechat : /MicroMessenger/,
	QQBrowser : /QQBrowser/,
	Baidu : /BIDUBrowser|baidubrowser|BaiduHD/,