数据采集之js埋点

一、后台nginx环境搭建　

web点数据采集后台配置nginx：
https://blog.csdn.net/weixin_37490221/article/details/80894827

下载数据源：
wget -O lua-nginx-module-0.10.0.tar.gz https://github.com/openresty/lua-nginx-module/archive/v0.10.0.tar.gz

wget --no-check-certificate -Oecho-nginx-module-0.58.tar.gz 'https://github.com/openresty/echo-nginx-module/archive/v0.58.tar.gz'

wget --no-check-certificate -O nginx_devel_kit-0.2.19.tar.gz https://github.com/simpl/ngx_devel_kit/archive/v0.2.19.tar.gz

wget https://openresty.org/download/openresty-1.9.7.3.tar.gz

wget --no-check-certificate -Oset-misc-nginx-module-0.29.tar.gz 'https://github.com/openresty/set-misc-nginx-module/archive/v0.29.tar.gz'

二、前端埋点

           前端页面中需要加载ma.js的脚本代码

    <script type="text/javascript">
                        var _maq = _maq || [];
                        _maq.push(['_setAccount', 'zaomianbao']);

                        (function() {
                                var ma = document.createElement('script');
                                ma.type = 'text/javascript';
                                ma.async = true;
                                ma.src = 'http://IP111/ma.js';
                                var s = document.getElementsByTagName('script')[
0];
                                s.parentNode.insertBefore(ma, s);
                        })();
</script>

           放到后台的前端代码

(function () {
    var params = {};
    var args = '';
    if(document) {
        params.domain = document.domain || ''; 
        params.url = document.URL || ''; 
        params.title = document.title || ''; 
        params.referrer = document.referrer || '';
        params.bio = document.getElementById("username").innerHTML || '';
        params.clickbio = ''; 
    }   
   
       document.querySelector("div#page-wrapper .wrapper.wrapper-content.animated.fadeInRight").addEventListener("click",function(e){
        params.clickbio = GetChinese(e.target.innerHTML);
        console.log(params.clickbio)
        args = '';
        console.log(params.clickbio) 
         for(var i in params) {
                if(args != '') {
                        args += '&';
                }
                args += i + '=' + encodeURIComponent(params[i]);
            }

            var img = new Image(1, 1);
            img.src = 'http://IP111/log.gif?' + args;
    })

     function GetChinese(strValue) {  
    if(strValue!= null && strValue!= ""){  
        var reg = /[\u4e00-\u9fa5]/g;   
        return strValue.match(reg).join("");  
    }  
}
 
    if(window && window.screen) {
        params.sh = window.screen.height || 0;
        params.sw = window.screen.width || 0;
        params.cd = window.screen.colorDepth || 0;
    }   
    
    if(navigator) {
        params.lang = navigator.language || ''; 
    }   
    
    if(_maq) {
        for(var i in _maq) {
            switch(_maq[i][0]) {
                case '_setAccount':
                    params.account = _maq[i][1];
                    break;
                default:
                    break;
            }   
        }   
    }   
    
    for(var i in params) {
        if(args != '') {
            args += '&';
        }   
        args += i + '=' + encodeURIComponent(params[i]);
    }   
 
    
    var img = new Image(1, 1); 
    img.src = 'http://IP111/log.gif?' + args;
})();

三、后端配置

    配置nginx服务器日志格式

worker_processes  2;

events {
    worker_connections  1024;
}

http {
    include       mime.types;
    default_type  application/octet-stream;

        log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '  '$status $body_bytes_sent "$http_referer" ' '"$http_user_agent" "$http_x_forwarded_for"';
                                          
        log_format user_log_format "$u_clickbio||$u_bio||$time_local||$msec||$remote_addr||$status||$body_bytes_sent||$u_domain||$u_url||$u_title||$u_referrer||$u_sh||$u_sw||$u_cd||$u_lang||$http_user_agent||$u_account";
    
    sendfile        on;

    keepalive_timeout  65;

    server {
        listen       80;
        server_name  localhost;
                location /log.gif {

                        default_type image/gif;    

                        access_log  logs/access.log  main;

                        access_by_lua "

                                local uid = ngx.var.cookie___utrace        
                                if not uid then

                                        uid = ngx.md5(ngx.now() .. ngx.var.remote_addr .. ngx.var.http_user_agent)
                                end 
                                ngx.header['Set-Cookie'] = {'__utrace=' .. uid .. '; path=/'}
                                if ngx.var.arg_domain then

                                        ngx.location.capture('/i-log?' .. ngx.var.args .. '&utrace=' .. uid)
                                end 
                        ";  


                        add_header Expires "Fri, 01 Jan 1980 00:00:00 GMT";
                        add_header Pragma "no-cache";
                        add_header Cache-Control "no-cache, max-age=0, must-revalidate";


                        empty_gif;
                }   

                location /i-log {

                        internal;
                    
                        set_unescape_uri $u_clickbio $arg_clickbio;
                        set_unescape_uri $u_bio $arg_bio;
                        set_unescape_uri $u_domain $arg_domain;
                        set_unescape_uri $u_url $arg_url;
                        set_unescape_uri $u_title $arg_title;
                        set_unescape_uri $u_referrer $arg_referrer;
                        set_unescape_uri $u_sh $arg_sh;
                        set_unescape_uri $u_sw $arg_sw;
                        set_unescape_uri $u_cd $arg_cd;
                        set_unescape_uri $u_lang $arg_lang;
                        set_unescape_uri $u_account $arg_account;


                        log_subrequest on;

                        access_log logs/user_defined.log user_log_format;

                        echo '';
                }

    }
}