hadoop 网站日志分析

jopen 10年前

一、项目要求


  • 本文讨论的日志处理方法中的日志,仅指Web日志。其实并没有精确的定义,可能包括但不限于各种前端Web服务器——apache、lighttpd、nginx、tomcat等产生的用户访问日志,以及各种Web应用程序自己输出的日志。  


二、需求分析: KPI指标设计

 PV(PageView): 页面访问量统计
 IP: 页面独立IP的访问量统计
 Time: 用户每小时PV的统计
 Source: 用户来源域名的统计
 Browser: 用户的访问设备统计

下面我着重分析浏览器统计

三、分析过程

1、 日志的一条nginx记录内容

222.68.172.190  - - [18/Sep/2013:06:49:57 +0000] "GET /images/my.jpg HTTP/1.1" 200 19939 
"http://www.angularjs.cn/A00n" 
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36"

2、对上面的日志记录进行分析

remote_addr : 记录客户端的ip地址, 222.68.172.190
remote_user :  记录客户端用户名称, –
time_local:  记录访问时间与时区, [18/Sep/2013:06:49:57 +0000]
request: 记录请求的url与http协议, “GET /images/my.jpg HTTP/1.1″
status:  记录请求状态,成功是200, 200
body_bytes_sent:  记录发送给客户端文件主体内容大小, 19939
http_referer:  用来记录从那个页面链接访问过来的, “http://www.angularjs.cn/A00n”
http_user_agent:  记录客户浏览器的相关信息, “Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36″  

3、java语言分析上面一条日志记录(使用空格切分)

String line = "222.68.172.190 - - [18/Sep/2013:06:49:57 +0000] \"GET /images/my.jpg HTTP/1.1\" 200 19939 \"http://www.angularjs.cn/A00n\" \"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36\"";       String[] elementList = line.split(" ");       for(int i=0;i<elementList.length;i++){        System.out.println(i+" : "+elementList[i]);       }

测试结果:

0 : 222.68.172.190  1 : -  2 : -  3 : [18/Sep/2013:06:49:57  4 : +0000]  5 : "GET  6 : /images/my.jpg  7 : HTTP/1.1"  8 : 200  9 : 19939  10 : "http://www.angularjs.cn/A00n"  11 : "Mozilla/5.0  12 : (Windows  13 : NT  14 : 6.1)  15 : AppleWebKit/537.36  16 : (KHTML,  17 : like  18 : Gecko)  19 : Chrome/29.0.1547.66  20 : Safari/537.36"
4、实体Kpi类的代码:
public class Kpi {   private String remote_addr;// 记录客户端的ip地址      private String remote_user;// 记录客户端用户名称,忽略属性"-"      private String time_local;// 记录访问时间与时区      private String request;// 记录请求的url与http协议      private String status;// 记录请求状态;成功是200      private String body_bytes_sent;// 记录发送给客户端文件主体内容大小      private String http_referer;// 用来记录从那个页面链接访问过来的      private String http_user_agent;// 记录客户浏览器的相关信息      private String method;//请求方法 get post      private String http_version; //http版本         public String getMethod() {    return method;   }   public void setMethod(String method) {    this.method = method;   }   public String getHttp_version() {    return http_version;   }   public void setHttp_version(String http_version) {    this.http_version = http_version;   }   public String getRemote_addr() {    return remote_addr;   }   public void setRemote_addr(String remote_addr) {    this.remote_addr = remote_addr;   }   public String getRemote_user() {    return remote_user;   }   public void setRemote_user(String remote_user) {    this.remote_user = remote_user;   }   public String getTime_local() {    return time_local;   }   public void setTime_local(String time_local) {    this.time_local = time_local;   }   public String getRequest() {    return request;   }   public void setRequest(String request) {    this.request = request;   }   public String getStatus() {    return status;   }   public void setStatus(String status) {    this.status = status;   }   public String getBody_bytes_sent() {    return body_bytes_sent;   }   public void setBody_bytes_sent(String body_bytes_sent) {    this.body_bytes_sent = body_bytes_sent;   }   public String getHttp_referer() {    return http_referer;   }   public void setHttp_referer(String http_referer) {    this.http_referer = http_referer;   }   public String getHttp_user_agent() {    return http_user_agent;   }   public void setHttp_user_agent(String http_user_agent) {    this.http_user_agent = http_user_agent;   }   @Override   public String toString() {    return "Kpi [remote_addr=" + remote_addr + ", remote_user="      + remote_user + ", time_local=" + time_local + ", request="      + request + ", status=" + status + ", body_bytes_sent="      + body_bytes_sent + ", http_referer=" + http_referer      + ", http_user_agent=" + http_user_agent + ", method=" + method      + ", http_version=" + http_version + "]";   }             }
5、kpi的工具类
package org.aaa.kpi;    public class KpiUtil {   /***    * line记录转化成kpi对象    * @param line 日志的一条记录    * @author tianbx    * */   public static Kpi transformLineKpi(String line){    String[] elementList = line.split(" ");    Kpi kpi = new Kpi();       kpi.setRemote_addr(elementList[0]);       kpi.setRemote_user(elementList[1]);       kpi.setTime_local(elementList[3].substring(1));       kpi.setMethod(elementList[5].substring(1));       kpi.setRequest(elementList[6]);       kpi.setHttp_version(elementList[7]);       kpi.setStatus(elementList[8]);       kpi.setBody_bytes_sent(elementList[9]);       kpi.setHttp_referer(elementList[10]);       kpi.setHttp_user_agent(elementList[11] + " " + elementList[12]);    return kpi;   }  }

6、算法模型: 并行算法 

Browser: 用户的访问设备统计
– Map: {key:$http_user_agent,value:1}
– Reduce: {key:$http_user_agent,value:求和(sum)} 
7、map-reduce分析代码


import java.io.IOException;  import java.util.Iterator;    import org.apache.hadoop.fs.Path;  import org.apache.hadoop.io.IntWritable;  import org.apache.hadoop.io.Text;  import org.apache.hadoop.mapred.FileInputFormat;  import org.apache.hadoop.mapred.FileOutputFormat;  import org.apache.hadoop.mapred.JobClient;  import org.apache.hadoop.mapred.JobConf;  import org.apache.hadoop.mapred.MapReduceBase;  import org.apache.hadoop.mapred.Mapper;  import org.apache.hadoop.mapred.OutputCollector;  import org.apache.hadoop.mapred.Reducer;  import org.apache.hadoop.mapred.Reporter;  import org.apache.hadoop.mapred.TextInputFormat;  import org.apache.hadoop.mapred.TextOutputFormat;  import org.hmahout.kpi.entity.Kpi;  import org.hmahout.kpi.util.KpiUtil;    import cz.mallat.uasparser.UASparser;  import cz.mallat.uasparser.UserAgentInfo;    public class KpiBrowserSimpleV {     public static class KpiBrowserSimpleMapper extends MapReduceBase     implements Mapper<Object, Text, Text, IntWritable> {    UASparser parser = null;    @Override    public void map(Object key, Text value,      OutputCollector<Text, IntWritable> out, Reporter reporter)      throws IOException {     Kpi kpi = KpiUtil.transformLineKpi(value.toString());       if(kpi!=null && kpi.getHttP_user_agent_info()!=null){      if(parser==null){       parser = new UASparser();      }      UserAgentInfo info =       parser.parseBrowserOnly(kpi.getHttP_user_agent_info());      if("unknown".equals(info.getUaName())){       out.collect(new Text(info.getUaName()), new IntWritable(1));      }else{       out.collect(new Text(info.getUaFamily()), new IntWritable(1));      }       }    }   }     public static class KpiBrowserSimpleReducer extends MapReduceBase implements    Reducer<Text, IntWritable, Text, IntWritable>{      @Override    public void reduce(Text key, Iterator<IntWritable> value,      OutputCollector<Text, IntWritable> out, Reporter reporter)      throws IOException {     IntWritable sum = new IntWritable(0);     while(value.hasNext()){      sum.set(sum.get()+value.next().get());     }     out.collect(key, sum);    }   }   public static void main(String[] args) throws IOException {    String input = "hdfs://127.0.0.1:9000/user/tianbx/log_kpi/input";          String output ="hdfs://127.0.0.1:9000/user/tianbx/log_kpi/browerSimpleV";          JobConf conf = new JobConf(KpiBrowserSimpleV.class);          conf.setJobName("KpiBrowserSimpleV");          String url = "classpath:";          conf.addResource(url+"/hadoop/core-site.xml");          conf.addResource(url+"/hadoop/hdfs-site.xml");          conf.addResource(url+"/hadoop/mapred-site.xml");                    conf.setMapOutputKeyClass(Text.class);          conf.setMapOutputValueClass(IntWritable.class);                    conf.setOutputKeyClass(Text.class);          conf.setOutputValueClass(IntWritable.class);                    conf.setMapperClass(KpiBrowserSimpleMapper.class);          conf.setCombinerClass(KpiBrowserSimpleReducer.class);          conf.setReducerClass(KpiBrowserSimpleReducer.class);            conf.setInputFormat(TextInputFormat.class);          conf.setOutputFormat(TextOutputFormat.class);            FileInputFormat.setInputPaths(conf, new Path(input));          FileOutputFormat.setOutputPath(conf, new Path(output));            JobClient.runJob(conf);          System.exit(0);   }    }


8、输出文件log_kpi/browerSimpleV内容

AOL Explorer 1
Android Webkit 123
Chrome 4867
CoolNovo 23
Firefox 1700
Google App Engine 5
IE 1521
Jakarta Commons-HttpClient 3
Maxthon 27
Mobile Safari 273
Mozilla 130
Openwave Mobile Browser 2
Opera 2
Pale Moon 1
Python-urllib 4
Safari 246
Sogou Explorer 157
unknown 4685

8 R制作图片


data<-read.table(file="borwer.txt",header=FALSE,sep=",") 

 names(data)<-c("borwer","num")

 qplot(borwer,num,data=data,geom="bar")


hadoop 网站日志分析


解决问题

1、排除爬虫和程序点击,对抗作弊

解决办法:页面做个检测鼠标是否动。

2、浏览量 怎么排除图片

3、浏览量排除假点击?

4、哪一个搜索引擎访问的?

5、点击哪一个关键字访问的?

6、从哪一个地方访问的?

7、使用哪一个浏览器访问的?