Hadoop案例（一）之日志清洗

日志清洗案例

一. 简单解析版

1）需求

去除日志中字段长度小于等于11的日志。

2）输入数据

194.237.142.21 - - [18/Sep/2013:06:49:18 +0000] "GET /wp-content/uploads/2013/07/rstudio-git3.png HTTP/1.1" 304 0 "-" "Mozilla/4.0 (compatible;)"
183.49.46.228 - - [18/Sep/2013:06:49:23 +0000] "-" 400 0 "-" "-"
163.177.71.12 - - [18/Sep/2013:06:49:33 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
163.177.71.12 - - [18/Sep/2013:06:49:36 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
101.226.68.137 - - [18/Sep/2013:06:49:42 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
101.226.68.137 - - [18/Sep/2013:06:49:45 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
60.208.6.156 - - [18/Sep/2013:06:49:48 +0000] "GET /wp-content/uploads/2013/07/rcassandra.png HTTP/1.0" 200 185524 "http://cos.name/category/software/packages/" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36"
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"
222.68.172.190 - - [18/Sep/2013:06:50:08 +0000] "-" 400 0 "-" "-"
183.195.232.138 - - [18/Sep/2013:06:50:16 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
183.195.232.138 - - [18/Sep/2013:06:50:16 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
66.249.66.84 - - [18/Sep/2013:06:50:28 +0000] "GET /page/6/ HTTP/1.1" 200 27777 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
221.130.41.168 - - [18/Sep/2013:06:50:37 +0000] "GET /feed/ HTTP/1.1" 304 0 "-" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36"
157.55.35.40 - - [18/Sep/2013:06:51:13 +0000] "GET /robots.txt HTTP/1.1" 200 150 "-" "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)"
50.116.27.194 - - [18/Sep/2013:06:51:35 +0000] "POST /wp-cron.php?doing_wp_cron=1379487095.2510800361633300781250 HTTP/1.0" 200 0 "-" "WordPress/3.6; http://blog.fens.me"
58.215.204.118 - - [18/Sep/2013:06:51:35 +0000] "GET /nodejs-socketio-chat/ HTTP/1.1" 200 10818 "http://www.google.com/url?sa=t&rct=j&q=nodejs%20%E5%BC%82%E6%AD%A5%E5%B9%BF%E6%92%AD&source=web&cd=1&cad=rja&ved=0CCgQFjAA&url=%68%74%74%70%3a%2f%2f%62%6c%6f%67%2e%66%65%6e%73%2e%6d%65%2f%6e%6f%64%65%6a%73%2d%73%6f%63%6b%65%74%69%6f%2d%63%68%61%74%2f&ei=rko5UrylAefOiAe7_IGQBw&usg=AFQjCNG6YWoZsJ_bSj8kTnMHcH51hYQkAA&bvm=bv.52288139,d.aGc" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-includes/js/jquery/jquery-migrate.min.js?ver=1.2.1 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:35 +0000] "GET /wp-includes/js/jquery/jquery.js?ver=1.10.2 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-includes/js/comment-reply.min.js?ver=3.6 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-content/uploads/2013/08/chat.png HTTP/1.1" 200 48968 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-content/uploads/2013/08/chat2.png HTTP/1.1" 200 59852 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:37 +0000] "GET /wp-content/uploads/2013/08/socketio.png HTTP/1.1" 200 80493 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.248.178.212 - - [18/Sep/2013:06:51:37 +0000] "GET /nodejs-grunt-intro/ HTTP/1.1" 200 51770 "http://blog.fens.me/series-nodejs/" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; MDDR; InfoPath.2; .NET4.0C)"
58.248.178.212 - - [18/Sep/2013:06:51:40 +0000] "GET /wp-includes/js/jquery/jquery-migrate.min.js?ver=1.2.1 HTTP/1.1" 200 7200 "http://blog.fens.me/nodejs-grunt-intro/" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; MDDR; InfoPath.2; .NET4.0C)"

3）实现代码

（1）编写LogMapper

package com.xyg.mapreduce.weblog;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
    
    Text k = new Text();
    
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        
        // 1 获取1行数据
        String line = value.toString();        
        // 2 解析日志
        boolean result = parseLog(line,context);       
        // 3 日志不合法退出
        if (!result) {
            return;
        }     
        // 4 设置key
        k.set(line);   
        // 5 写出数据
        context.write(k, NullWritable.get());
    }
    // 2 解析日志
    private boolean parseLog(String line, Context context) {
        // 1 截取
        String[] fields = line.split(" ");
        
        // 2 日志长度大于11的为合法
        if (fields.length > 11) {
            // 系统计数器
            context.getCounter("map", "true").increment(1);
            return true;
        }else {
            context.getCounter("map", "false").increment(1);
            return false;
        }
    }
}

（2）编写LogDriver

package com.xyg.mapreduce.weblog;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class LogDriver {

    public static void main(String[] args) throws Exception {
        args = new String[] { "e:/inputlog", "e:/output1" };
    // 1 获取job信息
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf);
    // 2 加载jar包
    job.setJarByClass(LogDriver.class);
    // 3 关联map
    job.setMapperClass(LogMapper.class);
    // 4 设置最终输出类型
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);
    // 5 设置输入和输出路径
    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    // 6 提交
    job.waitForCompletion(true);
    }
}

二. 复杂解析版

1）需求

对web访问日志中的各字段识别切分

去除日志中不合法的记录

根据统计需求，生成各类访问请求过滤数据

2）输入数据

194.237.142.21 - - [18/Sep/2013:06:49:18 +0000] "GET /wp-content/uploads/2013/07/rstudio-git3.png HTTP/1.1" 304 0 "-" "Mozilla/4.0 (compatible;)"
183.49.46.228 - - [18/Sep/2013:06:49:23 +0000] "-" 400 0 "-" "-"
163.177.71.12 - - [18/Sep/2013:06:49:33 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
163.177.71.12 - - [18/Sep/2013:06:49:36 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
101.226.68.137 - - [18/Sep/2013:06:49:42 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
101.226.68.137 - - [18/Sep/2013:06:49:45 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
60.208.6.156 - - [18/Sep/2013:06:49:48 +0000] "GET /wp-content/uploads/2013/07/rcassandra.png HTTP/1.0" 200 185524 "http://cos.name/category/software/packages/" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36"
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"
222.68.172.190 - - [18/Sep/2013:06:50:08 +0000] "-" 400 0 "-" "-"
183.195.232.138 - - [18/Sep/2013:06:50:16 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
183.195.232.138 - - [18/Sep/2013:06:50:16 +0000] "HEAD / HTTP/1.1" 200 20 "-" "DNSPod-Monitor/1.0"
66.249.66.84 - - [18/Sep/2013:06:50:28 +0000] "GET /page/6/ HTTP/1.1" 200 27777 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
221.130.41.168 - - [18/Sep/2013:06:50:37 +0000] "GET /feed/ HTTP/1.1" 304 0 "-" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.66 Safari/537.36"
157.55.35.40 - - [18/Sep/2013:06:51:13 +0000] "GET /robots.txt HTTP/1.1" 200 150 "-" "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)"
50.116.27.194 - - [18/Sep/2013:06:51:35 +0000] "POST /wp-cron.php?doing_wp_cron=1379487095.2510800361633300781250 HTTP/1.0" 200 0 "-" "WordPress/3.6; http://blog.fens.me"
58.215.204.118 - - [18/Sep/2013:06:51:35 +0000] "GET /nodejs-socketio-chat/ HTTP/1.1" 200 10818 "http://www.google.com/url?sa=t&rct=j&q=nodejs%20%E5%BC%82%E6%AD%A5%E5%B9%BF%E6%92%AD&source=web&cd=1&cad=rja&ved=0CCgQFjAA&url=%68%74%74%70%3a%2f%2f%62%6c%6f%67%2e%66%65%6e%73%2e%6d%65%2f%6e%6f%64%65%6a%73%2d%73%6f%63%6b%65%74%69%6f%2d%63%68%61%74%2f&ei=rko5UrylAefOiAe7_IGQBw&usg=AFQjCNG6YWoZsJ_bSj8kTnMHcH51hYQkAA&bvm=bv.52288139,d.aGc" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-includes/js/jquery/jquery-migrate.min.js?ver=1.2.1 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:35 +0000] "GET /wp-includes/js/jquery/jquery.js?ver=1.10.2 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-includes/js/comment-reply.min.js?ver=3.6 HTTP/1.1" 304 0 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-content/uploads/2013/08/chat.png HTTP/1.1" 200 48968 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:36 +0000] "GET /wp-content/uploads/2013/08/chat2.png HTTP/1.1" 200 59852 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.215.204.118 - - [18/Sep/2013:06:51:37 +0000] "GET /wp-content/uploads/2013/08/socketio.png HTTP/1.1" 200 80493 "http://blog.fens.me/nodejs-socketio-chat/" "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0"
58.248.178.212 - - [18/Sep/2013:06:51:37 +0000] "GET /nodejs-grunt-intro/ HTTP/1.1" 200 51770 "http://blog.fens.me/series-nodejs/" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; MDDR; InfoPath.2; .NET4.0C)"
58.248.178.212 - - [18/Sep/2013:06:51:40 +0000] "GET /wp-includes/js/jquery/jquery-migrate.min.js?ver=1.2.1 HTTP/1.1" 200 7200 "http://blog.fens.me/nodejs-grunt-intro/" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; MDDR; InfoPath.2; .NET4.0C)"

3）实现代码

（1）定义一个bean，用来记录日志数据中的各数据字段

package com.xyg.mapreduce.log;

public class LogBean {
    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 boolean valid = true;// 判断数据是否合法

    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;
    }

    public boolean isValid() {
        return valid;
    }

    public void setValid(boolean valid) {
        this.valid = valid;
    }

    @Override
    public String toString() {
        StringBuilder sb = new StringBuilder();
        sb.append(this.valid);
        sb.append("\001").append(this.remote_addr);
        sb.append("\001").append(this.remote_user);
        sb.append("\001").append(this.time_local);
        sb.append("\001").append(this.request);
        sb.append("\001").append(this.status);
        sb.append("\001").append(this.body_bytes_sent);
        sb.append("\001").append(this.http_referer);
        sb.append("\001").append(this.http_user_agent);
        
        return sb.toString();
    }
}

（2）编写LogMapper程序

package com.xyg.mapreduce.log;

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
    Text k = new Text();
    
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        // 1 获取1行
        String line = value.toString();        
        // 2 解析日志是否合法
        LogBean bean = pressLog(line);        
        if (!bean.isValid()) {
            return;
        }        
        k.set(bean.toString());        
        // 3 输出
        context.write(k, NullWritable.get());
    }

    // 解析日志
    private LogBean pressLog(String line) {
        LogBean logBean = new LogBean();
        // 1 截取
        String[] fields = line.split(" ");   
        if (fields.length > 11) {
            // 2封装数据
            logBean.setRemote_addr(fields[0]);
            logBean.setRemote_user(fields[1]);
            logBean.setTime_local(fields[3].substring(1));
            logBean.setRequest(fields[6]);
            logBean.setStatus(fields[8]);
            logBean.setBody_bytes_sent(fields[9]);
            logBean.setHttp_referer(fields[10]);
            
            if (fields.length > 12) {
                logBean.setHttp_user_agent(fields[11] + " "+ fields[12]);
            }else {
                logBean.setHttp_user_agent(fields[11]);
            }           
            // 大于400，HTTP错误
            if (Integer.parseInt(logBean.getStatus()) >= 400) {
                logBean.setValid(false);
            }
        }else {
            logBean.setValid(false);
        }
        return logBean;
    }
}

（3）编写LogDriver程序

package com.xyg.mapreduce.log;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class LogDriver {
    public static void main(String[] args) throws Exception {
        // 1 获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2 加载jar包
        job.setJarByClass(LogDriver.class);
        // 3 关联map
        job.setMapperClass(LogMapper.class);
        // 4 设置最终输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        // 5 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 6 提交
        job.waitForCompletion(true);
    }
}