Hadoop_25_MapReduce实现日志清洗程序

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KPI统计需求，生成各类访问请求过滤数据

2、实现代码：

a) 定义一个bean，用来记录日志数据中的各数据字段

package cn.bigdta.hdfs.weblog;

public class WebLogBean {

    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();
    }
}

b)定义一个parser用来解析过滤web访问日志原始记录

package cn.bigdta.hdfs.weblog;

import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Locale;

public class WebLogParser {

    static SimpleDateFormat sd1 = new SimpleDateFormat("dd/MMM/yyyy:HH:mm:ss", Locale.US);

    static SimpleDateFormat sd2 = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");

    public static WebLogBean parser(String line) {
        WebLogBean webLogBean = new WebLogBean();
        String[] arr = line.split(" ");
        if (arr.length > 11) {
            webLogBean.setRemote_addr(arr[0]);
            webLogBean.setRemote_user(arr[1]);
            webLogBean.setTime_local(parseTime(arr[3].substring(1)));
            webLogBean.setRequest(arr[6]);
            webLogBean.setStatus(arr[8]);
            webLogBean.setBody_bytes_sent(arr[9]);
            webLogBean.setHttp_referer(arr[10]);

            if (arr.length > 12) {
                webLogBean.setHttp_user_agent(arr[11] + " " + arr[12]);
            } else {
                webLogBean.setHttp_user_agent(arr[11]);
            }
            if (Integer.parseInt(webLogBean.getStatus()) >= 400) {// 大于400，HTTP错误
                webLogBean.setValid(false);
            }
        } else {
            webLogBean.setValid(false);
        }
        return webLogBean;
    }

    public static String parseTime(String dt) {

        String timeString = "";
        try {
            Date parse = sd1.parse(dt);
            timeString = sd2.format(parse);

        } catch (ParseException e) {
            e.printStackTrace();
        }
        return timeString;
    }
}

c) mapreduce程序

package cn.bigdta.hdfs.weblog;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WeblogPreProcess {

    static class WeblogPreProcessMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
        Text k = new Text();
        NullWritable v = NullWritable.get();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();
            WebLogBean webLogBean = WebLogParser.parser(line);
            //可以插入一个静态资源过滤（.....）
            /*WebLogParser.filterStaticResource(webLogBean);*/
            if (!webLogBean.isValid())
                return;
            k.set(webLogBean.toString());
            context.write(k, v);
        }
    }

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(WeblogPreProcess.class);

        job.setMapperClass(WeblogPreProcessMapper.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job, new Path("F:/weblog"));
        FileOutputFormat.setOutputPath(job, new Path("F:/weblogOut"));

        job.waitForCompletion(true);

    }
}

日志文件下载：https://pan.baidu.com/s/17oOaA_S5RRDKjFhCqMm40A