数据清洗-每月最火的搜索词

hadoop数据清洗

每月最火的搜索词代码

FirstMapper.java

package com.hniu.bigdata.hadoop.First;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.StringTokenizer;

public class FirstMapper  extends Mapper<LongWritable, Text,Text, NullWritable> {

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


            String line = value.toString();
            // 日期数据处理
            String[] values = line.split("\\s");
            String time = values[values.length - 1];
            SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd");
            String dateTime = format.format(new Date(Long.parseLong(time)));
            // 域名切分
            String url = values[4];
            values[values.length - 1] = dateTime;
            String domain = url.split("/")[0];
            values[4] = domain;
            line = StringUtils.join(" ",values);

            context.write(new Text(line),NullWritable.get());


    }
}

FirstMapReduce

package com.hniu.bigdata.hadoop.First;

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 FirstMapReduce  {

    public static void main(String[] args) throws Exception{
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.179.46:8020");

        Job job = Job.getInstance(configuration, "word count");
        job.setJarByClass(FirstMapReduce.class);
        job.setMapperClass(FirstMapper.class);
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.addInputPath(job, new Path("/syz"));
        FileOutputFormat.setOutputPath(job, new Path("/Clean_Data"));
        job.waitForCompletion(true);
    }
}