Hadoop电商分析（三）

一、问题描述

  日志的ETL操作（ETL：数据从来源端经过抽取（Extract）、转换（Transform）、加载（Load）至目的端的过程）

   为什么要ETL：没有必要解析出所有数据，只需要解析出有价值的字段即可。本项目中需要解析出：ip、url、pageId（topicId对应的页面Id）、country、province、city

二、实现步骤及代码

（1）将文件上传至hdfs上

（2）代码部分

Map阶段：

package page;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class PageViewMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] parts = line.split("\\x01"); // 使用特殊字符分隔符 (ASCII SOH)
        String count = "count";
        if (parts.length >= 2) { // 确保行包含至少两部分
            String page = count;
            word.set(page);
            context.write(word, one);
        } else {
            // 处理不合法的行
            System.err.println("Skipping invalid line: " + line);
        }
    }
}

Reducer阶段

package page;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class PageViewReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable result = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

ETLDriver部分

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 LogETLDriver {

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


        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Log ETL");

        job.setJarByClass(LogETLDriver.class);
        job.setMapperClass(LogETLMapper.class);
        job.setCombinerClass(LogETLReducer.class);
        job.setReducerClass(LogETLReducer.class);

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

        FileInputFormat.addInputPath(job, new Path("输入文件路径"));
        FileOutputFormat.setOutputPath(job, new Path("输出文件路径"));


        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

三、结果展示