Day6：Hadoop实战--电商分析（三）

weixin_69071093

已于 2024-06-21 16:14:49 修改

阅读量125

点赞数 1

文章标签： hadoop 大数据分布式 mapreduce

于 2024-06-19 22:05:54 首次发布

本文链接：https://blog.csdn.net/weixin_69071093/article/details/139814130

版权

项目要求：

根据电商日志文件，分析：

1、统计页面浏览量（每行记录就是一次浏览）
2、统计各个省份的浏览量（需要解析IP）
3、日志的ETL操作：解析出ip、url、pageId（topicId对应的页面Id）、country、province、city

项目过程：

今天主要完成第三问：日志的ETL操作

mapper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);
        }
    }
}

reduce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);
    }
}

ELTDrive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);
    }
}