mapreducer提取一个网站的信息

package zidingyi;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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 YongSubmitter{
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf=new Configuration();
    FileSystem fs=FileSystem.get(conf);
    if(fs.exists(new Path(args[1]))) {
        fs.delete(new Path(args[1]),true);
    }
    Job job=Job.getInstance();
    job.setJarByClass(YongSubmitter.class);
    
    job.setMapperClass(YongMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(NullWritable.class);
    
    job.setReducerClass(YongReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);
    
    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.waitForCompletion(true);
}
}

 

package zidingyi;
 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 YongMapper extends Mapper<LongWritable,Text, Text,NullWritable>{ 

@Override protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, 
InterruptedException { 
String line=value.toString(); 
String str[]=line.split(","); 
String phone=str[0]+"\t"+str[3]+"\t"+str[4]; 
context.write(new Text(phone),NullWritable.get()); 
} 
}

package zidingyi;

import java.io.IOException;

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

public class YongReducer extends Reducer<Text,NullWritable, Text,NullWritable>{
    @Override
    protected void reduce(Text k, Iterable<NullWritable> v,
            Reducer<Text, NullWritable, Text, NullWritable>.Context context) throws IOException, InterruptedException {
         context.write(k,NullWritable.get());    
    }

}

 文本和文件在文本里