hadoop的hdfs，下载文件

1、首先启动hadoop

start-all.sh

2、建立maven工程

2.1 编辑pom.xml文件

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>com.js</groupId>
  <artifactId>ss</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>ss</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <!-- 定義一個變量 -->
    <hadoop.version>3.1.1</hadoop.version>
  </properties>
 
  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
     
    <!-- JDK依賴 -->
    <dependency>
        <groupId>jdk.tools</groupId>
        <artifactId>jdk.tools</artifactId>
        <version>1.8</version>
        <scope>system</scope>
        <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
    </dependency>
     
    <!-- hadoop start -->
     
      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-hdfs</artifactId>
          <version>${hadoop.version}</version>
      </dependency>
     
      <dependency> 
          <groupId>org.apache.hadoop</groupId> 
          <artifactId>hadoop-client</artifactId> 
          <version>${hadoop.version}</version> 
      </dependency>
     
      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-common</artifactId>
          <version>${hadoop.version}</version>
      </dependency>
       
     <!-- hadoop end -->
 </dependencies>
 
</project>

2.2 新建一个类文件

package com.js;

import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

/**
 * Hello world!
 *
 */
public class App 
{
    public static void main( String[] args ) throws IOException, InterruptedException, URISyntaxException {
        System.out.println( "Hello World!" );
        System.out.println("hello world");

        
        Configuration conf = new Configuration();
        // 设置hadoop的文件系统格式
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        
        FileSystem fs = FileSystem.get(conf);
        
        Path src = new Path("/wordcount/input");
        FSDataInputStream in = fs.open(src);
        
        FileOutputStream os = new FileOutputStream("./out");
        IOUtils.copyBytes(in, os, conf, true);
        
    }
}

在当前目录下,会出现out文件