Java网络爬虫Hello world实现——Httpclient爬取百度首页

1.创建Maven项目

2.Httpclient Maven地址

 <dependency>
     <groupId>org.apache.httpcomponents</groupId>
     <artifactId>httpclient</artifactId>
     <version>4.5.5</version>
 </dependency>

在pom.xml文件中添加Httpclient jar包

 <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.gxy.blogs</groupId>
     <artifactId>Demo</artifactId>
     <version>0.0.1-SNAPSHOT</version>

     <dependencies>
         <dependency>
             <groupId>org.apache.httpcomponents</groupId>
             <artifactId>httpclient</artifactId>
             <version>4.5.5</version>
         </dependency>
     </dependencies>

 </project>

3.主要代码

 package cha01;

 import java.io.IOException;
 import org.apache.http.HttpEntity;
 import org.apache.http.client.ClientProtocolException;
 import org.apache.http.client.methods.CloseableHttpResponse;
 import org.apache.http.client.methods.HttpGet;
 import org.apache.http.impl.client.CloseableHttpClient;
 import org.apache.http.impl.client.HttpClients;
 import org.apache.http.util.EntityUtils;

 public class Test {

     public static void main(String[] args) throws IOException {
         CloseableHttpClient httpclient=HttpClients.createDefault();
         HttpGet httpget=new HttpGet("http://www.baidu.com");
         CloseableHttpResponse response=httpclient.execute(httpget);
         HttpEntity entity=response.getEntity();
         System.out.println(entity);
         String page=EntityUtils.toString(entity, "utf-8");
         System.out.println(page);
         response.close();
         httpclient.close();
     }
 }

4.运行结果