采用HttpClient和Jsoup实现简单的网页爬虫

在我们的学习过程中，有些时候难免可能需要在网上爬一些数据之类的，没有学过Python爬虫可能让你有些手足无措，这里我们就用Java程序实现一个简单的的网页爬虫程序。

jar包

HttpClient的使用

package tqb.test.httpclient;

import java.io.IOException;

import javax.swing.text.html.parser.Entity;

import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.conn.params.ConnRouteParams;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.CoreConnectionPNames;
import org.apache.http.util.EntityUtils;
import org.junit.Test;

/**
 * HttpClient的使用
 * @author tqb
 *
 */
public class Demo {

	@Test
	public void fun() throws ClientProtocolException, IOException{
		
		/*
		 * 创建HttpClient对象
		 */
		HttpClient http = new DefaultHttpClient();
		
		/*
		 * 创建要连接的url字符串,这里是我的博客地址
		 */
		String url = "https://blog.csdn.net/weixin_42061805";
		
		/*
		 * 设置代理服务器，有些网站可能有反爬虫，设置这个以防该网站对我的ip地址进行封锁
		 * 这里我们不设置代理服务器了，有兴趣的自己在网上寻找代理服务器
		 */
//		String ip = "";
//		int port = 10000;
		
		/*
		 * 获得HttpClient参数对象并进行设置
		 */
		http.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 3000).//设置连接超时
		setParameter(CoreConnectionPNames.SO_TIMEOUT, 3000);//设置响应超时
		//setParameter(ConnRouteParams.DEFAULT_PROXY, new HttpHost(ip,port));//设置代理服务器
		
		/*
		 * 设置请求方式
		 */
		HttpGet request = new HttpGet(url);
	
		/*
		 * 处理请求并响应
		 */
		HttpResponse response = http.execute(request);
	
		/*
		 * 获得响应的内容并打印输出
		 */
		String text = EntityUtils.toString(response.getEntity(), "utf-8");
		System.out.println(text);//这里打印出的就是当前地址的源码
	}

}

Jsoup的使用

package tqb.test.jsoup;

import java.io.IOException;

import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.junit.Test;

public class Demo {

	@Test
	public void fun() throws IOException{
		
		String url = "https://blog.csdn.net/weixin_42061805";
		
		/*
		 * 获取连接对象
		 */
		Connection conn = Jsoup.connect(url);
		
		/*
		 * 获得document 
		 */
		Document document = conn.get();
		
		/*
		 * 设置cssquery表达式得到元素集合
		 */
		Elements elements = document.select("h4 a");
		
		/*
		 * 遍历元素集合
		 */
		for (Element element : elements) {
			/*
			 * 打印该元素的文本和其href属性的值
			 */
			System.out.println(element.text() + ":" + element.attr("href"));
		}
	}

}

运行结果

HttpClient和Jsoup的结合使用

package tqb.test.jsoup;

import java.io.IOException;

import org.apache.http.HttpResponse;
import org.apache.http.ParseException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.junit.Test;

public class Demo2 {

	@Test
	public void fun() throws ParseException, IOException{
		String url = "https://blog.csdn.net/weixin_42061805";
		
		HttpClient http = new DefaultHttpClient();
		
		HttpGet request = new HttpGet(url);
		
		HttpResponse response = http.execute(request);
		
		String text = EntityUtils.toString(response.getEntity(),"utf-8");
	
		/*
		 * 解析内容
		 */
		Document document = Jsoup.parse(text);

		Elements elements = document.select("h4 a");

		for (Element element : elements) {
			System.out.println(element.text() + ":" + element.attr("href"));
		}
	}

}