Java实例——基于jsoup的简单爬虫

import java.io.IOException;

import java.net.Authenticator;

import java.net.InetSocketAddress;

import java.net.PasswordAuthentication;

import java.net.Proxy;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

public class Demo{

// 代理隧道验证信息

final static String ProxyUser = "16KASDA";

final static String ProxyPass = "1231321";

// 代理服务器

final static String ProxyHost = "t.16yun.cn";

final static Integer ProxyPort = 31111;

// 设置IP切换头

final static String ProxyHeadKey = "Proxy-Tunnel";

public static String getUrlProxyContent(String url)

{

Authenticator.setDefault(new Authenticator() {

public PasswordAuthentication getPasswordAuthentication()

{

return new PasswordAuthentication(ProxyUser, ProxyPass.toCharArray());

}

});

// 设置Proxy-Tunnel

Random random = new Random();

int tunnel = random.nextInt(10000);

String ProxyHeadVal = String.valueOf(tunnel);

Proxy proxy = new Proxy(Proxy.Type.HTTP, new InetSocketAddress(ProxyHost, ProxyPort));

try

{

// 处理异常、其他参数

Document doc = Jsoup.connect(url).timeout(3000).header(ProxyHeadKey, ProxyHeadVal).proxy(proxy).get();

if(doc != null) {

System.out.println(doc.body().html());

}

}

catch (IOException e)

{

e.printStackTrace();

}

return null;

}

public static void main(String[] args) throws Exception

{

// 要访问的目标页面

String targetUrl = "http://httpbin.org/ip";

getUrlProxyContent(targetUrl);

}}