『Java』一个简单的蜘蛛（Java Spider）

一个简单的java蜘蛛， 通过流的到网站的信息，没有对Html进行分析，等有时间了再完善。

package cn.border.spider;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

public class HttpUserAgentTest {

    /**
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {

        URL url = new URL("http://www.borderj.cn");
        HttpURLConnection httpConnection = (HttpURLConnection) url
                .openConnection();

        //设置User-Agent
        httpConnection.setRequestProperty("User-Agent",
                "BorderSpider ( Http://www.borderj.cn)");

        //获得输入流
        InputStream input = httpConnection.getInputStream();
        InputStreamReader inReader = new InputStreamReader(input, "utf-8");//获得链接该类的流
        BufferedReader reader = new BufferedReader(inReader);

        int retVal = 0;
        char[] cString = new char[1000];
        int len = 1000;
        String getString = "";

        while ((retVal = reader.read(cString, 0, len)) != -1) {
            getString += String.valueOf(cString, 0, retVal);
        }
        System.out.println(getString);
    }
}


--
Blog:     www.borderj.cn
MSN:   borderj@live.com

  Border