抓取网页案例

package com.oracle.test;

import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Reader;
import java.net.MalformedURLException;
import java.net.URL;

public class Test {

public static void main(String[] args) throws IOException  {


    URL url = new URL("http://www.baidu.com");

    //下载网络资源
    InputStream is = url.openStream();
    Reader reader = new InputStreamReader(is,"utf-8");

    //保存到本地
    OutputStream out = new FileOutputStream("F:\\baidu.html");
    OutputStreamWriter osw = new OutputStreamWriter(out, "utf-8");

    char[] c = new char[1024];
    int i = 0;
    StringBuffer sb = new StringBuffer();
    while((i=reader.read(c))!=-1){
        sb.append(c, 0, i);//把下载的内容存到可变字符串中
    }

    String str = sb.toString();
    str = str.replace("src=//", "src=http://");

    osw.write(str);

    osw.close();
    out.close();
    reader.close();
    is.close();

}

}