java抓取保存_JAVA 获取网页源代码保存到本地文件

package httpget;

import java.io.BufferedReader;

import java.io.File;

import java.io.FileNotFoundException;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.HttpURLConnection;

import java.net.URL;

public class demo {

private String u;

private String encoding;

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

String url = "http://www.baidu.com/";

demo client = new demo(url, "gb2312");

client.run();

}

public demo(String u, String encoding) {

this.u = u;

this.encoding = encoding;

}

public void run() throws Exception {

File fp = new File("E:\\zc\\test.txt");

URL url = new URL(u);

// 根据链接(字符串格式)，生成一个URL对象

HttpURLConnection urlConnection = (HttpURLConnection) url

.openConnection();// 打开URL

BufferedReader reader = new BufferedReader(new InputStreamReader(

urlConnection.getInputStream(), encoding));

// 得到输入流，即获得了网页的内容

String line;

while ((line = reader.readLine())!= null)

{

addfile(line,fp);

}

}

public void addfile(String line,File fp) throws IOException //追加文件

{

try {

String str = "\r\n";

FileOutputStream af = new FileOutputStream(fp,true);

af.write(line.getBytes());

af.write(str.getBytes());

} catch (FileNotFoundException e)

{

// TODO Auto-generated catch block

System.out.println("写入失败!");

e.printStackTrace();

}

}

}

如果不明白上面有些方法的意思可以自己去查API文档