/*
* 实现网页抓取http://www.qq.com
* 技术:导入URl地址,从URl地址中获取字节流,Reader使字节流转成字符流,用行读取方法读字符,把所有的字符串连接,用OutputStream的Write方法写入到文件中
*/
package tengxun;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
public class Tengxun {
public static void main(String[] args)
{
try
{
File f = new File("E:\\MyEclipse6.5\\workspace\\PageGet\\src\\tengxun\\qq.html");
URL url = new URL("http://www.qq.com");
InputStream is = url.openStream();
BufferedReader br= new BufferedReader(new InputStreamReader(is));
String s = br.readLine();
String last = "";
FileOutputStream fo = new FileOutputStream(f);
while(s != null)
{
last = last + s;
s = br.readLine();
}
byte[] b = last.getBytes();
fo.write(b, 0, b.length);
System.out.println("succeeful!!!");
fo.close();
}
catch(Exception e)
{
System.out.print(e);
}
}
}