java抓取网页css,Java 读取网页Html资料

当前位置:我的异常网» HTML/CSS » Java 读取网页Html资料

Java 读取网页Html资料

www.myexceptions.net  网友分享于：2013-10-27  浏览：13次

Java 读取网页Html文件

import java.net.*;

import java.io.*;

public class urlconnection

{

public static void main(String[] args)

{

StringBuffer document = new StringBuffer();

try

{

URL url = new URL("http://www.163.com");

URLConnection conn = url.openConnection();

BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream()));

String line = null;

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

document.append(line + " ");

reader.close();

}

catch (MalformedURLException e)

{

e.printStackTrace();

}

catch (IOException e)

{

e.printStackTrace();

}

System.out.println(document.toString());

}

}

==========================================================

方法二：

==========================================================

import java.net.*;

import java.io.*;

public class useSourceViewer

{

public static void main (String[] args)

{

if (args.length > 0)

{

try

{

URL u = new URL(args[0]);

InputStream in = u.openStream( );

in = new BufferedInputStream(in);

Reader r = new InputStreamReader(in);

int c;

while ((c = r.read( )) != -1)

{

System.out.print((char) c);

}

Object o = u.getContent( );

System.out.println("I got a " + o.getClass().getName( ));

}

catch (MalformedURLException e)

{

System.err.println(args[0] + " is not a parseable URL");

}

catch (IOException e)

{

System.err.println(e);

}

}

}

}

文章评论