java利用正则表达式写一个简单的网络爬虫

package regularExpression;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.nio.charset.Charset;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test2
{
	/*
	 * 简单的网络爬虫
	 * 想将淘宝的超链接取出来
	 */
	public static void main(String[] args) throws Exception
	{
		String getString = GetString("https://www.taobao.com/");
		//这里写上非贪婪模式,不然这个链接里面还包含链接
//		Pattern p=Pattern.compile("<a[\\s\\S]+?</a>");
		//这里可以将href和后面的链接取出来
//		Pattern p=Pattern.compile("href=\".+?\"");
//		Pattern p=Pattern.compile("href=\"(.+?)\"");
		//再次进行过滤
		Pattern p=Pattern.compile("href=\"([\\w\\s./:]+?)\"");
		Matcher m = p.matcher(getString);
		while(m.find())
		{
			System.out.println(m.group(1));
		}
	}
	public static String GetString(String url) throws Exception
	{
		URL url2 = new URL(url);
		BufferedReader in=new BufferedReader(new InputStreamReader(url2.openStream(),Charset.forName("utf-8")));
		StringBuffer all=new StringBuffer();
		String temp="";
		while((temp=in.readLine())!=null)
		{
			all.append(temp+"\n");
		}
		return all.toString();
	}
}