public class Demo01 {

    public static void main(String[] args) {

        //表达式对象

        Pattern p = Pattern.compile("\\w+");

        //创建Matcher对象

        Matcher m  = p.matcher("asfsdf&23323");

        boolean flag = m.matches(); //尝试将整个字符序列与该模式匹配

        boolean flag2 = m.find(); //该方法扫描输入的序列，查找与该模式匹配的下一个子序列

        String str = m.group(); //返回找到的字符串

        String newStr = m.replaceAll("#");///替换

        String str2 = "asds234adsa23sdsf";

        String[] arrs = str2.split("\\d+");

        System.out.println(Arrays.toString(arrs));

    }

}

/**

 * 简单网络爬虫

 * @author MA

 *

 */

public class WebSpiderTest {

    public static String getURLContent(String urlStr,String charSet) throws IOException{

        StringBuilder sb = new StringBuilder();

        try {

            URL url = new URL(urlStr);

            BufferedReader reader =new BufferedReader(new InputStreamReader(url.openStream(),Charset.forName(charSet)));

            String temp = "";

            while((temp=reader.readLine())!=null){

                //System.out.println(temp);

                sb.append(temp);

            }

        } catch (MalformedURLException e) {

            e.printStackTrace();

        }

        return sb.toString();

    }

    public static List<String> getMatherSubstrs(String destStr,String regexStr){

        //Pattern p = Pattern.compile("<a[\\s\\S]+?</a>");//取到超链接整个内容

        Pattern p = Pattern.compile(regexStr);//取到超链接地址

        Matcher m = p.matcher(destStr);

        List<String> result =new ArrayList<String>();

        while(m.find()){

            result.add(m.group(1));

        }

        return result;

    }

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

        String destStr = getURLContent("http://www.163.com","gbk");

        List<String> result = getMatherSubstrs(destStr, "href=\"([\\w\\s./:]+?)\"");

        for(String temp : result){

            System.out.println(temp);

        }

    }

}