我第一个java爬虫

先定一个网页字符串的匹配规则

 String regex = "https://[\\w+\\.?/?]+\\.[A-Za-z]+";

 URLConnection创建一个connection

通过将connection作为一个输入流

通过一个匹配器，如果URL满足匹配规则，就输出控制台

package com.cellstrain.icell.util;

import java.io.*;
import java.net.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * java爬虫
 */
public class Robot {
    public static void main(String[] args) {
        URL url = null;
        URLConnection urlconn = null;
        BufferedReader br = null;
        PrintWriter pw = null;

        String regex = "https://[\\w+\\.?/?]+\\.[A-Za-z]+";//url匹配规则
        Pattern p = Pattern.compile(regex);
        try {
            url = new URL("https://www.rndsystems.com/cn");
            urlconn = url.openConnection();
            br = new BufferedReader(new InputStreamReader(
                    urlconn.getInputStream()));
            String buf = null;
            while ((buf = br.readLine()) != null) {
                Matcher buf_m = p.matcher(buf);
                while (buf_m.find()) {
                    System.out.println(buf_m.group());
                }
            }

        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                br.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}