java网络爬虫

  java 源代码class文件  --->字节编码->虚拟机运行。 java 图形界面，Swing，SWT等。AWT现在基本不用。JavaFX

package example;
import java.io.*;
import java.net.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
    /**
     * java实现爬虫
     */
    public class Robot {
        public static void main(String[] args) {
            URL url = null;
            URLConnection urlconn = null;
            BufferedReader br = null;
            PrintWriter pw = null;
//        String regex = "http://[\\w+\\.?/?]+\\.[A-Za-z]+";
            String regex = "https://[\\w+\\.?/?]+\\.[A-Za-z]+";//url匹配规则
            Pattern p = Pattern.compile(regex);
            try {
                url = new URL("https://www.iqiyi.com/cn");//爬取的网址、这里爬取的是一个生物网站
                urlconn = url.openConnection();
                pw = new PrintWriter(new FileWriter("D:/SiteURL.txt"), true);//将爬取到的链接放到D盘的SiteURL文件中
                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()) {
                        pw.println(buf_m.group());
                    }
                }
                System.out.println("爬取成功^_^");
            } catch (MalformedURLException e) {
                e.printStackTrace();
            } catch (IOException e) {
                e.printStackTrace();
            } finally {
                try {
                    br.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
                pw.close();
            }
        }
    }