java读取网页信息

 

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ReadWebPage {
 public static void main(String[] args) {
  try {
   URL url = new URL("http://www.3158.com/view/dome/lxwm.shtml");
   HttpURLConnection connection = (HttpURLConnection) url.openConnection();
   InputStream is = connection.getInputStream();
   BufferedReader br = new BufferedReader(new InputStreamReader(is));
   String line = "";
   while ((line = br.readLine()) != null) {
    parse(line);
   }
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  } catch (IOException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
 }

 private static void parse(String line) {
  // 获取邮箱
  Pattern p = Pattern.compile("[//w[.-]]+@[//w[.-]]+//.[//w]+");
  // 获取手机号码
  // Pattern p = Pattern.compile("1[3,5]//d{9}");
  Matcher m = p.matcher(line);
  while (m.find()) {
   System.out.println(m.group());
  }
 }
}