爬網頁獲取電話號碼

明天補充

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

public class URLTest {

    private URLConnection connection = null;
    
    public String getDoucument(String url) throws IOException {
        
        URL newUrl = new URL(url);
        connection = newUrl.openConnection();
        InputStream is = connection.getInputStream();
        InputStreamReader isr = new InputStreamReader(is);
        BufferedReader br = new BufferedReader(isr);
        
        String line = "";
        StringBuffer sb = new StringBuffer();
        
        while( (line =  br.readLine()) != null) {
            sb.append(line +"\n");
        }
        
        return sb.toString();
        
    }
    
    public String MyFilter( String string ) {//內容過濾器-獲取網頁上的電話，沒有去重
        
        String regex = "18[\\d]{9}";
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(string);
        
        String result = "";
        while(matcher.find()) {
            result += matcher.group()+"\n";
        }
        
        return result;
    }
    
    public static void main(String[] args) throws IOException {
        
        URLTest test = new URLTest();
        String page = test.getDoucument("https://power.baidu.com/question/1511959129473915060.html?qbl=relate_question_1");
        String result = test.MyFilter(page);
//        System.out.println(page);
        
        if ( result != null ) {
            System.out.println("從該網頁上找到的號碼：\n"+result);
        }
        else {
            System.out.println("該網頁上沒有電話號碼");
        }
        
    }
}

 

程序效果