我靠，上班eclipse看糗事百科

最新推荐文章于 2025-09-10 15:47:18 发布

转载最新推荐文章于 2025-09-10 15:47:18 发布 · 63 阅读

文章标签：

#开发工具 #java

本文展示了一个简单的Java程序示例，该程序用于从指定网页抓取内容。通过使用URL、BufferedReader等类，程序能够打开一个网络连接并读取网页上的文本数据，同时跳过了HTML标签。

package test; 


import java.io.BufferedReader; 
import java.io.InputStreamReader; 
import java.net.URL; 
import java.util.Scanner; 


public class  NewClass{ 


/** 
* @param args 
*/ 
public static void main(String[] args) { 
StringBuffer sb = new StringBuffer(); 
System.out.println("Please input the page:"); 
while(true) { 
Scanner sc = new Scanner(System.in); 
sb = getUrl(sc.nextInt()); 
System.out.println(sb); 
} 
} 

private static StringBuffer getUrl(int page) { 
StringBuffer sb = new StringBuffer(); 
try { 
URL url = new URL("http://www.qiushibaike.com/month/page/"+page+"?s=4595690&slow"); 
InputStreamReader in = new InputStreamReader(url.openStream(),"UTF-8"); 
BufferedReader br = new BufferedReader(in); 
String line; 
while((line = br.readLine())!=null) { 
if(line!=null && !line.isEmpty() &&line.charAt(0) == '<'){ 
continue; 
} 
sb.append("\n"+changeLine(line)); 
} 
} catch (Exception e) { 
// TODO Auto-generated catch block 
e.printStackTrace(); 
} 
return sb; 
} 

private static String changeLine(String line) { 
StringBuffer sb = new StringBuffer(line); 
for(int i = 0;i < line.length()/70 ; i++) { 
sb.insert((i+1)*70, "\n"); 
} 
return sb.toString(); 
} 
}