java的URL类读取网页1

阳光穿透心脏的1/2处 2022-02-02 06:31 207阅读 0赞

package com.javabase.sss;
    
    import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileNotFoundException;
    import java.io.FileOutputStream;
    import java.io.FileWriter;
    import java.io.IOException;
    import java.io.InputStreamReader;
    import java.io.OutputStreamWriter;
    
    import java.net.MalformedURLException;
    import java.net.URL;
    
    public class Kpp {
    
    	/**
    	 * 
    	 * 
    	 * 
    	 * @param urlstr 网页地址
    	 * @param fileName 需要保存的文件名全路径
    	 * @throws IOException
    	 * void
    	 */
    	public static void readHttp(String urlstr,String fileName) throws IOException{
    
    		//装饰器 缓存读取
    		BufferedReader bReader = null;
    		File f = new File(fileName);
    		if(!f.exists()) {
    			try {
    				f.createNewFile();
    			} catch (IOException e) {
    				e.printStackTrace();
    			}
    		}
    		//文件输出流
    		FileOutputStream fout = new FileOutputStream(f);
    		//写入流
    		OutputStreamWriter myWriter = new OutputStreamWriter(fout);
    		//输入流
    		InputStreamReader myReader = null;
    		StringBuffer sbuf =new StringBuffer();
    		//URL对象
    		URL url = new URL(urlstr);
    						//输入流
    			myReader = new InputStreamReader(url.openStream(),"utf-8");
    			//把输入流放到装饰器 缓存读取
    			bReader = new BufferedReader(myReader);
    			String s = null;
    			//按行读取网页
    			while((s = bReader.readLine()) != null ) {
    			
    				sbuf.append(s);
    			}
    			//写入到文件
    			myWriter.write(sbuf.toString());
    			
    			System.out.println("完成");
    
    			bReader.close();
    			myReader.close();
    			myWriter.close();
    
    	}
    
    	public static void main(String[] args){
    		String url = "https://www.hao123.com/index.html";
    		String fileName = "C:/333.txt";
    		try {
    			readHttp(url,fileName);
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    		
    	}
    
    }