java的URL类读取网页2

逃离我推掉我的手 2022-02-01 08:21 219阅读 0赞

package com.javabase.p1;
    
    import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileNotFoundException;
    import java.io.FileOutputStream;
    import java.io.FileWriter;
    import java.io.IOException;
    import java.io.InputStream;
    import java.io.InputStreamReader;
    import java.io.OutputStream;
    import java.io.OutputStreamWriter;
    
    import java.net.MalformedURLException;
    import java.net.URL;
    
    import javax.net.ssl.HttpsURLConnection;
    
    public class Test_url {
    
    	/**
    	 * 按utf-8编码格式读取
    	 * 
    	 * @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();
    
    	}
    
    	
    	
    	/**
    	 * 按utf-8编码格式读取
    	 * @param http_str 网址
    	 * @param path     保存的磁盘位置 全路径
    	 * @throws IOException
    	 */
    	public static void read_http1(String http_str, String path) throws IOException {
    
    		URL url = new URL(http_str);
    		// 获取主机
    		String host = url.getHost();
    		// 获取端口
    		int port = url.getPort();
    		// 获取协议
    		String pStr = url.getProtocol();
    
    		System.out.println(host);
    		System.out.println(port);
    		System.out.println(pStr);
    
    		// 打开连接 连接参数设置
    		HttpsURLConnection conn = (HttpsURLConnection) url.openConnection();
    		// 获取网页内容
    		InputStream in = conn.getInputStream();
    		// 新建读取网页流对象
    		InputStreamReader inReader = new InputStreamReader(in, "utf-8");
    		// 放入缓存读取
    		BufferedReader bMyReader = new BufferedReader(inReader);
    
    		StringBuilder sbuf = new StringBuilder();
    		String s = null;
    		// 按行读取网页内容
    		while ((s = bMyReader.readLine()) != null) {
    			sbuf.append(s);
    
    		}
    
    		// 文件流
    		FileOutputStream f_out_s = new FileOutputStream(path);
    		// 写入到文件流
    		OutputStreamWriter myWriter = new OutputStreamWriter(f_out_s);
    		myWriter.write(sbuf.toString());
    		// 关闭各种资源
    		myWriter.close();
    		f_out_s.close();
    
    		bMyReader.close();
    		inReader.close();
    		in.close();
    		conn.disconnect();
    
    		System.out.println("读取网页完成！");
    
    	}
    
    	public static void main(String[] args) {
    		String url = "https://www.hao123.com/index.html";
    		String path1 = "C:/3331111.txt";
    
    		String path2 = "C:/1223100.txt";
    		//两种方式读取网页内容
    		try {
    			read_http1(url,path1);
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    
    		
    		//两种方式读取网页内容
    		try {
    			readHttp(url, path2);
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    
    	}
    
    }