java-实现网页代码的爬取

爬取一个网页的内容,当然相对路径以及样式都复制不过来,只能复制这个文件的内容。

先将所有异常使用Throws抛出的话

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;

public class Src {
    
    

	public static void main(String[] args) throws Exception {
    
     //抛出异常
		URL url = new URL("http://www.whxy.edu.cn/mdxw/xxxw.htm"); //访问的url地址,这个地址应该是一个html页面
		InputStream is = url.openStream(); 
		BufferedInputStream bis = new BufferedInputStream(is); //用包装流来处理,加速
		BufferedOutputStream bos = new BufferedOutputStream(new FileOutputStream( new File("d:\\a.html"))); //用包装流
		byte [] b = new byte[1024]; //用byte []数组来一次读取1024个字节,这样速度就会快一点
		int len = bis.read(b);
		while( len != -1) {
    
     //-1时,表示读到了最后
			bos.write(b);
			len = bis.read(b);
		}
		//最后关流,和创建的方式反着关
		bos.close();
		bis.close();
	}
}

//下面是将所有的异常try-catch

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;

public class Src {
    
    

	public static void main(String[] args)  {
    
    
		URL url = null;
		try {
    
    
			url = new URL("http://www.whxy.edu.cn/mdxw/xxxw.htm");
		} catch (MalformedURLException e) {
    
    
			e.printStackTrace();
		}
		InputStream is = null;
		try {
    
    
			is = url.openStream();
		} catch (IOException e) {
    
    
			e.printStackTrace();
		}
		BufferedInputStream bis = new BufferedInputStream(is);
		BufferedOutputStream bos = null;
		try {
    
    
			bos = new BufferedOutputStream(new FileOutputStream( new File("d:\\a.html")));
		} catch (FileNotFoundException e) {
    
    
			e.printStackTrace();
		}
		byte [] b = new byte[1024];
		int len = -1;
		try {
    
    
			len = bis.read(b);
			while( len != -1) {
    
    
				bos.write(b);
				len = bis.read(b);
			}
		} catch (IOException e) {
    
    
			e.printStackTrace();
		}finally {
    
    
			try {
    
    
				if( bos != null) {
    
    
					bos.close();
				}
			} catch (IOException e) {
    
    
				e.printStackTrace();
			}
			try {
    
    
				if( bis != null) {
    
    
					bis.close();
				}
			} catch (IOException e) {
    
    
				e.printStackTrace();
			}
		}	
	}
}

后期还会加上正则表达式那么就可以爬取我们想要的信息了。

猜你喜欢

转载自blog.csdn.net/toomemetoo/article/details/112846779