java网络编程url实现扒网站上的图片

java网络编程url实现扒网站上的图片

小型的java爬虫

package com.URL;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.net.URISyntaxException;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class UrlTest {
	public static void main(String[] args) {
		String url = "http://www.qq.com";
		try {
			URL u = new URL(url);
			URLConnection uc = u.openConnection();
			/** 获取html源文件 保存到文件 **/
			InputStream in =uc.getInputStream();
			InputStreamReader r = new InputStreamReader(in,"utf-8");
			BufferedReader br = new BufferedReader(r);
			String s = "";
			StringBuffer sum = new StringBuffer();
			while((s = br.readLine())!=null){
				sum.append(s);
				sum.append("\n");
			}
			System.out.println(sum);
			//获取img标签的src属性
			Pattern pat = Pattern.compile("<img[^>]+src\\s*=\\s*['\"]([^'\"]+)['\"][^>]*>");
			Matcher m = pat.matcher(sum.toString());
			while (m.find()) {
				System.out.println(m.group(1));
				writeimg(m.group(1));
				
			}

		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	public static void writeimg(String urlimg){
		try{
			//获取传入网络图片名
			File f = new File(urlimg);
			String imgname = f.getName();//获取网络图片的名称
			
			File f1 = new File("V:/java练习/img/"+imgname);//图片保存到本机的路径
			if(!f1.exists()){
				f1.createNewFile();
			}
			OutputStream out = new FileOutputStream(f1);
			//
			URL u = new URL(urlimg);
			URLConnection uc = u.openConnection();
			InputStream in = uc.getInputStream();
			byte[] b = new byte[1024];
			int len = 0;
			while((len = in.read(b))!=-1){
				out.write(b,0,len);
			}
			in.close();
			out.flush();
			out.close();
			
		}catch(Exception e){
			e.printStackTrace();
		}
	}
}