java获取网网页中出现的图片及判断网页代码中是否包含有效图片.docVIP

package com.hopsun.util; import java.io.BufferedInputStream; import java.io.BufferedReader; import java.io.File; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.IOException; import java.io.InputStreamReader; import .MalformedURLException; import .URL; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * 获取网页中的图片 * 2011-10-27 * @author 刘广 * */ public class GetContentPicture { /** * 保存获取的图片 * @return void * @date Oct 27, 2011 * @user 刘广 */ public void getHtmlPicture(String httpUrl) { URL url; BufferedInputStream in; FileOutputStream file; try { System.out.println(取网络图片); String fileName = httpUrl.substring(httpUrl.lastIndexOf(/)); String filePath = d:/pic/; url = new URL(httpUrl); in = new BufferedInputStream(url.openStream()); file = new FileOutputStream(new File(filePath+fileName)); int t; while ((t = in.read()) != -1) { file.write(t); } file.close(); in.close(); System.out.println(图片获取成功); } catch (MalformedURLException e) { e.printStackTrace(); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } /** * 获得网页代码 * @return String * @date Oct 27, 2011 * @user 刘广 */ public String getHtmlCode(String httpUrl) throws IOException { String content =; URL uu = new URL(httpUrl); // 创建URL类对象 BufferedReader ii = new BufferedReader(new InputStreamReader(uu.openStream())); // //使用openStream得到一输入流并由此构造一个BufferedReader对象 String input; while ((input = ii.readLine()) != null) { // 建立读取循环，并判断是否有读取值 content += input; } ii.close(); return content; } /** * 通过正则匹配获取图片 * @return void * @date Oct 27, 2011 * @user 刘广 */ public void get(String url) throws IOException { String searchImgReg = (?x)(src|SRC|background|BACKGROUND)=(|\)/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))(|\); String searchImgReg2 = (?x)(src|SRC|background|BACKGROUND)=(|\)(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))(|\); String content = this.ge