正则表达式抓取网页面上所有图片

最新推荐文章于 2025-12-21 19:59:20 发布

最新推荐文章于 2025-12-21 19:59:20 发布 · 195 阅读

文章标签：

#正则表达式 #Java #.net

Regular Exp 专栏收录该内容

2 篇文章

订阅专栏

本文介绍了一个简单的Java程序，该程序能从指定网址抓取HTML页面，并通过正则表达式匹配来提取页面中的图片资源链接。

package com.roadway.test;

import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class TeskSRC {
 public String getHtmlCode(String httpUrl) {
 String htmlCode = "";
 try {
 InputStream in;
 URL url = new java.net.URL(httpUrl);
 HttpURLConnection connection = (HttpURLConnection) url
 .openConnection();
 connection = (HttpURLConnection) url.openConnection();
 connection.setRequestProperty("User-Agent", "Mozilla/4.0");
 connection.connect();
 in = connection.getInputStream();
 byte[] buffer = new byte[512];
 int length = -1;
 while((length = in.read(buffer,0,512)) != -1){
 htmlCode += new String(buffer,0,length);
 }
 } catch (Exception e) {
 }
 if(htmlCode == null){
 return "";
 }
 return htmlCode;
 }
 public static void main(String[] args){
 TeskSRC ts = new TeskSRC();
 String searchImgReg = "(?x)(src|SRC|background|BACKGROUND)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";
 String content = ts.getHtmlCode("http://www.163.com");
 Pattern pattern = Pattern.compile(searchImgReg);
 Matcher matcher = pattern.matcher(content);
 while(matcher.find()){
 System.out.println(matcher.group(3));
 }
 //searchImgReg = "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";
 }
}