收藏 分销(赏)

实现java读取网页内容并下载网页中出现的图片.doc

上传人:xrp****65 文档编号:7699897 上传时间:2025-01-12 格式:DOC 页数:3 大小:31KB 下载积分:10 金币
下载 相关 举报
实现java读取网页内容并下载网页中出现的图片.doc_第1页
第1页 / 共3页
实现java读取网页内容并下载网页中出现的图片.doc_第2页
第2页 / 共3页


点击查看更多>>
资源描述
http: package com; 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; public class GetContentPicture { 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 = "./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(); } } 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; } 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.getHtmlCode(url); System.out.println(content); Pattern pattern = Ppile(searchImgReg); Matcher matcher = pattern.matcher(content); while (matcher.find()) { System.out.println(matcher.group(3)); this.getHtmlPicture(url+matcher.group(3)); } pattern = Ppile(searchImgReg2); matcher = pattern.matcher(content); while (matcher.find()) { System.out.println(matcher.group(3)); this.getHtmlPicture(matcher.group(3)); } // searchImgReg = // "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")"; } public static void main(String[] args) throws IOException { String url = " GetContentPicture gcp = new GetContentPicture(); gcp.get(url); } }
展开阅读全文

开通  VIP会员、SVIP会员  优惠大
下载10份以上建议开通VIP会员
下载20份以上建议开通SVIP会员


开通VIP      成为共赢上传

当前位置:首页 > 教育专区 > 其他

移动网页_全站_页脚广告1

关于我们      便捷服务       自信AI       AI导航        抽奖活动

©2010-2026 宁波自信网络信息技术有限公司  版权所有

客服电话:0574-28810668  投诉电话:18658249818

gongan.png浙公网安备33021202000488号   

icp.png浙ICP备2021020529号-1  |  浙B2-20240490  

关注我们 :微信公众号    抖音    微博    LOFTER 

客服