使用正则进行HTML页面属性的替换

　　使用正则表达式拼接富文本框

package com.goboosoft.common.utils;

import org.apache.commons.lang3.StringUtils;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

/**

 * Description:

 *

 * @author cy

 * @date 2019年04月01日 17:35

 * version 1.0

 */

public class HtmlUtils {

    /**

     * 替换指定标签的属性和值

     * @param str 需要处理的字符串

     * @param tag 标签名称

     * @param tagAttrib 要替换的标签属性值

     * @param startTag 新标签开始标记

     * @param endTag  新标签结束标记

     * @return

     * @author huweijun

     * @date 2016年7月13日 下午7:15:32

     */

    public static String replaceHtmlTag(String str, String tag, String tagAttrib, String startTag, String endTag) {

        String regxpForTag = "<\\s*" + tag + "\\s+([^>]*)\\s*" ;

        String regxpForTagAttrib = tagAttrib + "=\\s*\"([^\"]+)\"" ;

        Pattern patternForTag = Pattern.compile (regxpForTag,Pattern. CASE_INSENSITIVE );

        Pattern patternForAttrib = Pattern.compile (regxpForTagAttrib,Pattern. CASE_INSENSITIVE );

        Matcher matcherForTag = patternForTag.matcher(str);

        StringBuffer sb = new StringBuffer();

        boolean result = matcherForTag.find();

        while (result) {

            StringBuffer sbreplace = new StringBuffer( "<"+tag+" ");

            Matcher matcherForAttrib = patternForAttrib.matcher(matcherForTag.group());

            if (matcherForAttrib.find()) {

                String attributeStr = matcherForAttrib.group();

                matcherForAttrib.appendReplacement(sbreplace, startTag + attributeStr + endTag);

            }

            matcherForAttrib.appendTail(sbreplace);

            matcherForTag.appendReplacement(sb, sbreplace.toString());

            result = matcherForTag.find();

        }

        matcherForTag.appendTail(sb);

        return sb.toString();

    }

    public static String replaceImgSrc(String content,String domain){

        if(StringUtils.isBlank(content)){

            return null;

        }

        String buf = "src=\"" + domain;

        String s = replaceHtmlTag(content, "img", "src", buf, "\"");

        return s;

    }

    public static void main(String[] args) {

        StringBuffer content = new StringBuffer();

        content.append("<ul class=\"imgBox\"><li><img id=\"160424\" src=\"uploads/allimg/160424/1-160424120T1-50.jpg\" class=\"src_class\"></li>");

        content.append("<li><img id=\"150628\" src=\"uploads/allimg/150628/1-15062Q12247.jpg\" class=\"src_class\"></li></ul>");

        System.out.println("原始字符串为:"+content.toString());

        String s = replaceImgSrc(content.toString(), "http://files.goboosoft.com/zwjm/");

        System.out.println("替换后为:"+s);

    }

}

/**

     * 去除图片中的domain

     * @param htmlStr html字符串

     * @return String

     */

    private static String deleteImgSrcDomain(String htmlStr) {

        List<String> pics = new ArrayList<String>();

        String img = "";

        String repimg = "";

        Pattern p_image;

        Matcher m_image;

        String regEx_img = "<img.*src\\s*=\\s*(.*?)[^>]*?>";

        p_image = Pattern.compile(regEx_img, Pattern.CASE_INSENSITIVE);

        m_image = p_image.matcher(htmlStr);

        while (m_image.find()) {

            // 得到<img />数据

            img = m_image.group();

            // 匹配<img>中的src数据

            Matcher m = Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);

            while (m.find()) {

                String s = m.group();

                pics.add(s);

                // 处理图片信息

                String substring = s.substring(s.lastIndexOf("/") + , s.length());

                repimg = img.replace(s, substring);

                htmlStr = htmlStr.replace(img, repimg);

                img = repimg;

            }

        }

        return htmlStr;

    }