HTML中提取文字内容，去掉标签样式等

ゞ浴缸里的玫瑰 2023-05-28 11:27 8阅读 0赞

## html代码如下 ##

<h1>登鹳雀楼</h1>
            <div class="poem-detail-header-info">
                                                    <a class="poem-detail-header-author" href="/s?wd=王之涣">
                            <span class="poem-info-gray">【作者】</span>王之涣
                        </a>
                                                            <span class="poem-detail-header-author">
                        <span class="poem-info-gray">【朝代】</span>唐
                    </span>
                                        <div class="body-means-change">
                    译文对照
                </div>
                        </div>
            <div class="poem-detail-separator"></div>
                                    <div class="poem-detail-item-content">
                                    <p class="poem-detail-main-text" id="body_p">
                        <span id="body_1_0" data="means_1_0"><em><span class='body-zhushi-span' data='"\u592a\u9633\u3002"'>白日</span><span class='body-zhushi-span' data='"\u4f9d\u508d\u3002"'>依</span>山尽，</em></span><span id="body_1_1" data="means_1_1">黄河入海流。</span>                </p>
                    <p id="means_p" class="poem-detail-main-text body-means-p">
                        <span id="means_1_0" data="body_1_0">夕阳依傍着西山慢慢地沉没，</span><span id="means_1_1" data="body_1_1">滔滔黄河朝着东海汹涌奔流。</span>                </p>
                                    <p class="poem-detail-main-text" id="body_p">
                        <span id="body_2_0" data="means_2_0"><span class='body-zhushi-span' data='"\u60f3\u8981\u5f97\u5230\u67d0\u79cd\u4e1c\u897f\u6216\u8fbe\u5230\u67d0\u79cd\u76ee\u7684\u7684\u613f\u671b\uff0c\u4f46\u4e5f\u6709\u5e0c\u671b\u3001\u60f3\u8981\u7684\u610f\u601d\u3002"'>欲</span><span class='body-zhushi-span' data='"\u5c3d\uff0c\u4f7f\u8fbe\u5230\u6781\u70b9\u3002"'>穷</span>千里目，</span><span id="body_2_1" data="means_2_1"><span class='body-zhushi-span' data='"\u66ff\u3001\u6362\u3002\uff08\u4e0d\u662f\u901a\u5e38\u7406\u89e3\u7684\u201c\u518d\u201d\u7684\u610f\u601d\uff09"'>更</span>上一层楼。</span>                </p>
                    <p id="means_p" class="poem-detail-main-text body-means-p">

## 提取效果 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xlaXN1cmVfbGlmZQ_size_16_color_FFFFFF_t_70]

## java代码 ##

private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式
        private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式
        private static final String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
    
        /**
         * @param htmlStr
         * @return 删除Html标签
         */
        public static String formatHTMLTag(String htmlStr) {
            Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
            Matcher m_script = p_script.matcher(htmlStr);
            htmlStr = m_script.replaceAll(""); // 过滤script标签
    
            Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
            Matcher m_style = p_style.matcher(htmlStr);
            htmlStr = m_style.replaceAll(""); // 过滤style标签
    
            htmlStr = htmlStr.replaceAll("<br\\/>", "\n");// 换行替换
            htmlStr = htmlStr.replaceAll("</p>", "\n");// 段落替换
    
            Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
            Matcher m_html = p_html.matcher(htmlStr);
            htmlStr = m_html.replaceAll(""); // 过滤html标签
    
            htmlStr = htmlStr.replaceAll(" ", "");
            htmlStr = htmlStr.replaceAll("&", "&");
    
    
            Pattern p = Pattern.compile("(\r?\n(\\s*\r?\n)+)");//多个换行替换成一个
            Matcher m = p.matcher(htmlStr);
            htmlStr = m.replaceAll("\r\n");
    
            return htmlStr; // 返回文本字符串
        }

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xlaXN1cmVfbGlmZQ_size_16_color_FFFFFF_t_70]: /images/20230528/129c4f73aa8e4414bd3ed84226132e06.png