Java剔除富文本的HTML标签并保留换行

 /**
     * 剔除html标签，并保留换行
     * @param html
     * @return
     */
    public static String removeHtmlTags(String html) {
        Pattern pattern = Pattern.compile(HtmlUtil.RE_HTML_MARK);
        Matcher matcher = pattern.matcher(html);
        StringBuffer result = new StringBuffer();
        // 使用循环逐个匹配替换标签
        while (matcher.find()) {
            String matchedTag = matcher.group();
            if (matchedTag.startsWith("</p>") || matchedTag.startsWith("<br>") || matchedTag.startsWith("</li>")) {
                matcher.appendReplacement(result, System.lineSeparator());
            } else {
                matcher.appendReplacement(result, "");
            }
        }
        matcher.appendTail(result);
        // 去掉首尾空白,并剔除连续换行符
        return removeMultipleNewlines(result.toString().trim());
    }

    /**
     * 剔除连续换行符
     * @param content
     * @return
     */
    public static String removeMultipleNewlines(String content) {
        // 使用正则表达式剔除连续多个换行符
        Pattern newLines = Pattern.compile("(\\r?\\n){2,}");
        Matcher matcher = newLines.matcher(content);
        return matcher.replaceAll(System.lineSeparator());
    }