Java删除字符串中HTML标签

  • 时间:
  • 浏览:
  • 来源:互联网

Java删除字符串中HTML标签

		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
	    private static final String regEx_space = "\\s*|\t|\r|\n";// 定义空格回车换行符
	    private static final String regEx_w = "<w[^>]*?>[\\s\\S]*?<\\/w[^>]*?>";//定义所有w标签
	 
	    /**
	     * @param htmlStr
	     * @return 删除Html标签
	     * @author Abdulaziz
	     */
	    public static String delHTMLTag(String htmlStr) {
	        Pattern p_w = Pattern.compile(regEx_w, Pattern.CASE_INSENSITIVE);
	        Matcher m_w = p_w.matcher(htmlStr);
	        htmlStr = m_w.replaceAll(""); // 过滤script标签
	 
	 
	        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
	 
	 
	        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
	 
	 
	        Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
	        Matcher m_space = p_space.matcher(htmlStr);
	        htmlStr = m_space.replaceAll(""); // 过滤空格回车标签
	 
	 
	        htmlStr = htmlStr.replaceAll(" ", ""); //过滤 
	        return htmlStr.trim(); // 返回文本字符串
	    }

本文链接http://www.dzjqx.cn/news/show-617274.html