import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
     * 功能：删除Html标签
     * 时间：2017-2-13 下午7:04:08 
     * @param htmlStr
     * @return
     */
    public static String delHTMLTag(String htmlStr) {  
        String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式  
        String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式  
        String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式  
        String regEx_space = "\\s*|\t|\r|\n";//定义空格回车换行符
        String regEx_chinese = "[\u3002\uff1b\uff0c\uff1a\u201c\u201d\uff08\uff09\u3001\uff1f\u300a\u300b]*?";//中文标点
        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  
        
        Pattern p_chinese = Pattern.compile(regEx_chinese,Pattern.CASE_INSENSITIVE);  
        Matcher m_chinese = p_chinese.matcher(htmlStr);  
        htmlStr = m_chinese.replaceAll(""); // 过滤中文标点标签  
        return htmlStr.trim(); // 返回文本字符串  
    }