网页去除html元素

*、去除html元素

 public static String splitAndFilterString(String input, int length) {   
        if (input == null || input.trim().equals("")) {   
            return "";   
        }   
        // 去掉所有html元素,   
		//--------------------
		String htmlStr = input; // 含html标签的字符串
		String str = "";
		java.util.regex.Pattern p_script;
		java.util.regex.Matcher m_script;
		java.util.regex.Pattern p_style;
		java.util.regex.Matcher m_style;
		java.util.regex.Pattern p_html;
		java.util.regex.Matcher m_html;
		java.util.regex.Pattern p_ba;
		java.util.regex.Matcher m_ba;
		try {
			String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*? \\/[\\s]*?script[\\s]*?>"; // 定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script>
			// }
			String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*? \\/[\\s]*?style[\\s]*?>"; // 定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style>
			// }
			String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
			String patternStr = "\\s+";
			p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
			m_script = p_script.matcher(htmlStr);
			htmlStr = m_script.replaceAll(""); // 过滤script标签

			p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
			m_style = p_style.matcher(htmlStr);
			htmlStr = m_style.replaceAll(""); // 过滤style标签
			p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
			m_html = p_html.matcher(htmlStr);
			htmlStr = m_html.replaceAll(""); // 过滤html标签
			p_ba = Pattern.compile(patternStr, Pattern.CASE_INSENSITIVE);
			m_ba = p_ba.matcher(htmlStr);
			htmlStr = m_ba.replaceAll(" "); // 过滤空格
			str = htmlStr;
		} catch (Exception e) {
			e.printStackTrace();
		}
		
        int len = str.length();   
        if (len <= length) {  
		    str = str.replace("\'", "\''");
           return str;   
      } else {   
            str = str.substring(0, length);   
            str += "...";  
			str = str.replace("\'", "\''");
        }   
        return str;   
   }  

    input：带有html元素的字段

 length:目标长度