文本标签过滤

<pre name="code" class="java">public class HtmlCleaner {
  private static Pattern p_script;
  private static java.util.regex.Matcher m_script;
  private static Pattern p_style;
  private static java.util.regex.Matcher m_style;
  private static Pattern p_html;
  private static java.util.regex.Matcher m_html;
  
  private static  Pattern p_a;
  private static java.util.regex.Matcher m_a;
  
  private static 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>
  // }
  private static 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>
  // }
  private static String regEx_a = "<\\s*a\\s+([^>]*)\\s*>"; //过滤a的正则表达式
  
  private static String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式

  /**
   * Html2Text is used to clean the HTML tags in a String which is very useful
   * in the article component and so on
   * 
   * @param inputString
   *            the String which is needed to clean
   * @return String,the result of cleaning operation
   */
  public static String filterHtmlToA(String inputString){
	    String htmlStr = inputString; // 含html标签的字符串      
        String textStr = "";      
	    try {      
	      p_a = Pattern.compile(regEx_a,Pattern.CASE_INSENSITIVE);
	      m_a = p_a.matcher(htmlStr);
	      htmlStr = m_a.replaceAll(""); //过滤a标签
          textStr = htmlStr;
	     }catch (Exception e) {
	         System.err.println("Html2Text: " + e.getMessage());
		}
	    return textStr;// 返回文本字符串
  }
  
  public static String filterHtmlTag(String inputString) {
          String htmlStr = inputString; // 含html标签的字符串
          String textStr = "";

          try {
                  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

                  textStr = htmlStr;

          } catch (Exception e) {
                  System.err.println("Html2Text: " + e.getMessage());
          }

          return textStr;// 返回文本字符串
  }