Java中正則表達(dá)式去除html標(biāo)簽

private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定義script的正則表達(dá)式
  private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定義style的正則表達(dá)式
  private static final String regEx_html = "<[^>]+>"; // 定義HTML標(biāo)簽的正則表達(dá)式
  private static final String regEx_space = "\\s*|\t|\r|\n";// 定義空格回車(chē)換行符
  private static final String regEx_w = "<w[^>]*?>[\\s\\S]*?<\\/w[^>]*?>";//定義所有w標(biāo)簽
/**
   * @param htmlStr
   * @return 刪除Html標(biāo)簽
   * @author LongJin
   */
  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(""); // 過(guò)濾script標(biāo)簽
    Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
    Matcher m_script = p_script.matcher(htmlStr);
    htmlStr = m_script.replaceAll(""); // 過(guò)濾script標(biāo)簽
    Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
    Matcher m_style = p_style.matcher(htmlStr);
    htmlStr = m_style.replaceAll(""); // 過(guò)濾style標(biāo)簽
    Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
    Matcher m_html = p_html.matcher(htmlStr);
    htmlStr = m_html.replaceAll(""); // 過(guò)濾html標(biāo)簽
    Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
    Matcher m_space = p_space.matcher(htmlStr);
    htmlStr = m_space.replaceAll(""); // 過(guò)濾空格回車(chē)標(biāo)簽
    htmlStr = htmlStr.replaceAll(" ", ""); //過(guò)濾 
    return htmlStr.trim(); // 返回文本字符串
  }