java去除html tags
public static String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; public static String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>";public static String regEx_html = "<[^>]+>";public static Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE); public static Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE); public static Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);public static String getOptimizedData(String inputString) { if (inputString == null) { return inputString; } //stripping script tags whether the tag contains "\n" or "\r" or not. Matcher m_script = p_script.matcher(inputString); String htmlStr = m_script.replaceAll(""); //stripping style tags whether the tag contains "\n" or "\r" or not. Matcher m_style = p_style.matcher(htmlStr); htmlStr = m_style.replaceAll(""); //stripping html tags but continue to have the "\n" and "\r" in right place. Matcher m_html = p_html.matcher(htmlStr); htmlStr = m_html.replaceAll(""); return htmlStr; }
页:
[1]