通过正则过滤html标签

public static String delHtml(String inputString) { String htmlStr = inputString; // 含html标签的字符串 String textStr = ""; java.util.regex.Pattern p_script; java.util.regex.Matcher m_script; java.util.regex.Pattern p_html; java.util.regex.Matcher m_html; try { String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式 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> 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_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 } 本文来自优快云博客，转载请标明出处：http://blog.youkuaiyun.com/long0428/archive/2008/04/02/2243573.aspx