//定義script的正則表達式
private static String regEx_script="<script[^>]*?>[\\s\\S]*?<\\/script>";
//定義style的正則表達式
private static String regEx_style="<style[^>]*?>[\\s\\S]*?<\\/style>";
//定義HTML標簽的正則表達式
private static String regEx_html="<[^>]+>";
//定義空格回車換行符
private static String regEx_space = "\\s*|\t|\r|\n";//定義空格回車換行符
/**
* 驗證名稱中是否含有標簽，並返回字符串
* @param htmlStr
* @return
*/
public static String delHTMLTag(String htmlStr) {
Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
Matcher m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 過濾script標簽
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
Matcher m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 過濾style標簽
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 過濾html標簽
Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
Matcher m_space = p_space.matcher(htmlStr);
htmlStr = m_space.replaceAll(""); // 過濾空格回車標簽
return htmlStr.trim(); // 返回文本字符串
}
/**
* 獲取標簽中的字符串
* @param htmlStr
* @return
*/
public static String getTextFromHtml(String htmlStr){
htmlStr = delHTMLTag(htmlStr);
htmlStr = htmlStr.replaceAll(" ","");
//htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
return htmlStr;
}
public static void main(String[] args) {
String str = "<html>alert(2)</html>";
System.out.println(getTextFromHtml(str));
}