java正则表达式删除_java正则表达式删除html标签

package com.app.util;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

/**

*     @author Wonghoman

*/

public class HTMLSpirit {

// 定义script的正则表达式{或

private static final String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>";

// 定义style的正则表达式{或

private static final String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>";

// 定义HTML标签的正则表达式

private static final String regEx_html = "<[^>]+>";

// 定义一些特殊字符的正则表达式 如：

private static final String regEx_special = "\\&[a-zA-Z]{1,10};";

/**

* 删除Html标签

*

* @param inputString

* @return

*/

public static String removeHtmlTag(String inputString) {

if (inputString == null)

return null;

String htmlStr = inputString; // 含html标签的字符串

String textStr = "";

Pattern p_script;

Matcher m_script;

Pattern p_style;

Matcher m_style;

Pattern p_html;

Matcher m_html;

Pattern p_special;

Matcher m_special;

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

p_special = Pattern

.compile(regEx_special, Pattern.CASE_INSENSITIVE);

m_special = p_special.matcher(htmlStr);

htmlStr = m_special.replaceAll(""); // 过滤特殊标签

textStr = htmlStr;

} catch (Exception e) {

e.printStackTrace();

}

return textStr;// 返回文本字符串

}

}