将html标签 程序去除,将内容里的html标签去掉的类

网上找了个将内容里的html标签去掉的类

package com.foresee.jk;

import java.util.regex.Pattern;

public class HtmlText {

public static String html2Text(String inputString) {

String htmlStr = inputString;

String textStr = "";

java.util.regex.Pattern p_script;

java.util.regex.Matcher m_script;

java.util.regex.Pattern p_style;

java.util.regex.Matcher m_style;

java.util.regex.Pattern p_html;

java.util.regex.Matcher m_html;

java.util.regex.Pattern p_html1;

java.util.regex.Matcher m_html1;

try {

String regEx_script = "]*?>[\\s\\S]*?"; // 定义script的正则表达式{或

// }

String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定义style的正则表达式{或

// }

String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式

String regEx_html1 = "<[^>]+";

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_html1 = Pattern.compile(regEx_html1, Pattern.CASE_INSENSITIVE);

m_html1 = p_html1.matcher(htmlStr);

htmlStr = m_html1.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

}

public static void main(String[] arg) {

String strtext = "

测 vvv";

System.out.println(html2Text(strtext));

}

}