java 去标签获取纯文本_java过滤html标签获取纯文本信息的实例

package com.lyt.base.util;

import java.util.regex.Pattern;

public class FilterHtmlUtil {

public static String Html2Text(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_style;

java.util.regex.Matcher m_style;

java.util.regex.Pattern p_html;

java.util.regex.Matcher m_html;

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

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

textStr = htmlStr;

}catch(Exception e){

e.printStackTrace();

}

return textStr;//返回文本字符串

}

}