java過濾html標(biāo)簽獲取純文本信息的實(shí)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標(biāo)簽的字符串
  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]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; //定義script的正則表達(dá)式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
     String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //定義style的正則表達(dá)式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
     String regEx_html = "<[^>]+>"; //定義HTML標(biāo)簽的正則表達(dá)式
     p_script = Pattern.compile(regEx_script,Pattern.CASE_INSENSITIVE);
     m_script = p_script.matcher(htmlStr);
     htmlStr = m_script.replaceAll(""); //過濾script標(biāo)簽
     p_style = Pattern.compile(regEx_style,Pattern.CASE_INSENSITIVE);
     m_style = p_style.matcher(htmlStr);
     htmlStr = m_style.replaceAll(""); //過濾style標(biāo)簽
     p_html = Pattern.compile(regEx_html,Pattern.CASE_INSENSITIVE);
     m_html = p_html.matcher(htmlStr);
     htmlStr = m_html.replaceAll(""); //過濾html標(biāo)簽
     textStr = htmlStr;
  }catch(Exception e){
  e.printStackTrace();
  }
  return textStr;//返回文本字符串
} 
}