zoukankan      html  css  js  c++  java
  • java过滤html标签函数

    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]*?script[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?script[\s]*?>"; //定义script的正则表达式{或<script[^>]*?>[\s\S]*?<\/script> } 
               String regEx_style = "<[\s]*?style[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?style[\s]*?>"; //定义style的正则表达式{或<style[^>]*?>[\s\S]*?<\/style> } 
                  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) { 
                       System.err.println("Html2Text: " + e.getMessage()); 
              } 
           
              return textStr;//返回文本字符串 
               }   

  • 相关阅读:
    GTD180007:【运维】LINUX学习
    GTD180006:【运维】安装调试GDB
    {done}GTD180005:【翻译】LISP prehistory
    ComPiler180001:【学习】编译器学习链接
    AIIE180002:AIIE2015大会主题
    AIIE180001:AIIE2016大会主题
    GTD180004:【开发】python_med
    GTD180003:【开发】python_oeis
    欧亚大帝国及一战、二战
    大洲分界线
  • 原文地址:https://www.cnblogs.com/pangblog/p/3301679.html
Copyright © 2011-2022 走看看