html去除标签

最新推荐文章于 2024-01-24 15:30:50 发布

东哥的博客

最新推荐文章于 2024-01-24 15:30:50 发布

阅读量267

点赞数

分类专栏： java开发

本文链接：https://blog.csdn.net/xiaozhengdong/article/details/8542492

版权

java开发专栏收录该内容

24 篇文章 0 订阅

订阅专栏

//html数据去除标签

public 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;
       try {
           String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>";
           String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>";
           String regEx_html = "<[^>]+>";
           p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
           m_script = p_script.matcher(htmlStr);
           htmlStr = m_script.replaceAll("");
           textStr = htmlStr;
           p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
           m_style = p_style.matcher(htmlStr);
           htmlStr = m_style.replaceAll("");
           textStr = htmlStr;
           p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
           m_html = p_html.matcher(htmlStr);
           htmlStr = m_html.replaceAll("");
           textStr = htmlStr;
       } catch (Exception e) {
           System.err.println("Html2Text: " + e.getMessage() + " with:"
                   + inputString);
           return null;
       }
       return textStr;
   }