Java正則テキストからHTMLタグを削除

2181 ワード

import java.util.regex.Pattern;

/**
 * Created by CoolinTan on 7/2/2015.
 */
public class HtmlToTextUtil {


    /**
     *   inputString  HTML/CSS/JS  
     */
    public static String htmlToText(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 {
            //   script      { <script[^>]*?>[//s//S]*?<///script>
            String regEx_script = "<[//s]*?script[^>]*?>[//s//S]*?<[//s]*?///[//s]*?script[//s]*?>";

            //   style      { <style[^>]*?>[//s//S]*?<///style>
            String regEx_style = "<[//s]*?style[^>]*?>[//s//S]*?<[//s]*?///[//s]*?style[//s]*?>";

            //   HTML        
            String regEx_html = "<[^>]+>";
            String regEx_html1 = "<[^>]+";
            p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
            m_script = p_script.matcher(htmlStr);
            htmlStr = m_script.replaceAll(""); //   script  

            p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
            m_style = p_style.matcher(htmlStr);
            htmlStr = m_style.replaceAll(""); //   style  

            p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
            m_html = p_html.matcher(htmlStr);
            htmlStr = m_html.replaceAll(""); //   html  

            p_html1 = Pattern.compile(regEx_html1, Pattern.CASE_INSENSITIVE);
            m_html1 = p_html1.matcher(htmlStr);
            htmlStr = m_html1.replaceAll(""); //   html  

            textStr = htmlStr;

        } catch (Exception e) {
            System.err.println("Html2Text: " + e.getMessage());
        }

        return textStr;//        
    }
}