coding++：java—提取Html文本字符串中的內容

package com.tree.ztree_demo;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class StringTools {

    private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定義script的正則表達式
    private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定義style的正則表達式
    private static final String regEx_html = "<[^>]+>"; // 定義HTML標簽的正則表達式
    private static final String regEx_space = "\\s*|\t|\r|\n";//定義空格回車換行符

    /**
     * @param htmlStr
     * @return 刪除Html標簽
     */
    public static String delHTMLTag(String htmlStr) {
        Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
        Matcher m_script = p_script.matcher(htmlStr);
        htmlStr = m_script.replaceAll(""); // 過濾script標簽

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

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

        Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
        Matcher m_space = p_space.matcher(htmlStr);
        htmlStr = m_space.replaceAll(""); // 過濾空格回車標簽
        htmlStr = htmlStr.replaceAll("&nbsp;", "");
        htmlStr = htmlStr.replaceAll("↵", "");
        return htmlStr.trim(); // 返回文本字符串
    }

}