java正则去除富文本中各类html标签、空格、换行符

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

public class HtmlFormat {

    private static final String regEx_script = "]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式
    private static final String regEx_style = "]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式
    private static final String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
    private static final String regEx_space = "\\s*|\t|\r|\n";//定义空格回车换行符


    public static void main(String[] args) {
        String str = "
近 日， 徐工无人集群智能\" +\n" +
                "\t\t\t\t\"化施工火了~央视综合频道《新闻30分》媒体纷纷报道了徐工\" +\n" +
                "\t\t\t\t\"上驰骋出“中国速度”！ 
";
        System.out.println(getTextFromHtml(str));
    }

    public static String getTextFromHtml(String htmlStr){
        htmlStr = delHTMLTag(htmlStr);
        htmlStr = htmlStr.replaceAll(" ", "");
        htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
        return htmlStr;
    }
    /**
     * @param htmlStr
     * @return
     *  删除Html标签
     */
    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(""); // 过滤script标签

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

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

        Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
        Matcher m_space = p_space.matcher(htmlStr);
        htmlStr = m_space.replaceAll(""); // 过滤空格回车标签
        return htmlStr.trim(); // 返回文本字符串
    }

}