文本去除html标签

package com.csf.msnews.common.utils;

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

public class HtmlUtil {
    private static final String regEx_script = "<script[^>]*?>[\s\S]*?<\/script>"; // 定义script的正则表达式
    private static final String regEx_style = "<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|	|
|
";// 定义空格回车换行符

    /**
     * @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
    }

    public static String getTextFromHtml(String htmlStr) {
        htmlStr = htmlStr.replaceAll("

", "#&#");
        htmlStr = htmlStr.replaceAll("
", "#&#");
        htmlStr = htmlStr.replaceAll("
", "#&#");
        htmlStr = htmlStr.replaceAll("
", "#&#");
        htmlStr = htmlStr.replaceAll("<br/>", "#&#");
        htmlStr = htmlStr.replaceAll("</p>", "#&#");
        htmlStr = htmlStr.replaceAll("  ", "#&#");

        htmlStr = delHTMLTag(htmlStr);
        htmlStr = htmlStr.replaceAll("&nbsp;", "");

        int len = htmlStr.length();
        while (true) {
            htmlStr = htmlStr.replaceAll("#&##&#", "#&#");
            if (htmlStr.length() == len) {
                break;
            } else {
                len = htmlStr.length();
            }
        }

        return htmlStr;
    }

    public static void main(String[] args) {
        String str = "<P class=Para>  视觉(中国)文化发展股份有限公司</p><p class=Para> 111</p></p></p><a></p></p></p></p>222 投资者关系活动登记表</p><p class=Para>  无</p><p class=Para>  日 期 2017年03月16日</P>";
        // str = " aaa 



 春节过后";
        System.out.println(str);
        System.out.println(getTextFromHtml(str));
    }
}
原文地址:https://www.cnblogs.com/xiaolei2017/p/8989012.html