java 去掉html标签（Java中去掉网页HTML标记的方法 ）--正则表达式

Posted 2020-09-28 tangyongathuse

参考：

http://www.cnblogs.com/newsouls/p/3995394.html

http://blog.csdn.net/he20101020/article/details/21228311

 

内容：

package utils;

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

/**
 * 注：\\n 回车(\\u000a)
 *    \\t 水平制表符(\\u0009)
 *    \\s 空格(\\u0008)
 *    \\r 换行(\\u000d)
 * Created by Administrator on 2017/7/14.
 */
public class HtmlUtil {
    public static void main(String[] args) {

        String str = "<div class=\\"WB_cardwrap S_bg2\\">\\n" +
                "  <div class=\\"search_feed\\">\\n" +
                "    <div class=\\"person_list_feed clearfix\\">\\n" +
                "      <div class=\\"pl_personlist\\">\\n" +
                "        <div class=\\"list_person clearfix\\">\\n" +
                "          <div class=\\"person_pic\\">\\n" +
                "            <a target=\\"_blank\\" href=\\"http://weibo.com/114dotcom?refer_flag=1001030201_\\" title=\\"114导航\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_icon\\">\\n" +
                "              <img class=\\"W_face_radius\\" src=\\"http://tva4.sinaimg.cn/crop.176.129.505.505.180/006aCV5fgw1f0gxs4ikuyj30ne0juq47.jpg\\" uid=\\"5653836249\\" height=\\"80\\" width=\\"80\\" /></a>\\n" +
                "          </div>\\n" +
                "          <div class=\\"person_detail\\">\\n" +
                "            <p class=\\"person_name\\">\\n" +
                "              <a class=\\"W_texta W_fb\\" target=\\"_blank\\" href=\\"http://weibo.com/114dotcom?refer_flag=1001030201_\\" title=\\"114导航\\" uid=\\"5653836249\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_name\\">114导航</a>\\n" +
                "              <a target=\\"_blank\\" href=\\"http://verified.weibo.com/verify\\" title=\\"微博机构认证\\" alt=\\"微博机构认证\\" class=\\"W_icon icon_approve_co\\"></a>\\n" +
                "            </p>\\n" +
                "            <p class=\\"person_addr\\">\\n" +
                "              <span class=\\"male m_icon\\" title=\\"男\\"></span>\\n" +
                "              <span>广东</span>\\n" +
                "              <a class=\\"W_linkb\\" target=\\"_blank\\" href=\\"http://weibo.com/114dotcom?refer_flag=1001030201_\\" class=\\"wb_url\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_url\\">http://weibo.com/114dotcom</a></p>\\n" +
                "            <p class=\\"person_card\\">\\n" +
                "              <em class=\\"red\\">一一四网络有限公司</em></p>\\n" +
                "            <p class=\\"person_num\\">\\n" +
                "              <span>关注\\n" +
                "                <a class=\\"W_linkb\\" href=\\"http://weibo.com/5653836249/follow?refer_flag=1001030201_\\" target=\\"_blank\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_num\\">68</a></span>\\n" +
                "              <span>粉丝\\n" +
                "                <a class=\\"W_linkb\\" href=\\"http://weibo.com/5653836249/fans?refer_flag=1001030201_\\" target=\\"_blank\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_num\\">118</a></span>\\n" +
                "              <span>微博\\n" +
                "                <a class=\\"W_linkb\\" href=\\"http://weibo.com/5653836249/profile?refer_flag=1001030201_\\" target=\\"_blank\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_num\\">7</a></span>\\n" +
                "            </p>\\n" +
                "            <div class=\\"person_info\\">\\n" +
                "              <p>简介： 114.com，不一样的导航，能记住吗？追求小清新，简约到极致。推荐给您的不仅是网址，更是给你需要的答案。此外，114.com还提供电话、品牌、名人、价格等各种实用查询。</p>\\n" +
                "            </div>\\n" +
                "            <p class=\\"person_label\\">标签：\\n" +
                "              <a class=\\"W_linkb\\" href=\\"&tag=%25E6%2596%25B0%25E9%2597%25BB%25E7%2583%25AD%25E7%2582%25B9&Refer=SUer_tag\\" suda-data=\\"key=tblog_search_user&value=user_feed_1_label\\">新闻热点</a></p>\\n" +
                "          </div>\\n" +
                "        </div>\\n" +
                "      </div>\\n" +
                "    </div>\\n" +
                "  </div>\\n" +
                "</div>\\n" +
                "<div class=\\"WB_cardwrap S_bg2 relative\\"></div>\\n" +
                "<!-- 未登录提示 -->\\n" +
                "<div class=\\"search_tips clearfix\\">\\n" +
                "  <p class=\\"tips_co\\">\\n" +
                "    <span class=\\"tips_icon icon_warn\\"></span>\\n" +
                "    <span class=\\"tips_txt\\">\\n" +
                "      <a href=\\"javascript:void(0);\\" action-type=\\"login\\">立即登录</a>查看更多结果。还没有账号？赶紧\\n" +
                "      <a href=\\"http://weibo.com/signup/signup.php?lang=zh-cn&amp;entry=weisousuo\\" suda-data=\\"key=tblog_search_v4.1&amp;value=nologin_reg\\" target=\\"_blank\\">注册微博</a></span>\\n" +
                "  </p>\\n" +
                "</div>\\n" +
                "<!-- /未登录提示 -->";

        System.out.println(delHTMLTag(str));
    }

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

        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 stripHtml(String content) {
// <p>段落替换为换行
        content = content.replaceAll("<p .*?>", "\\r\\n");
// <br><br/>替换为换行
        content = content.replaceAll("<br\\\\s*/?>", "\\r\\n");
// 去掉其它的<>之间的东西
        content = content.replaceAll("\\\\<.*?>", "");
// 还原HTML
// content = HTMLDecoder.decode(content);
        return content;
    }

    public static String getTextFromHtml(String htmlStr){
        htmlStr = delHTMLTag(htmlStr);
        htmlStr = htmlStr.replaceAll("&nbsp;", "");
        //htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
        return htmlStr;
    }

}