zoukankan      html  css  js  c++  java
  • java 去掉html/style/css等标签

    //定义script的正则表达式
    private static String regEx_script="<script[^>]*?>[\s\S]*?<\/script>";

    //定义style的正则表达式
    private static String regEx_style="<style[^>]*?>[\s\S]*?<\/style>";

    //定义HTML标签的正则表达式
    private static String regEx_html="<[^>]+>";

    //定义空格回车换行符
    private static String regEx_space = "\s*| | | ";//定义空格回车换行符


    /**
    * 验证名称中是否含有标签,并返回字符串
    * @param htmlStr
    * @return
    */
    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
    }
    /**
    * 获取标签中的字符串
    * @param htmlStr
    * @return
    */
    public static String getTextFromHtml(String htmlStr){
    htmlStr = delHTMLTag(htmlStr);
    htmlStr = htmlStr.replaceAll("&nbsp;","");
    //htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
    return htmlStr;
    }

    public static void main(String[] args) {
    String str = "<html>alert(2)</html>";
    System.out.println(getTextFromHtml(str));
    }

  • 相关阅读:
    Codeforces Round #443 (Div. 2)ABC
    Codeforces Round #442 (Div. 2) ABC
    Wannafly挑战赛2 Cut
    热爱工作的蒜蒜
    Codeforces Round #441 (Div. 2) (ABC)
    Codeforces Round #440 (Div. 2)(ABC)
    Codeforces Round #439 (Div. 2)(ABC)
    sphinx 分词搭建手册
    [转]Chrome 控制台console的用法
    shell脚本复制文件夹内容到另外的文件夹,如果存在则自动备份
  • 原文地址:https://www.cnblogs.com/yaomajor/p/6019570.html
Copyright © 2011-2022 走看看