- 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*|\t|\r|\n";// 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
- htmlStr = htmlStr.replaceAll(" ", "");
- htmlStr = htmlStr.replaceAll("", "");
- return htmlStr.trim(); // 返回文本字符串
- }
- }
来源: http://www.bubuko.com/infodetail-3284552.html