package com.xz.cxzy.utils; import java.util.regex.Matcher; import java.util.regex.Pattern; public class HtmlUtil { private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定義script的正則表達式 private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定義style的正則表達式 private static final String regEx_html = "<[^>]+>"; // 定義HTML標籤的正則表達式 private static final String regEx_space = "\\s*|\t|\r|\n";//定義空格回車換行符 /** * @param htmlStr * @return * 刪除Html標籤 */ 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(""); // 過濾script標籤 Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE); Matcher m_style = p_style.matcher(htmlStr); htmlStr = m_style.replaceAll(""); // 過濾style標籤 Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE); Matcher m_html = p_html.matcher(htmlStr); htmlStr = m_html.replaceAll(""); // 過濾html標籤 Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE); Matcher m_space = p_space.matcher(htmlStr); htmlStr = m_space.replaceAll(""); // 過濾空格回車標籤 return htmlStr.trim(); // 返回文本字符串 } public static String getTextFromHtml(String htmlStr){ htmlStr = delHTMLTag(htmlStr); htmlStr = htmlStr.replaceAll(" ", ""); htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1); return htmlStr; } public static void main(String[] args) { String str = "<div style='text-align:center;'> 整治「四風」 清弊除垢<br/><span style='font-size:14px;'> </span><span style='font-size:18px;'>公司召開黨的羣衆路線教育實踐活動動員大會</span><br/></div>"; System.out.println(getTextFromHtml(str)); } }