225
Java 正則匹配html標簽
package com.test.util;
import java.util.regex.Pattern;
public class HtmlUtil {
/**
* 去除所有HTML標簽
* @param inputString
* @return
*/
public static String removeHtmlTag(String inputString) {
if (inputString == null){
return null;
} else {
// 含html標簽的字符串
String htmlStr = inputString;
String textStr = "";
java.util.regex.Pattern p_script;
java.util.regex.Matcher m_script;
java.util.regex.Pattern p_style;
java.util.regex.Matcher m_style;
java.util.regex.Pattern p_html;
java.util.regex.Matcher m_html;
java.util.regex.Pattern p_special;
java.util.regex.Matcher m_special;
try {
//定義script的正則表達式{或<script[^>]*?>[\\s\\S]*?<\\/script>
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>";
//定義style的正則表達式{或<style[^>]*?>[\\s\\S]*?<\\/style>
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>";
// 定義HTML標簽的正則表達式
String regEx_html = "<[^>]+>";
// 定義一些特殊字符的正則表達式 如：
String regEx_special = "\\&[a-zA-Z]{1,10};";
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
// 過濾script標簽
htmlStr = m_script.replaceAll("");
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
// 過濾style標簽
htmlStr = m_style.replaceAll("");
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
// 過濾html標簽
htmlStr = m_html.replaceAll("");
p_special = Pattern.compile(regEx_special, Pattern.CASE_INSENSITIVE);
m_special = p_special.matcher(htmlStr);
// 過濾特殊標簽
htmlStr = m_special.replaceAll("");
textStr = htmlStr;
} catch (Exception e) {
e.printStackTrace();
}
return textStr;
}
}
}
最後更新：2017-07-26 11:33:27