过滤HTML部分
package cn.jxsme.util.tool;import java.util.regex.Pattern;
/*
* autho huangjin green eat
*Oct 17, 2008
*/
public class FifterHtml {
public static String Html2Text(String inputString) {
String htmlStr = inputString; //��html��ǩ���ַ�
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;
try {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; //����script��������ʽ{��<script[^>]*?>[\\s\\S]*?<\\/script> }
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //����style��������ʽ{��<style[^>]*?>[\\s\\S]*?<\\/style> }
// String regEx_html = "<[^>]+>"; //����HTML��ǩ��������ʽ
String regEx_html = "<[.[^<]]*>";
p_script = Pattern.compile(regEx_script,Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); //����script��ǩ
p_style = Pattern.compile(regEx_style,Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //����style��ǩ
p_html = Pattern.compile(regEx_html,Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //����html��ǩ
textStr= htmlStr.replaceAll("<td>", "");
textStr=htmlStr.replaceAll("<","");
textStr=htmlStr.replaceAll(">","");
textStr = htmlStr;
}catch(Exception e) {
System.err.println("yjxHtml2Text().Html2Text: " + e.getMessage());
}
return textStr;//�����ı��ַ�
}
public static String FifterSQL(String str)
{
return str.replaceAll(".*([';]+|(--)+).*", " ");
}
public static StringTestToHtml(String input){
if (input == null) {
return null;
}
if (input.length() == 0) {
return input;
}
input = input.replaceAll(" ", " ");
input = input.replaceAll("\r\n", "<br/>");
input = input.replaceAll("\n", "<br/>");
return input;
}
public static StringHtmlToTest(String input){
if (input == null) {
return null;
}
if (input.length() == 0) {
return input;
}
input = input.replaceAll( " "," ");
input = input.replaceAll("<br/>","\r\n");
input = input.replaceAll("<br/>","\n");
return input;
}
}
页:
[1]