package search;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/** *//**
* 功能：过滤标签
* @author jiadong
* 时间：2007年10月15日��
* 版本：1.0�
*/
public class HtmlTagsProcessor 
{
public static String tagsProcessor(String inputString){
String processedString = "" ;
Pattern js_pattern,style_pattern, html_pattern ,particular_pattern;
Matcher js_matcher,style_matcher,html_matcher,particular_matcher;
//过滤js的正则表达式
String js_str = "<script.*>X*.*</script>X*";
//过滤样式的正则表达式
String style_str = "<style.*>X*.*</style>X*";
//过滤html标签的正则表达式
String html_str = "<[^>]+>" ;
String particular_str = ">|&| |"";
//处理js标签
js_pattern = Pattern.compile(js_str, Pattern.CASE_INSENSITIVE);
js_matcher = js_pattern.matcher(inputString);
processedString = js_matcher.replaceAll("");
//处理样式标签
style_pattern = Pattern.compile(style_str, Pattern.CASE_INSENSITIVE);
style_matcher = style_pattern.matcher(processedString);
processedString = style_matcher.replaceAll("");
//处理html标签
html_pattern = Pattern.compile(html_str, Pattern.CASE_INSENSITIVE);
html_matcher = html_pattern.matcher(processedString);
processedString = html_matcher.replaceAll("");
particular_pattern = Pattern.compile(particular_str,Pattern.CASE_INSENSITIVE);
particular_matcher = particular_pattern.matcher(processedString);
processedString = particular_matcher.replaceAll("");
return processedString ;
}
}
posted on 2007-10-17 11:32
jiadong 阅读(405)
评论(0) 编辑 收藏 所属分类:
OTHERS