怎么过滤html标签

html-css026

怎么过滤html标签,第1张

过滤html标签代码如下：

public string checkStr(string html)

{

System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" on[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)

html = regex1.Replace(html, "")//过滤<script></script>标记

html = regex2.Replace(html, "")//过滤href=javascript: (<A>) 属性

html = regex3.Replace(html, " _disibledevent=")//过滤其它控件的on...事件

html = regex4.Replace(html, "")//过滤iframe

html = regex5.Replace(html, "")//过滤frameset

html = regex6.Replace(html, "")//过滤frameset

html = regex7.Replace(html, "")//过滤frameset

html = regex8.Replace(html, "")//过滤frameset

html = regex9.Replace(html, "")

html = html.Replace(" ", "")

html = html.Replace("</strong>", "")

html = html.Replace("<strong>", "")

return html

}

1、过滤所有html标签的属性的正则表达式：

$search = array ("'<script[^>]*?>.*?</script>'si", // 去掉 JavaScript

"'<[\/\!]*?[^<>]*?>'si", // 去掉 HTML 标记

"'([\r\n])[\s]+'",// 去掉空白字符

"'&(quot|#34)'i",// 替换 HTML 实体

"'&(amp|#38)'i",

"'&(lt|#60)'i",

"'&(gt|#62)'i",

"'&(nbsp|#160)'i"

) // 作为 PHP 代码运行

$replace = array ("","","\\1","\"","&","<",">"," ")

$html = preg_replace($search, $replace, $html)

顶