#region --------------------过滤HTML标签-----------------------
/// <summary>
/// 删除标签
/// </summary>
/// <param name="Htmlstring">原始标签</param>
/// <returns></returns>
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(html, @"<img[^>]*>;", "", RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
private 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(@" no[\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 网管网bitsCN.com
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;
}
public string subStringHTML(string param, int length, string end)
{
string Pattern = null;
MatchCollection m = null;//using System.Text.RegularExpressions;空间下的
StringBuilder result = new StringBuilder();
int n = 0;
char temp;
bool isCode = false; //是不是HTML代码
bool isHTML = false; //是不是HTML特殊字符,如
char[] pchar = param.ToCharArray();
for (int i = 0; i < pchar.Length; i++)
{
temp = pchar[i];
if (temp == '<')
{ isCode = true; }
else if (temp == '&')
{
isHTML = true;
}
else if (temp == '>' && isCode)
{
n = n - 1;
isCode = false;
}
else if (temp == ';' && isHTML)
{
isHTML = false;
}
if (!isCode && !isHTML)
{
n = n + 1; //UNICODE码字符占两个字节
if (System.Text.Encoding.Default.GetBytes(temp + "").Length > 1)
{
n = n + 1;
}
}
result.Append(temp);
if (n >= length)
{
break;
}
}
result.Append(end); //取出截取字符串中的HTML标记
string temp_result = result.ToString().Replace("(>)[^<>]*(<?)", "$1$2"); //去掉不需要结素标记的HTML标记
temp_result = temp_result.Replace(@"</?(AREA|BASE|BASEFONT|BODY|BR|COL|COLGROUP|DD|DT|FRAME|HEAD|HR|HTML|IMG|INPUT|ISINDEX|LI|LINK|META|OPTION|P|PARAM|TBODY|TD|TFOOT|TH|THEAD|TR|area|base|basefont|body|br|col|colgroup|dd|dt|frame|head|hr|html|img|input|isindex|li|link|meta|option|p|param|tbody|td|tfoot|th|thead|tr)[^<>]*/?>", ""); //去掉成对的HTML标记
temp_result = temp_result.Replace(@"<([a-zA-Z]+)[^<>]*>(.*?)</\1>", "$2"); //用正则表达式取出标记
Pattern = ("<([a-zA-Z]+)[^<>]*>");
m = Regex.Matches(temp_result, Pattern);
ArrayList endHTML = new ArrayList();
foreach (Match mt in m)
{
endHTML.Add(mt.Result("$1")); //补全不成对的HTML标记
}
for (int i = endHTML.Count - 1; i >= 0; i--)
{
result.Append("</");
result.Append(endHTML[i]);
result.Append(">");
}
return result.ToString();
}
#endregion
/// <summary>
/// 删除标签
/// </summary>
/// <param name="Htmlstring">原始标签</param>
/// <returns></returns>
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(html, @"<img[^>]*>;", "", RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
private 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(@" no[\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 网管网bitsCN.com
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;
}
public string subStringHTML(string param, int length, string end)
{
string Pattern = null;
MatchCollection m = null;//using System.Text.RegularExpressions;空间下的
StringBuilder result = new StringBuilder();
int n = 0;
char temp;
bool isCode = false; //是不是HTML代码
bool isHTML = false; //是不是HTML特殊字符,如
char[] pchar = param.ToCharArray();
for (int i = 0; i < pchar.Length; i++)
{
temp = pchar[i];
if (temp == '<')
{ isCode = true; }
else if (temp == '&')
{
isHTML = true;
}
else if (temp == '>' && isCode)
{
n = n - 1;
isCode = false;
}
else if (temp == ';' && isHTML)
{
isHTML = false;
}
if (!isCode && !isHTML)
{
n = n + 1; //UNICODE码字符占两个字节
if (System.Text.Encoding.Default.GetBytes(temp + "").Length > 1)
{
n = n + 1;
}
}
result.Append(temp);
if (n >= length)
{
break;
}
}
result.Append(end); //取出截取字符串中的HTML标记
string temp_result = result.ToString().Replace("(>)[^<>]*(<?)", "$1$2"); //去掉不需要结素标记的HTML标记
temp_result = temp_result.Replace(@"</?(AREA|BASE|BASEFONT|BODY|BR|COL|COLGROUP|DD|DT|FRAME|HEAD|HR|HTML|IMG|INPUT|ISINDEX|LI|LINK|META|OPTION|P|PARAM|TBODY|TD|TFOOT|TH|THEAD|TR|area|base|basefont|body|br|col|colgroup|dd|dt|frame|head|hr|html|img|input|isindex|li|link|meta|option|p|param|tbody|td|tfoot|th|thead|tr)[^<>]*/?>", ""); //去掉成对的HTML标记
temp_result = temp_result.Replace(@"<([a-zA-Z]+)[^<>]*>(.*?)</\1>", "$2"); //用正则表达式取出标记
Pattern = ("<([a-zA-Z]+)[^<>]*>");
m = Regex.Matches(temp_result, Pattern);
ArrayList endHTML = new ArrayList();
foreach (Match mt in m)
{
endHTML.Add(mt.Result("$1")); //补全不成对的HTML标记
}
for (int i = endHTML.Count - 1; i >= 0; i--)
{
result.Append("</");
result.Append(endHTML[i]);
result.Append(">");
}
return result.ToString();
}
#endregion