过滤掉 html代码
#region 过滤掉 html代码
public static string StripHTML(string strHtml)
...{
string [] aryReg =...{
@"<script[^>]*?>.*?</script>",
@"<(/s*)?!?((w+:)?w+)(w+(s*=?s*(([""'])(/[""'tbnr]|[^])*?|w+)|.{0})|s)*?(/s*)?>",
@"([ ])[s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(d+);",
@"-->",
@"<!--.* "
};
string [] aryRep = ...{
"",
"",
"",
""",
"&",
"<",
">",
" ",
"¡",//chr(161),
"¢",//chr(162),
"£",//chr(163),
"©",//chr(169),
"",
" ",
""
};
string newReg =aryReg[0];
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
...{
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i],System.Text.RegularExpressions.RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput,aryRep[i]);
}
strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace(" ","");
return strOutput;
}
#endregion
public static string StripHTML(string strHtml)
...{
string [] aryReg =...{
@"<script[^>]*?>.*?</script>",
@"<(/s*)?!?((w+:)?w+)(w+(s*=?s*(([""'])(/[""'tbnr]|[^])*?|w+)|.{0})|s)*?(/s*)?>",
@"([ ])[s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(d+);",
@"-->",
@"<!--.* "
};
string [] aryRep = ...{
"",
"",
"",
""",
"&",
"<",
">",
" ",
"¡",//chr(161),
"¢",//chr(162),
"£",//chr(163),
"©",//chr(169),
"",
" ",
""
};
string newReg =aryReg[0];
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
...{
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i],System.Text.RegularExpressions.RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput,aryRep[i]);
}
strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace(" ","");
return strOutput;
}
#endregion