去除html标记,比较实用,分享给大家。
/// <summary>
/// 去除HTML标记
/// </summary>
/// <param name="Htmlstring">包括HTML的源码 </param>
/// <returns>已经去除后的文字</returns>
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Htmlstring.Replace("
","");
Htmlstring = Regex.Replace(Htmlstring,@"<script.*?</script>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<style.*?</style>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<.*?>","",RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring,@"<(.[^>]*)>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"([
])[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 = Htmlstring.Replace("<","");
Htmlstring = Htmlstring.Replace(">","");
Htmlstring = Htmlstring.Replace("
","");
Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
/// <summary>
/// 提取HTML代码中文字的C#函数
/// </summary>
public static string StripHTML(string strHtml)
{
string [] aryReg ={
@"<script[^>]*?>.*?</script>",
@"<(/s*)?!?((w+:)?w+)(w+(s*=?s*(([""'])(\[""'tbnr]|[^7])*?7|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 = {
"",
"",
"",
""",
"&",
"<",
">",
" ",
"xa1",//chr(161),
"xa2",//chr(162),
"xa3",//chr(163),
"xa9",//chr(169),
"",
"
",
""
};
string newReg =aryReg[0];
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
{
Regex regex = new Regex(aryReg[i],RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput,aryRep[i]);
}
strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace("
","");
return strOutput;
}
#region 取出文本中的图片地址
/**//// <summary>
/// 取出文本中的图片地址
/// </summary>
/// <param name="HTMLStr">HTMLStr</param>
public static string GetImgUrl(string HTMLStr)
{
string str = string.Empty;
string sPattern = @"^<imgs+[^>]*>";
Regex r = new Regex(@"<imgs+[^>]*s*srcs*=s*([']?)(?<url>S+)'?[^>]*>",
RegexOptions.Compiled);
Match m = r.Match(HTMLStr.ToLower());
if (m.Success)
str = m.Result("${url}");
return str;
}
#endregion