/**//// <summary>
/// 去除Html標記
/// </summary>
/// <param name="NoHTML">包括Html的源碼 </param>
/// <returns>已經去除後的文字</returns>
public static string NoHTML(string Htmlstring)
{
//刪除腳本
Htmlstring = Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",RegexOptions.IgnoreCase);
//刪除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.Replace("<","");
Htmlstring.Replace(">","");
Htmlstring.Replace("\r\n","");
Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
/**////提取Html代碼中文字的C#函數
/// <summary>
/// 去除Html標記
/// </summary>
/// <param name="strHtml">包括Html的源碼 </param>
/// <returns>已經去除後的文字</returns>
using System;
using System.Text.RegularExpressions;
public class StripHtmlTest
{
public static void Main()
{
string s=StripHTML("<HTML><HEAD><TITLE>中國石龍信息平台</TITLE></HEAD><BODY>faddfs龍信息平台</BODY></Html>");
Console.WriteLine(s);
}
public static string StripHTML(string strHtml)
{
string [] aryReg =
{
@"<script[^>]*?>.*?</script>",
@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""''])(\\[""''tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>",
@"([\r\n])[\s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(IExcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(\d+);",
@"-->",
@"<!--.*\n"
};
string [] aryRep =
{
"",
"",
"",
"\"",
"&",
"<",
">",
" ",
"\xa1",//chr(161),
"\xa2",//chr(162),
"\xa3",//chr(163),
"\xa9",//chr(169),
"",
"\r\n",
""
};
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("\r\n","");
return strOutput;
}
}
寫一個靜態方法
移除HTML標簽#region 移除Html標簽
/**//// <summary>
/// 移除Html標簽
/// </summary>
/// <param name="HTMLStr">HtmlStr</param>
public static string ParseTags(string HtmlStr)
{
return System.Text.RegularExpressions.Regex.Replace(HtmlStr, "<[^>]*>", "");
}
#endregion
取出文本中的圖片地址#region 取出文本中的圖片地址
/**//// <summary>
/// 取出文本中的圖片地址
/// </summary>
/// <param name="HTMLStr">HtmlStr</param>
public static string GetImgUrl(string HtmlStr)
{
string str = string.Empty;
string sPattern = @"^<img\s+[^>]*>";
Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*(['']?)(?<url>\S+)''?[^>]*>",
RegexOptions.Compiled);
Match m = r.Match(HtmlStr.ToLower());
if (m.Success)
str = m.Result("${url}");
return str;
}
#endregion
