using System; using System.Web; using System.Text.RegularExpressions; public static string NoHTML(string Htmlstring) { //删除剧本 Htmlstring = Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>", "",RegexOptions.IgnoreCase); //删除HTML Htmlstring = Regex.Replace(Htmlstring,@"<(.[^>]*)>","",RegexOption s.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"([\r\n])[\s]+","",Regex Options.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"-->","",RegexOptions.Ign oreCase); Htmlstring = Regex.Replace(Htmlstring,@"<!--.*","",RegexOptions. IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(quot|#34);","\"",Rege xOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(amp|#38);","&",RegexO ptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(lt|#60);","<",RegexOpt ions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(gt|#62);",">",RegexOpt ions.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",R egexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(pound|#网易);","\xa3", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring,@"&(copy|#169);","\xa9",R egexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);","",RegexOptions.IgnoreCase); Htmlstring.Replace("<",""); Htmlstring.Replace(">",""); Htmlstring.Replace("\r\n",""); Htmlstring=HttpContext.Current.Server.HtmlEncode(H tmlstring).Trim(); return Htmlstring; }
/**提取HTML代码中书契的C#函数
/// <summary>
/// 去除HTML标记
/// </summary>
/// <param name="strHtml">包孕HTML的源码 </param>
/// <returns>已经去除后的书契</returns>
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest{
public static void Main(){
string s=StripHTML("<HTML><HEAD><TITLE>资料测试</TITLE></HEAD><BODY>信息</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|#网易);",
@"&(copy|#169);",
@"&#(\d+);",
@"-->",
@"<!--.*\n"
};
string [] aryRep = {
"",
"",
"",
"\"",
"&",
"<",
">",
" ",
"\xa1",//chr(161),
"\xa2",//chr(162),
"\xa3",//chr(网易),
"\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;
}
}
写一个静态要领
移除HTML标签#region 移除HTML标签
/** <summary>
/// 移除HTML标签
/// </summary>
/// <param name="HTMLStr">HTMLStr</param>
public static string ParseTags(string HTMLStr)
{
return System.Text.RegularExpressions.Regex.Replace(HTMLS tr, "<[^>]*>", "");
}
取出文本中的图片地址#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 = @"^<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; }