3种方法从Html中取文本

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.Replace("<", "");
        Htmlstring.Replace(">", "");
        Htmlstring.Replace("\r\n", "");
        Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

        return Htmlstring;
    }

 

 

using System.Text.RegularExpressions;//需要引用

  // 利用正则表达式去掉"<"和">"之间的内容
  private string StripHT(string strHtml)
  {
   Regex regex=new Regex("<.+?>",RegexOptions.IgnoreCase);
   string strOutput=regex.Replace(strHtml,"");
   return strOutput;
  }

 

 

2

using System.Text.RegularExpressions;
/// <summary>
/// HtmlExtract 抽取html里面的文本信息
/// </summary>
public class HtmlExtract
{
   
        #region private attributes
        private string _strHtml;
        #endregion
        #region public mehtods
         public HtmlExtract(string inStrHtml)
        { _strHtml = inStrHtml;}
        public string ExtractText()
        {
            string result = _strHtml;
            result = RemoveComment(result);
            result = RemoveScript(result);
            result = RemoveStyle(result);
            result = RemoveTags(result);
            return result.Trim();
        }
        #endregion
     #region private methods
       private string RemoveComment(string input)
{
string result = input;
//remove comment
result = Regex.Replace(result, @"<!--[^-]*-->", string.Empty, RegexOptions.IgnoreCase);
return result;
}

3,using System.Text.RegularExpressions;

/// <summary>
/// HtmlExtract 抽取html里面的文本信息
/// </summary>
public class HtmlExtract
{
   
        #region private attributes
        private string _strHtml;
        #endregion

        #region public mehtods
         public HtmlExtract(string inStrHtml)
        { _strHtml = inStrHtml;}

        public string ExtractText()
        {
            string result = _strHtml;
            result = RemoveComment(result);
            result = RemoveScript(result);
            result = RemoveStyle(result);
            result = RemoveTags(result);
            return result.Trim();
        }
        #endregion

     #region private methods
       private string RemoveComment(string input)
{
string result = input;
//remove comment
result = Regex.Replace(result, @"<!--[^-]*-->", string.Empty, RegexOptions.IgnoreCase);
return result;
}
       private string RemoveStyle(string input)
{
string result = input;
//remove all styles
result = Regex.Replace(result, @"<style[^>]*?>.*?</style>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline);
return result;
}
       private string RemoveScript(string input)
{
string result = input;
result = Regex.Replace(result, @"<script[^>]*?>.*?</script>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline);
result = Regex.Replace(result, @"<noscript[^>]*?>.*?</noscript>", string.Empty, RegexOptions.IgnoreCase | RegexOptions.Singleline);
return result;
}
       private string RemoveTags(string input)
{
string result = input;
result = result.Replace(" ", " ");
result = result.Replace("'", "\"");
result = result.Replace("<", "<");
result = result.Replace(">", ">");
result = result.Replace("&", "&");
result = result.Replace("<br>", "\r\n");
result = Regex.Replace(result, @"<[\s\S]*?>", string.Empty, RegexOptions.IgnoreCase);
return result;
}
     #endregion
}