把文章里边的html标签去掉(去掉文字的样式,显示css设置的样式)

//删除脚本 
Htmlstring = Regex.Replace(Htmlstring, @” <script(\s[^>]*?)?>[\s\S]*? </script>”, “”, RegexOptions.IgnoreCase);
//删除样式
Htmlstring = Regex.Replace(Htmlstring, @” <style>[\s\S]*? </style>”, “”, RegexOptions.IgnoreCase);
//删除html标签
Htmlstring = Regex.Replace(Htmlstring, @” <(.[^>]*)>”, “”, RegexOptions.IgnoreCase);

public string checkStr(string html)
      {
          System.Text.RegularExpressions.Regex regex1
= new System.Text.RegularExpressions.Regex(@”<script[\s\S]+</script *>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex2
= new System.Text.RegularExpressions.Regex(@” href *= *[\s\S]*script *:, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex3
= new System.Text.RegularExpressions.Regex(@” no[\s\S]*=, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex4
= new System.Text.RegularExpressions.Regex(@”<iframe[\s\S]+</iframe *>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex5
= new System.Text.RegularExpressions.Regex(@”<frameset[\s\S]+</frameset *>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex6
= new System.Text.RegularExpressions.Regex(@”\<img[^\>]+\>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7
= new System.Text.RegularExpressions.Regex(@”</p>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex8
= new System.Text.RegularExpressions.Regex(@”<p>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          System.Text.RegularExpressions.Regex regex9
= new System.Text.RegularExpressions.Regex(@”<[^>]*>, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
          html
= regex1.Replace(html, “”);
          html
= regex2.Replace(html, “”);
          html
= regex3.Replace(html, _disibledevent=);
          html
= regex4.Replace(html, “”);
          html
= regex5.Replace(html, “”);
          html
= regex6.Replace(html, “”);
          html
= regex7.Replace(html, “”);
          html
= regex8.Replace(html, “”);
          html
= regex9.Replace(html, “”);
          html
= html.Replace( , “”);
          html
= html.Replace(</strong>, “”);
          html
= html.Replace(<strong>, “”);
         
return html;
}

版权声明:本文为elephant-wp原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
本文链接:https://www.cnblogs.com/elephant-wp/archive/2011/08/09/2132616.html