一個用C#過濾HTML代碼的函數

正好有時間所以用C#寫了一段Regex,作用是刪除 Page 裡面Code 中的 HTML標籤,這在做採集資訊,消除其中的HTML很有用處。

以下是引用片段：
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, ""); //過濾<script></script>標記
          html = regex2.Replace(html, ""); //過濾href=javascript: (<A>) 屬性
          html = regex3.Replace(html, " _disibledevent="); //過濾其它控制項的on...事件
          html = regex4.Replace(html, ""); //過濾iframe
          html = regex5.Replace(html, ""); //過濾frameset
          html = regex6.Replace(html, ""); //過濾frameset
          html = regex7.Replace(html, ""); //過濾frameset
          html = regex8.Replace(html, ""); //過濾frameset
          html = regex9.Replace(html, "");
          html = html.Replace(" ", "");
          html = html.Replace("</strong>", "");
          html = html.Replace("<strong>", "");
          return html;
}