熱點推薦:
您现在的位置: 電腦知識網 >> 編程 >> .NET編程 >> 正文

C#過濾HTML代碼

2013-11-13 09:57:31  來源: .NET編程 

  public string NoHTML(string Htmlstring)

  //去除HTML標記

  {

  //刪除腳本

  Htmlstring = RegexReplace(Htmlstring@<script[^>]*?>*?</script>RegexOptionsIgnoreCase);

  //刪除HTML

  Htmlstring = RegexReplace(Htmlstring@<([^>]*)>RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@([\r\n])[\s]+RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@>RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@<!*RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(quot|#);\RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(amp|#);&RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(lt|#);<RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(gt|#);>RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(nbsp|#); RegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(iexcl|#);\xaRegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(cent|#);\xaRegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(pound|#);\xaRegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&(copy|#);\xaRegexOptionsIgnoreCase);

  Htmlstring = RegexReplace(Htmlstring@&#(\d+);RegexOptionsIgnoreCase);

  HtmlstringReplace(<);

  HtmlstringReplace(>);

  HtmlstringReplace(\r\n);

  Htmlstring=HttpContextCurrentServerHtmlEncode(Htmlstring)Trim();

  return Htmlstring;

  }


From:http://tw.wingwit.com/Article/program/net/201311/12113.html
    推薦文章
    Copyright © 2005-2013 電腦知識網 Computer Knowledge   All rights reserved.