想去掉除了段落標記之外的所有html標記,只要頁面的文字,好比是我把代碼貼到記事本裡面的效果,去掉了連結等代碼。 可以試試。
public static string DelHTML(string Htmlstring)//將HTML去除 { #region //刪除樣式 Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<STYLE>[/s/S]*<\/STYLE>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); //刪除WORD樣式 begin Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"Normal[^>]*?Mso", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"Normal[^>]*?Mso", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"v[^>]*?}", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"o[^>]*?beha", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"w[^>]*?beha", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @".shape[^>]*?beha", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); //刪除WORD樣式 end //刪除指令碼 Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"-->", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"<!--.*", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(amp|#38);", "&", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(lt|#60);", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(gt|#62);", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring, @"&#(\d+);", "", System.Text.RegularExpressions.RegexOptions.IgnoreCase); Htmlstring = Htmlstring.Replace("<", ""); Htmlstring = Htmlstring.Replace(">", ""); Htmlstring = Htmlstring.Replace("\r\n", ""); #endregion //Htmlstring = Regex.Replace(Htmlstring, @"[^一-龥]", ""); //只留漢字 return Htmlstring; }
調用時傳入原資料.返回的就是除去後的.
|