黑马程序员技术交流社区
标题:
TXT与HTML互转及清除HTML标记
[打印本页]
作者:
guo329838627
时间:
2013-9-22 12:05
标题:
TXT与HTML互转及清除HTML标记
TXT转HTML
#region TXT代码转换成HTML格式
/// <summary>
/// TXT代码转换成HTML格式
/// </summary>
/// <param name="Input">等待处理的字符串</param>
/// <returns>处理后的字符串</returns>
public static String ToHtml(string Input)
{
StringBuilder sb = new StringBuilder(Input);
sb.Replace("&", "&");
sb.Replace("<", "<");
sb.Replace(">", ">");
sb.Replace("\r\n", "<br/>");
sb.Replace("\r", "<br/>");
sb.Replace("\n", "<br/>");
sb.Replace("\t", " ");
sb.Replace(" ", " ");
return sb.ToString();
}
#endregion
复制代码
HTML转TXT
#region HTML代码转换成TXT格式
/// <summary>
/// HTML代码转换成TXT格式
/// </summary>
/// <param name="Input">等待处理的字符串</param>
/// <returns>处理后的字符串</returns>
public static String ToTxt(String Input)
{
StringBuilder sb = new StringBuilder(Input);
sb.Replace(" ", " ");
sb.Replace("<br>", "\r\n");
sb.Replace("<br>", "\n");
sb.Replace("<br />", "\n");
sb.Replace("<br />", "\r\n");
sb.Replace("<", "<");
sb.Replace(">", ">");
sb.Replace("&", "&");
return sb.ToString();
}
#endregion
复制代码
清除HTML标记:
#region 清除HTML标记
/// <summary>
/// 清除HTML标记
/// </summary>
/// <param name="Htmlstring">要清除的字符串</param>
/// <returns></returns>
public static string DropHTML(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;
}
#endregion
复制代码
作者:
haxyek
时间:
2013-9-22 15:25
txt转成html:
"<"转成html 应该是“<” 吧?
欢迎光临 黑马程序员技术交流社区 (http://bbs.itheima.com/)
黑马程序员IT技术论坛 X3.2