用到这个的一般是显示文章内容的摘要的时候.
一般文章内容里有html的时候,用一般的截取,会将内容里的html一起给截出来,轻则显示出不必要的乱码,重则导致网站样式/布局的破坏.
要解决这个问题很容易,两步就可以搞定
一,过滤掉内容里的html.
二,截取过滤后的内容.
这里把c#的代码放出来.
//截取部分内容方法
public string strvalue(string value, int length)
{
if (value.Length > length)
{
value = value.Substring(0, length);
value = value + "...";
return NoHTML(value);
}
else
{
return NoHTML(value);
}
}
#region 回车,空格过滤
/**/
/// <summary>
/// 去除HTML标记
/// </summary>
/// <param name="NoHTML">包括HTML的源码 </param>
/// <returns>已经去除后的文字</returns>
public static string NoHTML(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
代码就这些,记得要引用正则的命名空间 using System.Text.RegularExpressions;
剩下的就是在需要将需要截取的部分用strvalue 方法搞定!