用C#去除字符串中HTML的格式
2010-01-16 11:32
423 查看
public static string DelHTML(string Htmlstring)//将HTML去除
{ #region //删除脚本
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//删除HTML
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,@"<A>.*</A>",""); //Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=\.[a-zA-Z]*\?[a-zA-Z]+=\d&\w=%[a-zA-Z]*|[A-Z0-9]","");
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.Replace("<","");
Htmlstring.Replace(">","");
Htmlstring.Replace("\r\n","");
//Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim(); #endregion
return Htmlstring;
}
{ #region //删除脚本
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//删除HTML
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,@"<A>.*</A>",""); //Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=\.[a-zA-Z]*\?[a-zA-Z]+=\d&\w=%[a-zA-Z]*|[A-Z0-9]","");
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.Replace("<","");
Htmlstring.Replace(">","");
Htmlstring.Replace("\r\n","");
//Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim(); #endregion
return Htmlstring;
}
相关文章推荐
- C#字符串去除html格式
- 用C#去除字符串中HTML的格式(清除数据库中html标签)
- [转]C#字符串去除html格式
- 用C#去除字符串中HTML的格式(清除数据库中html标签)
- C# 字符串去除HTML格式
- 用C#去除字符串中HTML的格式
- 用C#去除字符串中HTML的格式
- 用C#去除字符串中HTML的格式
- 去除HTML格式 截取字符串
- asp.net(C#)去除html格式
- C#去除一段字符串内的HTML标签,正则表达式
- C#截取数据库中有HTML格式的字符串
- C#字符串去除html标记
- C#去除指定字符串中的HTML标签
- C#中利用正则表达式去除HTML中的格式
- 请问我如何在一个webBrowser控件中加载一个 html格式的字符串 - _NET技术 - C#
- asp.net(C#)去除html格式
- 去除字符串中的html格式
- C#去除字符串中的HTML,效果就像将HTML复制到记事本一样
- c#使用输出html字符串进行导出excel功能时,常用到得几种格式