C#中利用正则表达式去除HTML中的格式
2011-07-27 16:33
639 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#中利用正则表达式去除HTML中的格式
- .net中利用正则表达式去除html格式
- C#去除一段字符串内的HTML标签,正则表达式
- C# 正则表达式,去除所有HTML标签
- 利用正则表达式去除HTML标签
- C# .Net使用正则表达式去除HTML标记和空格
- C#、JS利用正则表达式清理HTML标记一例
- 利用正则表达式实现去除所有HTML标签代码
- 笔记:JS利用正则表达式实现去除Html标签方法
- asp.net(c#)常用正则表达式实例(http://www.cnblogs.com/Aspnet2007/articles/1230060.html)
- .NET(C#)用正则表达式清除HTML标签(包括script和style),保留纯本文
- ios利用正则表达式判断手机号码格式是否正确
- C#中利用正则表达式获取字符串中双引号包含的内容
- C# 利用正则表达式进行忽略大小写的字符串替换的应用
- C#利用正则表达式实现字符串搜索
- [C#][固定格式网页解析]使用正则表达式处理网页的初步体会
- C#正则表达式匹配HTML中的图片路径,图片地址代码
- 正则表达式,去除所有HTML标签
- C#中利用正则表达式实现字符串搜索
- c#利用system.net发送html格式邮件