c#中过滤html的正则表达式
作者:mdxy-dxy 时间:2023-07-04 04:03:24
实现代码
/// <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;
}
C#过滤Html标签及空格
public static string FilterHTML(string HTMLStr)
{
if (!string.IsNullOrEmpty(HTMLStr))
return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>| ", "");
else
return "";
}
写一个静态方法移除HTML标签
#region
/// <summary>
/// 移除HTML标签
/// </summary>
/// <param name="HTMLStr">HTMLStr</param>
public static string ParseTags(string HTMLStr)
{
return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
}
#endregion
取出文本中的图片地址
#region
/// <summary>
/// 取出文本中的图片地址
/// </summary>
/// <param name="HTMLStr">HTMLStr</param>
public static string GetImgUrl(string HTMLStr)
{
string str = string.Empty;
string sPattern = @"^<img\s+[^>]*>";
Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>",
RegexOptions.Compiled);
Match m = r.Match(HTMLStr.ToLower());
if (m.Success)
str = m.Result("${url}");
return str;
}
#endregion
提取HTML代码中文字的C#函数
/// <summary>
/// 提取HTML代码中文字的C#函数
/// </summary>
/// <param name="strHtml">包括HTML的源码 </param>
/// <returns>已经去除后的文字</returns>
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest
{
public static void Main()
{
string s = StripHTML(
"<HTML><HEAD><TITLE>中国石龙信息平台</TITLE></HEAD><BODY>faddfs龙信息平台</BODY></HTML>");
Console.WriteLine(s);
}
public static string StripHTML(string strHtml)
{
string[]aryReg =
{
@"<script[^>]*?>.*?</script>",
@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\["
"'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @
"&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @
"&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);",
@"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.*\n"
};
string[]aryRep =
{
"", "", "", "\"", "&", "<", ">", " ", "\xa1", //chr(161),
"\xa2", //chr(162),
"\xa3", //chr(163),
"\xa9", //chr(169),
"", "\r\n", ""
};
string newReg = aryReg[0];
string strOutput = strHtml;
for (int i = 0; i < aryReg.Length; i++)
{
Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput, aryRep[i]);
}
strOutput.Replace("<", "");
strOutput.Replace(">", "");
strOutput.Replace("\r\n", "");
return strOutput;
}
}
TempContent 表示包含有html的字符串;
TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]+>","");至少一个
TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]*>","");任意个
标签:c#,过滤,html
0
投稿
猜你喜欢
利用python实现AR教程
2021-07-09 16:39:04
使用python实现ftp的文件读写方法
2022-02-06 11:25:03
利用Python自动生成PPT的示例详解
2021-10-16 18:25:08
栅格:一以贯之
2008-07-22 12:19:00
Python机器学习之KNN近邻算法
2022-05-12 23:14:17
SQLServer2000 报1053错误(服务没有及时响应或控制请求)的解决方法
2024-01-23 10:40:47
安装SQL Server 2005时出现计数器错误
2008-11-28 14:19:00
asp如何写入超长的字符串?
2010-06-09 18:53:00
Python中的单例模式与反射机制详解
2023-11-24 00:55:54
简介Django框架中可使用的各类缓存
2022-01-16 13:02:39
Python Datetime模块和Calendar模块用法实例分析
2022-08-05 10:23:46
python实现简单图片物体标注工具
2021-09-07 21:31:50
Mysqlslap MySQL压力测试工具 简单教程
2024-01-15 20:10:10
解决python 3 urllib 没有 urlencode 属性的问题
2022-03-31 12:42:44
php 的反射详解及示例代码
2024-06-05 09:46:28
asp MYSQL出现问号乱码的解决方法
2011-04-15 11:13:00
Centos部署django服务nginx+uwsgi的方法
2022-03-18 07:47:26
Python实现读写sqlite3数据库并将统计数据写入Excel的方法示例
2024-01-21 07:55:04
2个asp获取安全字符串的方法
2007-10-19 15:08:00
通过事务日志解决SQL Server常见四大故障(一)
2009-03-25 13:46:00