-
C# 替换去除HTML标记方法(正则表达式)
- using System.Text.RegularExpressions;
-
- public static string NoHTML(string Htmlstring)
- {
-
- Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
-
- 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;
- }
-
-
-
-
-
- public static string StripHTML(string strHtml)
- {
- string[] aryReg ={
- @"<script[^>]*?>.*?</script>",
- @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(file://[""'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",
- "\xa2",
- "\xa3",
- "\xa9",
- "",
- "\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;
- }
-
相关阅读:
PL/SQL 入门
Nginx 安装和配置
MySql 优化方案
类加载器(ClassLoader)
动态代理入门
Servlet 3.0 介绍
反射加强(一)
Python(1)—is和==区别
代码题(10)— 验证二叉搜索树、二叉搜索树的最近公共祖先
代码题(9)— 二叉树的最大、最小深度、平衡二叉树
-
原文地址:https://www.cnblogs.com/fery/p/1605679.html
Copyright © 2020-2023
润新知