C# 删除String中的HTML标记的类

 1 using  System;
 2 using  System.Data;
 3 using  System.Configuration;
 4 using  System.Web;
 5 using  System.Text.RegularExpressions;
 6
 7 namespace  ConsoleApplication1
 8 {
 9    class Class1
10    {
11        /**//// <summary>
12        /// 去除HTML标记
13        /// </summary>
14        /// <param name="strHtml">包括HTML的源码 </param>
15        /// <returns>已经去除后的文字</returns>
16        public static string StripHTML(string strHtml)
17        {
18            string[] aryReg ={
19          @"<script[^>]*?>.*?</script>",
20
21          @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(file://[""'tbnr]|[^/7])*?/7|/w+)|.{0})|/s)*?(///s*)?>",
22          @"([\r\n])[\s]+",
23          @"&(quot|#34);",
24          @"&(amp|#38);",
25
26          @"&(lt|#60);",
27          @"&(gt|#62);", 
28          @"&(nbsp|#160);", 
29          @"&(iexcl|#161);",
30          @"&(cent|#162);",
31          @"&(pound|#163);",
32          @"&(copy|#169);",
33          @"&#(\d+);",
34          @"-->",
35          @"<!--.*\n"
36         
37         };
38
39            string[] aryRep = {
40           "",
41           "",
42           "",
43           "\"",
44           "&",
45           "<",
46           ">",
47           " ",
48           "\xa1",//chr(161),
49           "\xa2",//chr(162),
50           "\xa3",//chr(163),
51           "\xa9",//chr(169),
52           "",
53           "\r\n",
54           ""
55          };
56
57            string newReg = aryReg[0];
58            string strOutput = strHtml;
59            for (int i = 0; i < aryReg.Length; i++)
60            {
61                Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
62                strOutput = regex.Replace(strOutput, aryRep[i]);
63            }
64
65            strOutput.Replace("<", "");
66            strOutput.Replace(">", "");
67            strOutput.Replace("\r\n", "");
68
69
70            return strOutput;
71        }
72    }
73}
74
75
76