String文本去除HTML格式

View Code

1 /// <summary>
2 /// String文本去除HTML格式
3 /// </summary>
4 /// <param name="Htmlstring"></param>
5 /// <returns></returns>
6 public static string NoHTML( string Htmlstring)
7 {
8
9 // 删除脚本
10 Htmlstring = Regex.Replace(Htmlstring, @" <script[^>]*?>.*?</script> " , "" , RegexOptions.IgnoreCase);
11 // 删除HTML
12 Htmlstring = Regex.Replace(Htmlstring, @" <(.[^>]*)> " , "" , RegexOptions.IgnoreCase);
13 Htmlstring = Regex.Replace(Htmlstring, @" ([\r\n])[\s]+ " , "" , RegexOptions.IgnoreCase);
14
15 Htmlstring = Regex.Replace(Htmlstring, @" --> " , "" , RegexOptions.IgnoreCase);
16
17 Htmlstring = Regex.Replace(Htmlstring, @" <!--.* " , "" , RegexOptions.IgnoreCase);
18
19 Htmlstring = Regex.Replace(Htmlstring, @" &(quot|#34); " , " \" " , RegexOptions.IgnoreCase);
20
21 Htmlstring = Regex.Replace(Htmlstring, @" &(amp|#38); " , " & " , RegexOptions.IgnoreCase);
22
23 Htmlstring = Regex.Replace(Htmlstring, @" &(lt|#60); " , " < " , RegexOptions.IgnoreCase);
24
25 Htmlstring = Regex.Replace(Htmlstring, @" &(gt|#62); " , " > " , RegexOptions.IgnoreCase);
26
27 Htmlstring = Regex.Replace(Htmlstring, @" &(nbsp|#160); " , " " , RegexOptions.IgnoreCase);
28
29 Htmlstring = Regex.Replace(Htmlstring, @" &(iexcl|#161); " , " \xa1 " , RegexOptions.IgnoreCase);
30
31 Htmlstring = Regex.Replace(Htmlstring, @" &(cent|#162); " , " \xa2 " , RegexOptions.IgnoreCase);
32
33 Htmlstring = Regex.Replace(Htmlstring, @" &(pound|#163); " , " \xa3 " , RegexOptions.IgnoreCase);
34
35 Htmlstring = Regex.Replace(Htmlstring, @" &(copy|#169); " , " \xa9 " , RegexOptions.IgnoreCase);
36
37 Htmlstring = Regex.Replace(Htmlstring, @" &#(\d+); " , "" , RegexOptions.IgnoreCase);
38
39 Htmlstring.Replace( " < " , "" );
40
41 Htmlstring.Replace( " > " , "" );
42
43 Htmlstring.Replace( " \r\n " , "" );
44
45 Htmlstring = System.Web.HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
46
47
48 return Htmlstring;
49
50 }

转载于:https://www.cnblogs.com/Barret/archive/2011/03/24/1993677.html