字符串 html之间的转换

 1   /**/
 2         /// <summary>
 3         ///将字符串格式化为HTML
 4         /// </summary>
 5         /// <param name="normalStr">所要格式化的字符串</param>
 6         /// <param name="identiftyURL">是否自动识别URL,识别出来的URL将会自动加上超级链接标签</param>
 7         /// <returns>返回格式化后的HTML代码</returns>
 8         public static string FormatToHTML(string normalStr, bool identiftyURL)
 9         {
10             StringBuilder html = new StringBuilder(normalStr);
11 
12             html.Append(' ');
13             html.Replace("&amp;", "&");
14             html.Replace("&nbsp;", " ");
15             html.Replace("&lt;", "<");
16             html.Replace("&gt;", ">");
17             html.Replace("&quot;", "\"");
18 
19             if (identiftyURL)
20             {
21                 Regex linkRegex = new Regex("(http://|www)[\\S]{5,}(?=&nbsp;|\r\n)");
22 
23                 MatchCollection regMathes = linkRegex.Matches(html.ToString());
24 
25                 int add = 0;
26 
27                 foreach (Match match in regMathes)
28                 {
29                     string head = string.Format("<a href=\"{0}\">", match.Value[0] == 'h' ? match.Value : "http://" + match.Value);
30 
31                     html.Insert(match.Index + add, head);
32                     add += head.Length;
33 
34                     html.Insert(match.Index + match.Length + add, "</a>");
35                     add += 3;
36                 }
37             }
38 
39             html.Replace("\r\n", "<br />");
40 
41             return html.ToString();
42         }
43 
44 
45 
46         #region 过滤掉 html代码
47         private static string StripHTML(string strHtml)
48         {
49             #region
50             string[] aryReg ={ 
51             @"<script[^>]*?>.*?</script>",  
52             @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", 
53             @"([\r\n])[\s]+", 
54             @"&(quot|#34);", 
55             @"&(amp|#38);", 
56             @"&(lt|#60);", 
57             @"&(gt|#62);", 
58             @"&(nbsp|#160);", 
59             @"&(iexcl|#161);", 
60             @"&(cent|#162);", 
61             @"&(pound|#163);", 
62             @"&(copy|#169);", 
63             @"&#(\d+);", 
64             @"-->", 
65             @"<!--.*\n" 
66             };
67 
68             string[] aryRep = { 
69             "", 
70             "", 
71             "", 
72             "\"", 
73             "&", 
74             "<", 
75             ">", 
76             " ", 
77             "\xa1",//chr(161), 
78             "\xa2",//chr(162), 
79             "\xa3",//chr(163), 
80             "\xa9",//chr(169), 
81             "", 
82             "\r\n", 
83             "" 
84             };
85             #endregion
86             string newReg = aryReg[0];
87             string strOutput = strHtml;
88             for (int i = 0; i < aryReg.Length; i++)
89             {
90                 System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i], System.Text.RegularExpressions.RegexOptions.IgnoreCase);
91                 strOutput = regex.Replace(strOutput, aryRep[i]);
92             }
93             strOutput.Replace("<", "");
94             strOutput.Replace(">", "");
95             strOutput.Replace("\r\n", "");
96             return strOutput;
97         }
98         #endregion

 

posted @ 2013-05-14 13:50  Ganler1988  阅读(486)  评论(0编辑  收藏  举报