html字符串处理

最近我正在做一个博客系统，其中有两个页面需要截取和处理HTML字符串。现在将用到的几个函数写出来和大家交流。如果大家有什么好的修改建议或者意见，请告诉我。

 

重载的3个方法列表如下：

public static string GetContentSummary(string content, int length, bool StripHTML){}

public static void GetContentSummary(DataSet ds, string TableName, string column, int length, bool StripHTML){}

public static void GetContentSummary(DataTable dt, string column, int length, bool StripHTML){}

 

[c-sharp]  view plain copy

1. /// <summary>  
2.         /// 按字节长度截取字符串(支持截取带HTML标记的字符串)  
3.         /// </summary>  
4.         /// <param name="content">将要截取的字符串参数</param>  
5.         /// <param name="length">截取的字节长度</param>  
6.         /// <param name="StripHTML">截取的结果是否为html代码。如果为true,则去掉Html标记；否则保留html标记。</param>  
7.         /// <returns>截取的字符串</returns>  
8.         public static string GetContentSummary(string content, int length, bool StripHTML)  
9.         {  
10.             if (string.IsNullOrEmpty(content) || length == 0)  
11.                 return "";  
12.             if (StripHTML)  
13.             {  
14.                 System.Text.RegularExpressions.Regex re = new System.Text.RegularExpressions.Regex("<[^>]*>");  
15.                 content = re.Replace(content, "");  
16.                 content = content.Replace("　", "").Replace(" ", "").Replace(" ", "");  
17.                 if (content.Length <= length)  
18.                     return content;  
19.                 else  
20.                     return content.Substring(0, length) + "...";  
21.             }  
22.             else  
23.             {  
24.                 if (content.Length <= length)  
25.                     return content;  
26.   
27.                 int pos = 0, npos = 0, size = 0;  
28.                 bool firststop = false, notr = false, noli = false;  
29.                 System.Text.StringBuilder sb = new System.Text.StringBuilder();  
30.                 while (true)  
31.                 {  
32.                     if (pos >= content.Length)  
33.                         break;  
34.                     string cur = content.Substring(pos, 1);  
35.                     if (cur == "<")  
36.                     {  
37.                         string next = content.Substring(pos + 1, 3).ToLower();  
38.                         if (next.IndexOf("p") == 0 && next.IndexOf("pre") != 0)  
39.                         {  
40.                             npos = content.IndexOf(">", pos) + 1;  
41.                         }  
42.                         else if (next.IndexOf("/p") == 0 && next.IndexOf("/pr") != 0)  
43.                         {  
44.                             npos = content.IndexOf(">", pos) + 1;  
45.                             if (size < length)  
46.                                 sb.Append("<br />");  
47.                         }  
48.                         else if (next.IndexOf("br") == 0)  
49.                         {  
50.                             npos = content.IndexOf(">", pos) + 1;  
51.                             if (size < length)  
52.                                 sb.Append("<br />");  
53.                         }  
54.                         else if (next.IndexOf("img") == 0)  
55.                         {  
56.                             npos = content.IndexOf(">", pos) + 1;  
57.                             if (size < length)  
58.                             {  
59.                                 sb.Append(content.Substring(pos, npos - pos));  
60.                                 size += npos - pos + 1;  
61.                             }  
62.                         }  
63.                         else if (next.IndexOf("li") == 0 || next.IndexOf("/li") == 0)  
64.                         {  
65.                             npos = content.IndexOf(">", pos) + 1;  
66.                             if (size < length)  
67.                             {  
68.                                 sb.Append(content.Substring(pos, npos - pos));  
69.                             }  
70.                             else  
71.                             {  
72.                                 if (!noli && next.IndexOf("/li") == 0)  
73.                                 {  
74.                                     sb.Append(content.Substring(pos, npos - pos));  
75.                                     noli = true;  
76.                                 }  
77.                             }  
78.                         }  
79.                         else if (next.IndexOf("tr") == 0 || next.IndexOf("/tr") == 0)  
80.                         {  
81.                             npos = content.IndexOf(">", pos) + 1;  
82.                             if (size < length)  
83.                             {  
84.                                 sb.Append(content.Substring(pos, npos - pos));  
85.                             }  
86.                             else  
87.                             {  
88.                                 if (!notr && next.IndexOf("/tr") == 0)  
89.                                 {  
90.                                     sb.Append(content.Substring(pos, npos - pos));  
91.                                     notr = true;  
92.                                 }  
93.                             }  
94.                         }  
95.                         else if (next.IndexOf("td") == 0 || next.IndexOf("/td") == 0)  
96.                         {  
97.                             npos = content.IndexOf(">", pos) + 1;  
98.                             if (size < length)  
99.                             {  
100.                                 sb.Append(content.Substring(pos, npos - pos));  
101.                             }  
102.                             else  
103.                             {  
104.                                 if (!notr)  
105.                                 {  
106.                                     sb.Append(content.Substring(pos, npos - pos));  
107.                                 }  
108.                             }  
109.                         }  
110.                         else  
111.                         {  
112.                             npos = content.IndexOf(">", pos) + 1;  
113.                             sb.Append(content.Substring(pos, npos - pos));  
114.                         }  
115.                         if (npos <= pos)  
116.                             npos = pos + 1;  
117.                         pos = npos;  
118.                     }  
119.                     else  
120.                     {  
121.                         if (size < length)  
122.                         {  
123.                             sb.Append(cur);  
124.                             size++;  
125.                         }  
126.                         else  
127.                         {  
128.                             if (!firststop)  
129.                             {  
130.                                 sb.Append("...");  
131.                                 firststop = true;  
132.                             }  
133.                         }  
134.                         pos++;  
135.                     }  
136.   
137.                 }  
138.                 return sb.ToString();  
139.             }  
140.         }  
141.   
142.         /// <summary>  
143.         /// 按字节长度截取DataSet对象中的字符串(支持截取带HTML标记的字符串)  
144.         /// </summary>  
145.         /// <param name="ds">DataSet对象</param>  
146.         /// <param name="TableName">字符串所在的数据表的名称</param>  
147.         /// <param name="column">字符串所在的数据列的名称</param>  
148.         /// <param name="length">截取的字节长度</param>  
149.         /// <param name="StripHTML">截取的结果是否为html代码。如果为true,则去掉Html标记；否则保留html标记。</param>  
150.         /// <return>因为需要更改的DataSet对象已经通过参数传递过来了，所以不需要返回值。</return>  
151.         public static void GetContentSummary(DataSet ds, string TableName, string column, int length, bool StripHTML)  
152.         {  
153.             string content = "";  
154.             DataTable dt = ds.Tables[TableName];  
155.             int ColumnCount = dt.Rows.Count;  
156.   
157.             for (int i = 0; i < ColumnCount; i++)  
158.             {  
159.                 content = dt.Rows[i][column].ToString();  
160.                 dt.Rows[i][column] = HTML.FormatString.GetContentSummary(content, length, true);  
161.             }  
162.         }  
163.   
164.         /// <summary>  
165.         /// 按字节长度截取DataTable对象中的字符串(支持截取带HTML标记的字符串)  
166.         /// </summary>  
167.         /// <param name="dt">DataTable对象</param>  
168.         /// <param name="column">字符串所在的列的名称</param>  
169.         /// <param name="length">截取的字节长度</param>  
170.         /// <param name="StripHTML">截取的结果是否为html代码。如果为true,则去掉Html标记；否则保留html标记。</param>  
171.         /// <return>因为需要更改的DataTable对象已经通过参数传递过来了，所以不需要返回值。</return>  
172.         public static void GetContentSummary(DataTable dt, string column, int length, bool StripHTML)  
173.         {  
174.             string content = "";  
175.             int ColumnCount = dt.Rows.Count;  
176.   
177.             for (int i = 0; i < ColumnCount; i++)  
178.             {  
179.                 content = dt.Rows[i][column].ToString();  
180.                 dt.Rows[i][column] = HTML.FormatString.GetContentSummary(content, length, true);  
181.             }  
182.         }  

原文章：http://blog.csdn.net/byygyy/article/details/5531921?reload