当前文件路径：NetCMSv15/NetCMS.Content/Collect/Utility.cs 
1
//======================================================
2//== (c)2008 aspxcms inc by NeTCMS v1.0 ==
3//== Forum:bbs.aspxcms.com ==
4//== Website:www.aspxcms.com ==
5//======================================================
6using System;
7using System.Collections;
8using System.Collections.Generic;
9using System.Text;
10using System.Text.RegularExpressions;
11using System.Net;
12using System.IO;
13
14namespace NetCMS.Content.Collect
15
...{
16
public class Utility
17
...{
18 /**//// <summary>
19 /// 取得网页的内容
20 /// </summary>
21 /// <param name="sUrl">url地址</param>
22 /// <param name="sEncode">编码名称</param>
23 /// <param name="sDocument">返回的网页内容或者是异常</param>
24
/// <returns>有异常返回false</returns>
25 public static string GetPageContent(Uri Url, string sEncode)
26 ...{
27 try
28 ...{
29
30 Encoding encoding = System.Text.Encoding.GetEncoding(sEncode);
31 return GetPageContent(Url, encoding);
32 }
33 catch (WebException ex)
34 ...{
35 throw ex;
36 }
37 catch (Exception ex)
38 ...{
39 throw ex;
40 }
41 }
42 /**//// <summary>
43 /// 取得网页的内容
44 /// </summary>
45 /// <param name="sUrl">url地址</param>
46 /// <param name="encoding">编码方式</param>
47 /// <param name="sDocument">返回的网页内容或者是异常</param>
48 /// <returns>有异常返回false</returns>
49 public static string GetPageContent(Uri Url, Encoding encoding)
50 ...{
51 WebClient webclient = new WebClient();
52 try
53 ...{
54
55 webclient.Encoding = encoding;
56 return webclient.DownloadString(Url);
57 }
58 catch (WebException ex)
59 ...{
60 throw ex;
61 }
62 catch (Exception ex)
63 ...{
64 throw ex;
65 }
66 finally
67 ...{
68 webclient.Dispose();
69 }
70 }
71 /**//// <summary>
72 /// 处理URL地址，当BranchUrl为一个全名的URL时则返回本身，否则恰当的衔接到BaseUrl后面
73 /// </summary>
74 /// <param name="BaseUrl">完整的URL</param>
75 /// <param name="BranchUrl">分支URL</param>
76 /// <returns></returns>
77 public static string StickUrl(string BaseUrl, string BranchUrl)
78 ...{
79 if (Regex.Match(BranchUrl, @"^(http|https|ftp|rtsp|mms)://", RegexOptions.IgnoreCase | RegexOptions.Compiled).Success)
80 ...{
81 return BranchUrl;
82 }
83 else
84 ...{
85 BaseUrl = BaseUrl.Replace("\\", "/");
86 BranchUrl = BranchUrl.Replace("\\", "/");
87 //2007-09-27 ken暂时修改
88 if (NetCMS.Common.Input.GetSubString(BranchUrl, 1).ToString() == "/")
89 ...{
90 return GetLastUrl(BaseUrl, BranchUrl);
91 }
92 //--------------------------
93 BranchUrl = BranchUrl.TrimStart('/');
94 if (BranchUrl.IndexOf("../") != 0)
95 ...{
96 return UrlPlus(BaseUrl, BranchUrl);
97 }
98 else
99 ...{
100 if (Regex.Match(BaseUrl, @"/$", RegexOptions.Compiled).Success)
101 ...{
102 BaseUrl = BaseUrl.TrimEnd('/');
103 }
104 else if (Regex.Match(BaseUrl, @"/[^\./]+\.[^/]+$", RegexOptions.Compiled).Success)
105 ...{
106 BaseUrl = Regex.Replace(BaseUrl, @"/[^\./]+\.[^/]+$", "", RegexOptions.Compiled);
107 }
108 while (BranchUrl.IndexOf("../") >= 0)
109 ...{
110 BranchUrl = Regex.Replace(BranchUrl, @"^\.\./", "", RegexOptions.Compiled);
111 BaseUrl = Regex.Replace(BaseUrl, @"/[^/]*$", "", RegexOptions.Compiled);
112 }
113 return BaseUrl + "/" + BranchUrl;
114 }
115 }
116 }
117 //--------------------------------
118 private static string GetLastUrl(string BaseUrl, string BranchUrl)
119 ...{
120 BranchUrl = BranchUrl.TrimStart('/');
121 string Star_url = "";
122 string End_Url = BaseUrl;
123 if (BaseUrl.IndexOf("//") > 0)
124 ...{
125 BaseUrl = BaseUrl.Replace("//", "|");
126 string[] Url_Arr = BaseUrl.Split('|');
127 Star_url = Url_Arr[0].ToString();
128 End_Url = Url_Arr[1].ToString();
129 }
130 if (End_Url.IndexOf("/") > 0)
131 ...{
132 string[] End_Arr = End_Url.Split('/');
133 End_Url = End_Arr[0].ToString();
134 if (Star_url != string.Empty)
135 ...{
136 return Star_url + "//" + End_Url + "/" + BranchUrl;
137 }
138 else
139 ...{
140 return End_Url + "/" + BranchUrl;
141 }
142 }
143 else
144 ...{
145 if (Star_url != string.Empty)
146 ...{
147 return Star_url + "//" + End_Url + "/" + BranchUrl;
148 }
149 else
150 ...{
151 return End_Url + "/" + BranchUrl;
152 }
153 }
154 }
155
156
157
158 private static string UrlPlus(string front, string tail)
159 ...{
160 if (Regex.Match(front, "(http|https|ftp|rtsp|mms)://[^/]+$", RegexOptions.Compiled | RegexOptions.IgnoreCase).Success)
161 ...{
162 return front + "/" + tail;
163 }
164 else if (Regex.Match(front, "(http|https|ftp|rtsp|mms)://[^/]+/$", RegexOptions.Compiled | RegexOptions.IgnoreCase).Success)
165 ...{
166 return front + tail;
167 }
168 else if (Regex.Match(front, "(http|https|ftp|rtsp|mms)://.+/$", RegexOptions.Compiled | RegexOptions.IgnoreCase).Success)
169 ...{
170 return front + tail;
171 }
172 else if (Regex.Match(front, @"/[^/\.]+$", RegexOptions.Compiled | RegexOptions.IgnoreCase).Success)
173 ...{
174 return front + "/" + tail;
175 }
176 else if (Regex.Match(front, @"/[^/\.]+\.[^/]+$", RegexOptions.Compiled | RegexOptions.IgnoreCase).Success)
177 ...{
178 return Regex.Replace(front, @"/[^/\.]+\.[^/]+$", "", RegexOptions.IgnoreCase | RegexOptions.Compiled) + "/" + tail;
179 }
180 else
181 ...{
182 return front + "/" + tail;
183 }
184 }
185 /**//// <summary>
186 /// 获取一个目标的匹配结果
187 /// </summary>
188 /// <param name="input">要匹配的字符串</param>
189 /// <param name="pattern"></param>
190 /// <param name="find"></param>
191 /// <returns></returns>
192 public static Match GetMatch(string input, string pattern, string find)
193 ...{
194 string _pattn = Regex.Escape(pattern);
195 _pattn = _pattn.Replace(@"\[变量]", @"[\s\S]*?");
196 _pattn = Regex.Replace(_pattn, @"((\\r\\n)|(\\ ))+", @"\s*", RegexOptions.Compiled);
197 if (Regex.Match(pattern.TrimEnd(), Regex.Escape(find) + "$", RegexOptions.Compiled).Success)
198 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[\s\S]+)");
199 else
200 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[\s\S]+?)");
201 Regex r = new Regex(_pattn, RegexOptions.IgnoreCase | RegexOptions.Compiled);
202 Match m = r.Match(input);
203 return m;
204 }
205 /**//// <summary>
206 /// 按严格的匹配方式获取一个目标的匹配结果
207 /// </summary>
208 /// <param name="input"></param>
209 /// <param name="pattern"></param>
210 /// <param name="find"></param>
211 /// <returns></returns>
212 public static Match GetMatchRigid(string input, string pattern, string find)
213 ...{
214 string _pattn = Regex.Escape(pattern);
215 _pattn = _pattn.Replace(@"\[变量]", @"[\s\S]*?");
216 if (Regex.Match(pattern.TrimEnd(), Regex.Escape(find) + "$", RegexOptions.Compiled).Success)
217 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[\s\S]+)");
218 else
219 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[\s\S]+?)");
220 Regex r = new Regex(_pattn, RegexOptions.IgnoreCase | RegexOptions.Compiled);
221 Match m = r.Match(input);
222 return m;
223 }
224 /**//// <summary>
225 /// 匹配超级链接地址
226 /// </summary>
227 /// <param name="input"></param>
228 /// <param name="pattern"></param>
229 /// <param name="find"></param>
230 /// <returns></returns>
231 public static Match GetMatchUrl(string input, string pattern, string find)
232 ...{
233 string _pattn = Regex.Escape(pattern);
234 _pattn = _pattn.Replace(@"\[变量]", @"[\s\S]*?");
235 if (Regex.Match(pattern.TrimEnd(), Regex.Escape(find) + "$", RegexOptions.Compiled).Success)
236 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[^'""\ >]+)");
237 else
238 _pattn = _pattn.Replace(@"\" + find, @"(?<TARGET>[^'""\ >]+?)");
239 Regex r = new Regex(_pattn, RegexOptions.IgnoreCase | RegexOptions.Compiled);
240 Match m = r.Match(input);
241 return m;
242 }
243 }
244 /**//*
245 // The RequestState class passes data across async calls.
246 public class RequestState
247 {
248 const int BufferSize = 1024;
249 public StringBuilder RequestData;
250 public byte[] BufferRead;
251 public WebRequest Request;
252 public Stream ResponseStream;
253 // Create Decoder for appropriate enconding type.
254 public Decoder StreamDecode = Encoding.UTF8.GetDecoder();
255
256 public RequestState()
257 {
258 BufferRead = new byte[BufferSize];
259 RequestData = new StringBuilder(String.Empty);
260 Request = null;
261 ResponseStream = null;
262 }
263 }
264
