c#自动登录网页，浏览页面

15

2012
07

需求：客户的数据同时存在在另外一个不可控的系统中，需要和当前系统同步。

思路：自动登录另外一个系统，然后抓取数据，同步到本系统中。

技术点：模拟用户登录；保存登录状态；抓取数据

1   /// <summary>
2         /// visit the target url
3         /// </summary>
4         /// <param name="targetURL"></param>
5         /// <param name="cc">this is for keeping cookies and sessions</param>
6         /// <param name="param">this is the data need post inside form</param>
7         /// <returns>html page</returns>
8         public static string PostAndGetHTML(string targetURL,CookieContainer cc,Hashtable param)
9         {
10             //prepare the submit data
11             string formData = "";
12             foreach (DictionaryEntry de in param)
13             {
14                 formData += de.Key.ToString() + "=" + de.Value.ToString() + "&";
15             }
16             if (formData.Length > 0)
17                 formData = formData.Substring(0, formData.Length - 1); //remove last '&'
18
19             ASCIIEncoding encoding = new ASCIIEncoding();
20             byte[] data = encoding.GetBytes(formData);
21
22             HttpWebRequest request = (HttpWebRequest)WebRequest.Create(targetURL);
23             request.Method = "POST";    //post
24             request.ContentType = "application/x-www-form-urlencoded";
25             request.ContentLength = data.Length;
26             request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 2.0.1124)";
27
28             Stream newStream = request.GetRequestStream();
29             newStream.Write(data, 0, data.Length);
30
31             newStream.Close();
32
33             request.CookieContainer = cc;
34             HttpWebResponse response = (HttpWebResponse)request.GetResponse();
35             cc.Add(response.Cookies);
36             Stream stream = response.GetResponseStream();
37             string result = new StreamReader(stream, System.Text.Encoding.Default).ReadToEnd();
38             return result;
39         }
40
41         public static DataTable ConvertToDT(DataTable dt, string tableHTML)
42         {
43
44             int lastTD = tableHTML.ToLower().LastIndexOf("</td>");
45             int firstRow = tableHTML.ToLower().IndexOf("<tr") + 3;//after ""<tr
46             int index = tableHTML.ToLower().IndexOf("<tr", firstRow) + 3;//after ""<tr
47             while (index < lastTD)
48             {
49                 DataRow dr = dt.NewRow();
50                 for (int i = 0; i < dt.Columns.Count; i++)
51                 {
52                     string value = "";
53                     int startTD = tableHTML.ToLower().IndexOf("<td", index) + 3;//after "<td"
54                     int endTD = tableHTML.ToLower().IndexOf("</td>", startTD);
55                     if (endTD < 0)
56                         break;
57                     string tdStr = tableHTML.Substring(startTD, endTD - startTD);
58
59                     //remove <> and others
60                     tdStr = tdStr.Replace(" ", "").Replace("\t", "").Replace("\r", "");
61                     string[] v = tdStr.Split('<', '>');
62                     for (int j = 0; j < v.Length; j++)
63                     {
64                         j++;
65                         if (v[j].Trim() != "")
66                         {
67                             value = v[j].Trim();
68                             break;
69                         }
70                     }
71                     //
72                     dr[i] = value;
73                     index = endTD;
74                 }
75                 dt.Rows.Add(dr);
76
77             }
78             return dt;
79         }

这一个是调用的例子：先登录，在查询。实际中这个逻辑可能有很多步骤

1             CookieContainer cc = new CookieContainer();//this is for keep the Session and Cookie
2             Hashtable param = new Hashtable();//this is for keep post data.
3
4             string urlLogin = "http://demo.server//login.asp";
5             //do find the elementId that needed. check the source of login page can get this information
6             param.Add("User", "xxx");
7             param.Add("Password", "xxxx");
8             string result =GrabHelper.PostAndGetHTML(urlLogin, cc, param);
9             //check result, whether login success
10
11             //if login success, goto the target url, and input some value.
12             string url2 = " http://demo.server/query.asp?id=1";// need change. special logic
13             param.Clear();
14             //param.Add("SearchAreaId","JobId")
15             result = GrabHelper.PostAndGetHTML(url2, cc, new Hashtable());
16             //ConvertToDT the html or do something others

注：对于有验证码登录系统的无效。（如果该系统的验证码放到cookie中存储的例外，这个容易破解）

Tags: 登录网页