C# asp.net 抓取需要登錄的網頁內容 抓取asp.net登錄驗證的網站


 private void btnASPNET_Click(object sender, EventArgs e)
        {
            Dictionary<string, string> postParams = new Dictionary<string, string>();
            postParams.Add("txtLoginId", "www.cnuunet.com");
            postParams.Add("txtPassword", "www.cnuunet.com");
            postParams.Add("btnLogin", "Sign in");
            textBox1.Text = GetAspNetCodeResponseDataFromWebSite(postParams, "http://www.cnuunet.com/login.aspx", "http://www.cnuunet.com/ProductList.aspx");
        }

        /// <summary>
        /// ASP.net頁面登錄方式 通過post密碼方式讀取網頁內容
        /// 在本頁面(login.aspx)的.cs文件內驗證用戶名和密碼。
        /// Asp.net驗證需要記住本次頁面加載的__VIEWSTATE和__EVENTVALIDATION信息,並且需要button按鈕的ID和Text信息
        /// </summary>
        /// <param name="postParams">用戶名(用戶名文本框的ID和內容)、密碼(密碼文本框的ID和內容)、summit按鈕(button按鈕的ID和Text)</param>
        /// <param name="getViewStateAndEventValidationLoginUrl">需要驗證登陸信息的url</param>
        /// <param name="getDataUrl">需要抓取數據的網頁url</param>
        /// <returns>抓取頁面返回的html信息</returns>
        private string GetAspNetCodeResponseDataFromWebSite(Dictionary<string, string> postParams, string getViewStateAndEventValidationLoginUrl, string getDataUrl)
        {
            if (postParams == null || postParams.Keys.Count!=3)
            {
                string errorMessage = "參數中需要包含如下3個信息,缺一不可。用戶名(用戶名文本框的ID和內容)、密碼(密碼文本框的ID和內容)、summit按鈕(button按鈕的ID和Text)";
                MessageBox.Show(errorMessage);
                return errorMessage ;
            }

            try
            {
                CookieContainer cookieContainer = new CookieContainer();

                ///////////////////////////////////////////////////
                // 1.打開 MyLogin.aspx 頁面,獲得 GetVeiwState & EventValidation
                ///////////////////////////////////////////////////                
                // 設置打開頁面的參數
                HttpWebRequest request = WebRequest.Create(getViewStateAndEventValidationLoginUrl) as HttpWebRequest;
                request.Method = "GET";
                request.KeepAlive = false;

                // 接收返回的頁面
                HttpWebResponse response = request.GetResponse() as HttpWebResponse;
                System.IO.Stream responseStream = response.GetResponseStream();
                System.IO.StreamReader reader = new System.IO.StreamReader(responseStream, Encoding.UTF8);
                string srcString = reader.ReadToEnd();

                // 獲取頁面的 VeiwState,分析返回的頁面,解析出__VIEWSTATE的值          
                string viewStateFlag = "id=\"__VIEWSTATE\" value=\"";
                int i = srcString.IndexOf(viewStateFlag) + viewStateFlag.Length;
                int j = srcString.IndexOf("\"", i);
                string viewState = srcString.Substring(i, j - i);

                // 獲取頁面的 EventValidation,分析返回的頁面,解析出__VIEWSTATE的值                   
                string eventValidationFlag = "id=\"__EVENTVALIDATION\" value=\"";
                i = srcString.IndexOf(eventValidationFlag) + eventValidationFlag.Length;
                j = srcString.IndexOf("\"", i);
                string eventValidation = srcString.Substring(i, j - i);

                ///////////////////////////////////////////////////
                // 2.自動填充並提交 Login.aspx 頁面,提交Login.aspx頁面,來保存Cookie
                ///////////////////////////////////////////////////

                // 將文本轉換成 URL 編碼字符串
                viewState = System.Web.HttpUtility.UrlEncode(viewState);
                eventValidation = System.Web.HttpUtility.UrlEncode(eventValidation);
                
                // 要提交的字符串數據。格式形如:user=uesr1&password=123
                string postString = "";
                foreach (KeyValuePair<string, string> de in postParams)
                {
                    //把提交按鈕中的中文字符轉換成url格式,以防中文或空格等信息
                    postString += System.Web.HttpUtility.UrlEncode(de.Key.ToString()) + "=" + System.Web.HttpUtility.UrlEncode(de.Value.ToString()) + "&";
                }
                postString += string.Format("__VIEWSTATE={0}&__EVENTVALIDATION={1}", viewState, eventValidation);
                
                // 將提交的字符串數據轉換成字節數組
                byte[] postData = Encoding.ASCII.GetBytes(postString);

                // 設置提交的相關參數
                request = WebRequest.Create(getViewStateAndEventValidationLoginUrl) as HttpWebRequest;
                request.Method = "POST";
                request.KeepAlive = false;
                request.ContentType = "application/x-www-form-urlencoded";
                request.CookieContainer = cookieContainer;
                request.ContentLength = postData.Length;

                // 提交請求數據
                System.IO.Stream outputStream = request.GetRequestStream();
                outputStream.Write(postData, 0, postData.Length);
                outputStream.Close();

                // 接收返回的頁面
                response = request.GetResponse() as HttpWebResponse;
                responseStream = response.GetResponseStream();
                reader = new System.IO.StreamReader(responseStream, Encoding.GetEncoding("GB2312"));
                srcString = reader.ReadToEnd();

                ///////////////////////////////////////////////////
                // 3.打開需要抓取數據的頁面
                ///////////////////////////////////////////////////
                // 設置打開頁面的參數
                request = WebRequest.Create(getDataUrl) as HttpWebRequest;
                request.Method = "GET";
                request.KeepAlive = false;
                request.CookieContainer = cookieContainer;

                // 接收返回的頁面
                response = request.GetResponse() as HttpWebResponse;
                responseStream = response.GetResponseStream();
                reader = new System.IO.StreamReader(responseStream, Encoding.UTF8);
                srcString = reader.ReadToEnd();
                return srcString;
                ///////////////////////////////////////////////////
                // 4.分析返回的頁面
                ///////////////////////////////////////////////////
                // ...... ......
            }
            catch (WebException we)
            {
                string msg = we.Message;
                return msg;
            }  
        }
    


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM