在C#中,能夠使用HttpWebRequest進行相關的模擬登錄,登錄後進行相關的操做,好比抓取數據,頁面分析,製做相關登錄助手等等。web
先說下流程c#
1.使用httpwebrequest先進入你要登陸的網站,獲取cookie服務器
2.使用第一步獲取的cookie到驗證碼的網頁將驗證碼下載下來。cookie
3.使用Post數據 發送至網站。若是有cookie則繼續保存。app
4.使用第三步的cookie登錄相關網頁操做。工具
獲取相關數據能夠使用抓包工具進行抓取,如httpwatch。(網上下載的好多都有病毒,下載的時候注意點)post
1。網站
- public static ArrayList GetHtmlData(string postUrl, CookieContainer cookie)
- {
- HttpWebRequest request;
- HttpWebResponse response;
- ArrayList list = new ArrayList();
- request = WebRequest.Create(postUrl) as HttpWebRequest;
- request.Method = "GET";
- request.UserAgent = "Mozilla/4.0";
- request.CookieContainer = cookie;
- request.KeepAlive = true;
-
- request.CookieContainer = cookie;
- try
- {
-
- using (response = (HttpWebResponse)request.GetResponse())
- {
- using (StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.Default))
- {
- cookie.Add(response.Cookies);
-
- list.Add(cookie);
- list.Add(reader.ReadToEnd());
- list.Add(Guid.NewGuid().ToString());
- }
- }
- }
- catch (WebException ex)
- {
- list.Clear();
- list.Add("發生異常/n/r");
- WebResponse wr = ex.Response;
- using (Stream st = wr.GetResponseStream())
- {
- using (StreamReader sr = new StreamReader(st, System.Text.Encoding.Default))
- {
- list.Add(sr.ReadToEnd());
- }
- }
- }
- catch (Exception ex)
- {
- list.Clear();
- list.Add("5");
- list.Add("發生異常:" + ex.Message);
- }
- return list;
- }
2.下載驗證碼,保存在本地。ui
-
-
-
-
-
- public static bool DowloadCheckImg(string Url, CookieContainer cookCon, string savePath)
- {
- bool bol = true;
- HttpWebRequest webRequest = (HttpWebRequest)WebRequest.Create(Url);
-
- webRequest.AllowWriteStreamBuffering = true;
- webRequest.Credentials = System.Net.CredentialCache.DefaultCredentials;
- webRequest.MaximumResponseHeadersLength = -1;
- webRequest.Accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, */*";
- webRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 1.1.4322)";
- webRequest.ContentType = "application/x-www-form-urlencoded";
- webRequest.Method = "GET";
- webRequest.Headers.Add("Accept-Language", "zh-cn");
- webRequest.Headers.Add("Accept-Encoding", "gzip,deflate");
- webRequest.KeepAlive = true;
- webRequest.CookieContainer = cookCon;
- try
- {
-
- using (HttpWebResponse webResponse = (HttpWebResponse)webRequest.GetResponse())
- {
- using (Stream sream = webResponse.GetResponseStream())
- {
- List<byte> list = new List<byte>();
- while (true)
- {
- int data = sream.ReadByte();
- if (data == -1)
- break;
- list.Add((byte)data);
- }
- File.WriteAllBytes(savePath, list.ToArray());
- }
- }
- }
- catch (WebException ex)
- {
- bol = false;
- }
- catch (Exception ex)
- {
- bol = false;
- }
- return bol;
- }
3。發送post數據url
- public static ArrayList PostData(string postData, string postUrl, CookieContainer cookie)
- {
- ArrayList list = new ArrayList();
- HttpWebRequest request;
- HttpWebResponse response;
- ASCIIEncoding encoding = new ASCIIEncoding();
- request = WebRequest.Create(postUrl) as HttpWebRequest;
- byte[] b = encoding.GetBytes(postData);
- request.UserAgent = "Mozilla/4.0";
- request.Method = "POST";
- request.CookieContainer = cookie;
- request.ContentLength = b.Length;
- using (Stream stream = request.GetRequestStream())
- {
- stream.Write(b, 0, b.Length);
- }
-
- try
- {
-
- using (response = request.GetResponse() as HttpWebResponse)
- {
- using (StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8))
- {
- if (response.Cookies.Count > 0)
- cookie.Add(response.Cookies);
- list.Add(cookie);
- list.Add(reader.ReadToEnd());
- }
- }
- }
- catch (WebException wex)
- {
- WebResponse wr = wex.Response;
- using (Stream st = wr.GetResponseStream())
- {
- using (StreamReader sr = new StreamReader(st, System.Text.Encoding.Default))
- {
- list.Add(sr.ReadToEnd());
- }
- }
- }
- catch (Exception ex)
- {
- list.Add("發生異常/n/r"+ex.Message);
- }
- return list;
- }
4。就是第三步請求的連接地址換一個就好了
好了
以上核心代碼已經貼出了
具體實現須要靠大家按照大家本身的邏輯
還有一些header能不寫就不寫,由於我2天前一直在獲取返回response這地方報500錯誤。
找了N多代碼,看了N多資料都不能夠。最後將一些header註釋掉就能夠了,真鬱悶。