政务公开网站开发,江门专业网站建设公司,山西省建设工程信息网,网站备案手机号网页自动登录和提交POST信息的核心就是分析网页的源代码#xff08;HTML#xff09;#xff0c;在C#中#xff0c;可以用来提取网页HTML的组件比较多#xff0c;常用的用WebBrowser、WebClient、HttpWebRequest这三个。 以下就分别用这三种方法来实现#xff1a;1、WebBr…网页自动登录和提交POST信息的核心就是分析网页的源代码HTML在C#中可以用来提取网页HTML的组件比较多常用的用WebBrowser、WebClient、HttpWebRequest这三个。 以下就分别用这三种方法来实现1、WebBrowser是个迷你浏览器其特点是Post时不用关心Cookie、内置JS等问题WebBrowser是VS2005新提供的组件其实就是封装了IE接口实现POST功能一般在webBrowser的DocumentCompleted中分析HtmlDocument 来实现代码如下 HtmlElement ClickBtn null; if (e.Url.ToString().ToLower().IndexOf(http://sandou.cnblogs.com/) 0) //登陆页面 { HtmlDocument doc webBrowser1.Document; for (int i 0; i doc.All.Count ; i) { if (doc.All[i].TagName.ToUpper().Equals(INPUT)) { switch (doc.All[i].Name) { case userCtl: doc.All[i].InnerText user01; break; case passCt1: doc.All[i].InnerText mypass; break; case B1: ClickBtn doc.All[i]; //提交按钮 break; } } } ClickBtn.InvokeMember(Click); //执行按扭操作 } 2、WebClient封装了HTTP的一些类操作简单相较于webBrowser特点是可以自设代理缺点是对COOKIE的控制WebClient的运行全在后台并且提供了异步操作的能力这样很方便并发多个任务然后等待结果的返回再逐个处理。多任务异步调用的代码如下 private void StartLoop(int ProxyNum) { WebClient [] wcArray new WebClient[ProxyNum]; //初始化 for (int idArray 0; idArray ProxyNum;idArray) { wcArray[idArray] new WebClient(); wcArray[idArray].OpenReadCompleted new OpenReadCompletedEventHandler(Pic_OpenReadCompleted2); wcArray[idArray].UploadDataCompleted new UploadDataCompletedEventHandler(Pic_UploadDataCompleted2); try { wcArray[idArray].Proxy new WebProxy(proxy[1], port); wcArray[idArray].OpenReadAsync(new Uri(http://sandou.cnblogs.com/)); //打开WEB; proxy null; } catch { } } } private void Pic_OpenReadCompleted2(object sender, OpenReadCompletedEventArgs e) { if (e.Error null) { string textData new StreamReader(e.Result, Encoding.Default).ReadToEnd(); //取返回信息 .. String cookie ((WebClient)sender).ResponseHeaders[Set-Cookie]; ((WebClient)sender).Headers.Add(Content-Type, application/x-www-form-urlencoded); ((WebClient)sender).Headers.Add(Accept-Language, zh-cn); ((WebClient)sender).Headers.Add(Cookie, cookie); string postData byte[] byteArray Encoding.UTF8.GetBytes(postData); // 转化成二进制数组 ((WebClient)sender).UploadDataAsync(new Uri(http://sandou.cnblogs.com/), POST, byteArray); } } private void Pic_UploadDataCompleted2(object sender, UploadDataCompletedEventArgs e) { if (e.Error null) { string returnMessage Encoding.Default.GetString(e.Result); } } 3、HttpWebRequest较为低层能实现的功能较多Cookie操作也很简单: private bool PostWebRequest() { CookieContainer cc new CookieContainer(); string pos tData user strUser pass strPsd; byte[] byteArray Encoding.UTF8.GetBytes(postData); // 转化 HttpWebRequest webRequest2 (HttpWebRequest)WebRequest.Create(new Uri(http://sandou.cnblogs.com/)); webRequest2.CookieContainer cc; webRequest2.Method POST; webRequest2.ContentType application/x-www-form-urlencoded; webRequest2.ContentLength byteArray.Length; Stream newStream webRequest2.GetRequestStream(); // Send the data. newStream.Write(byteArray, 0, byteArray.Length); //写入参数 newStream.Close(); HttpWebResponse response2 (HttpWebResponse)webRequest2.GetResponse(); StreamReader sr2new StreamReader(response2.GetResponseStream(), Encoding.Default); string text2 sr2.ReadToEnd(); } HttpWebRequest 实现 这个是从网上COPY 的我以前用相关的代码登录到WWW.ASP.NET上并且成功post可惜代码不知道放什么地方了。 HttpWebRequest自动登录网站并获取网站内容不包含验证码的网站 可以使用 Visual Sniffer百度搜索 来捕捉提交的数据信息1. 访问你需要站外提交的页面比如 CSDN 登陆页 http://www.csdn.net/member/UserLogin.aspx2. 填写好需要的资料比如用户名和密码3. 打开 Visual Sniffer, 点“开始拦截”4. 在访问的页面中提交。5. 等提交成功之后在 Visual Sniffer 中“停止拦截”6. 在 Visual Sniffer 的左侧栏的加号中依次点开右边是它拦截到的内容 POST http://www.csdn.net/member/UserLogin.aspx HTTP/1.0Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-shockwave-flash, */*Referer: http://www.csdn.net/member/UserLogin.aspxAccept-Language: zh-cnContent-Type: application/x-www-form-urlencodedUA-CPU: x86Pragma: no-cacheUser-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1)Host: www.csdn.netContent-Length: 355Proxy-Connection: Keep-AliveCookie: ASPSESSIONIDAAAATBQCFMEGGCKDBKHAMMCGKPFDMBFG; ASP.NET_SessionIdlusprmnom05lr445tmteaf55; userid699879 __EVENTTARGET__EVENTARGUMENT__VIEWSTATEdDwtMTcwMzgxNjQ2Mjs7bDxDU0ROVXNlckxvZ2luOmNiX1NhdmVTdGF0ZTtDU0ROVXNlckxvZ2luOkltYWdlX0xvZ2luOz4%2Btu1q2wmRZoAJTi9L73w1zBleylY%3DCSDNUserLogin%3Atb_UserNametestusernameCSDNUserLogin%3Atb_PasswordtestpasswordCSDNUserLogin%3Atb_ExPwd9232fromCSDNUserLogin%3AImage_Login.x36CSDNUserLogin%3AImage_Login.y6GET http://www.csdn.net/mycustompage.htm?aspxerrorpath/member/UserLogin.aspx HTTP/1.0Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-shockwave-flash, */*Referer: http://www.csdn.net/member/UserLogin.aspxAccept-Language: zh-cnUA-CPU: x86Pragma: no-cacheUser-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1)Host: www.csdn.netProxy-Connection: Keep-AliveCookie: ASPSESSIONIDAAAATBQCFMEGGCKDBKHAMMCGKPFDMBFG; ASP.NET_SessionIdlusprmnom05lr445tmteaf55; userid699879以上为拦截内容其中提交数据的参数部分程序中的strArgs如__EVENTTARGET__EVENTARGUMENT__VIEWSTATEdDwtMTcwMzgxNjQ2Mjs7bDxDU0ROVXNlckxvZ2luOmNiX1NhdmVTdGF0ZTtDU0ROVXNlckxvZ2luOkltYWdlX0xvZ2luOz4%2Btu1q2wmRZoAJTi9L73w1zBleylY%3DCSDNUserLogin%3Atb_UserNametestusernameCSDNUserLogin%3Atb_PasswordtestpasswordCSDNUserLogin%3Atb_ExPwd9232 protected static string cookieHeader; private void Page_Load(object sender, System.EventArgs e) { string strReContent string.Empty; //登录 strReContent PostLogin(http://www.mystand.com.cn/login/submit.jsp提交的页面,提交的参数useridhgj0000password06045369,引用地址http://www.mystand.com.cn/); //asp.net登录传递的参数需注意 //strReContent PostLogin(http://www.mystand.com.cn/login.aspx,__VIEWSTATEdDwtNjkzMjUyNDczO3Q8O2w8aTwzPjs%2BO2w8dDxwPHA8bDxUZXh0Oz47bDxcZTs%2BPjs%2BOzs%2BOz4%2BOz6aX2dtqkJTK%2BKbNPsjd7Op%2Fl26Iw%3D%3DtxtUserNamehxftxtPasswordhxf0000btnEnter%E7%99%BB%E5%BD%95,http://www.mystand.com.cn/login.aspx); //获取页面 strReContent GetPage(http://www.mystand.com.cn/company/getdata.jsp?code,引用地址http://www.mystand.com.cn/); //strReContent GetPage(http://www.mystand.com.cn/Modules/index.aspx,http://www.mystand.com.cn/login.aspx); //可以对获得的内容进行处理strReContent } /** summary /// 功能描述模拟登录页面提交登录数据进行登录并记录Header中的cookie /// /summary /// param namestrURL登录数据提交的页面地址/param /// param namestrArgs用户登录数据/param /// param namestrReferer引用地址/param /// returns可以返回页面内容或不返回/returns public static string PostLogin(string strURL,string strArgs,string strReferer) { string strResult ; HttpWebRequest myHttpWebRequest (HttpWebRequest)WebRequest.Create(strURL); myHttpWebRequest.AllowAutoRedirect true; myHttpWebRequest.KeepAlive true; myHttpWebRequest.Accept image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/msword, application/x-shockwave-flash, */*; myHttpWebRequest.Referer strReferer; myHttpWebRequest.UserAgent Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 2.0.50727); myHttpWebRequest.ContentType application/x-www-form-urlencoded; myHttpWebRequest.Method POST; CookieCollection myCookies null; CookieContainer myCookieContainer new CookieContainer(); myHttpWebRequest.CookieContainer myCookieContainer; Stream MyRequestStrearm myHttpWebRequest.GetRequestStream(); StreamWriter MyStreamWriter new StreamWriter(MyRequestStrearm,Encoding.ASCII); //把数据写入HttpWebRequest的Request流 MyStreamWriter.Write(strArgs); //关闭打开对象 MyStreamWriter.Close(); MyRequestStrearm.Close(); HttpWebResponse response null; System.IO.StreamReader sr null; response (HttpWebResponse)myHttpWebRequest.GetResponse(); cookieHeader myHttpWebRequest.CookieContainer.GetCookieHeader(new Uri(strURL)); HttpContext.Current.Application.Lock(); HttpContext.Current.Application[cookieHeader] cookieHeader; HttpContext.Current.Application.UnLock(); myCookies response.Cookies; sr new System.IO.StreamReader(response.GetResponseStream(),Encoding.GetEncoding(gb2312)); // //utf-8 strResult sr.ReadToEnd(); return strResult; } /** summary /// 功能描述在PostLogin成功登录后记录下Headers中的cookie然后获取此网站上其他页面的内容 /// /summary /// param namestrURL获取网站的某页面的地址/param /// param namestrReferer引用的地址/param /// returns返回页面内容/returns public static string GetPage(string strURL,string strReferer) { string strResult ; HttpWebRequest myHttpWebRequest (HttpWebRequest)WebRequest.Create(strURL); myHttpWebRequest.ContentType text/html; myHttpWebRequest.Method GET; myHttpWebRequest.Referer strReferer; myHttpWebRequest.Headers.Add(cookie: cookieHeader); HttpWebResponse response null; System.IO.StreamReader sr null; response (HttpWebResponse)myHttpWebRequest.GetResponse(); sr new System.IO.StreamReader(response.GetResponseStream(), Encoding.GetEncoding(gb2312)); // //utf-8 strResult sr.ReadToEnd(); return strResult; } 技术应用——网页自动登录提交Post内容的用途很多如验证身份、程序升级、网络投票等以下是用C#实现的方法. 未解决问题——目前最大问题无法绕过验证码——我曾经和同事讨论图片的算法基本上很难识别网上也有很多识别验证码的例子但是对于简单的噪声还是可以的可是对于复杂的就一点用都没有了到目前为止我没有测试成功过如果你有测试成功过请帖代码我们一起研究研究。转载于:https://www.cnblogs.com/gxy217/archive/2012/06/07/2539121.html
