【发布时间】:2010-11-22 22:24:06
【问题描述】:
我正在尝试以编程方式提交特定表单,但我总是会返回初始页面。 我一定是做错了什么或在这里遗漏了什么。 我发送会话 cookie 和一些 POST 数据,如 viewState(我从初始请求中解析)和 SessionID(这是我在表单中更改的值以获取其他年份的数据)。但在第二个请求中,我总是获取 Session 899 的数据,而不是我请求的那个:875。
这里是使用的代码:,非常感谢任何帮助
retrieveEdmIndexForSession(875);
protected string retrieveEdmIndexForSession(int sessionId) {
CookieContainer cookies;
HttpWebRequest oRequest;
HttpWebResponse oResponse;
Stream sw;
StreamReader sr;
string pageData;
string PathRemote = @"http://edmi.parliament.uk/EDMi/EDMList.aspx";
/*
* download the index page so we can get Cookies and ViewState from it.
*/
oRequest = (HttpWebRequest)WebRequest.Create(PathRemote);
oRequest.Method = "GET";
oRequest.AllowAutoRedirect = true;
oRequest.CookieContainer = new CookieContainer();
oRequest.Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";
oRequest.Referer = "http://edmi.parliament.uk/EDMi/EDMList.aspx";
oResponse =(HttpWebResponse) oRequest.GetResponse();
sr = new StreamReader(oResponse.GetResponseStream());
pageData = sr.ReadToEnd();
/*
* extract view state from pageData.
*/
string viewState = this.ExtractViewState(pageData);
/*
* lets submit the form with the parameters we want
*/
oRequest = (HttpWebRequest)WebRequest.Create(PathRemote);
oRequest.Method = "POST";
oRequest.AllowAutoRedirect = true;
oRequest.ContentType = "application/x-www-form-urlencoded";
oRequest.CookieContainer = new CookieContainer();
oRequest.CookieContainer.Add(oResponse.Cookies);
oRequest.Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";
oRequest.Referer = "http://edmi.parliament.uk/EDMi/EDMList.aspx";
string postdata = "__EVENTTARGET=&__EVENTARGUMENT=&__VIEWSTATE=" + viewState + "&_MenuCtrl%3AddlSession=" + sessionId + "&_MenuCtrl%3A_GoTo.x=57&_MenuCtrl%3A_GoTo.y=14&ddlStatus=1&ddlSortedBy=1";
byte[] buffer = Encoding.UTF8.GetBytes(postdata);
oRequest.ContentLength = buffer.Length;
/*
* Send post data into request stream first
*/
sw = oRequest.GetRequestStream();
sw.Write(buffer, 0, buffer.Length);
sw.Flush();
sw.Close();
/*
* Connect, send and get response
*/
oResponse = (HttpWebResponse)oRequest.GetResponse();
sr = new StreamReader(oResponse.GetResponseStream());
//OnLogUpdated(1, "\r\nStatus Code: " + oResponse.StatusCode);
//OnLogUpdated(1, "\r\nServer: " + oResponse.Server);
pageData = sr.ReadToEnd();
string result = getSessionId(pageData);
//OnLogUpdated(1, "\r\nRestuls: [" + result + "]");
//OnLogUpdated(1, "\r\nPage: [" + pageData + "]");
return pageData;
}
private string ExtractViewState(string str)
{
string viewState = "";
string pattern = "(?<=__VIEWSTATE\" value=\")(?<val>.*?)(?=\")";
Match match = Regex.Match(str, pattern);
if (match.Success)
{
viewState = match.Groups["val"].Value;
viewState = HttpUtility.UrlEncodeUnicode(viewState);
}
return viewState;
}
protected string getSessionId(string str)
{
string sessionId = string.Empty;
str = str.Trim();
string pattern = @"&SESSION=([^']+)'";
Match match = Regex.Match(str, pattern, RegexOptions.IgnoreCase);
if (match.Success)
{
sessionId = match.Groups[1].ToString(); ;
}
return sessionId;
}
这是 .NET 脚本发送的 RAW 请求。
POST /EDMi/EDMList.aspx HTTP/1.1 内容类型: 应用程序/x-www-form-urlencoded 接受: text/html,application/xhtml+xml,application/xml;q=0.9,/;q=0.8 推荐人: http://edmi.parliament.uk/EDMi/EDMList.aspx 用户代理:.NET Framework 客户端 主持人:edmi.parliament.uk Cookie: ASP.NET_SessionId=k55fqarvx2oszp2wxhtrol45 内容长度:2431 期望: 100-继续
__ EVENTTARGET =&__ EVENTARGUMENT =&__ VIEWSTATE = dDwxMDgyNzIxNDQ2O3Q8O2w8aTwzPjs%2bO2w8dDw7bDxpPDE%2bO2k8Mz47aTw1PjtpPDExPjs%2bO2w8dDw7bDxpPDEzPjtpPDE3Pjs%2bO2w8dDx0PHA8cDxsPERhdGFWYWx1ZUZpZWxkO0RhdGFUZXh0RmllbGQ7PjtsPFNFU1NJT05JRDtJVEVNX1ZBTFVFOz4%2bOz47dDxpPDIwPjtAPDA4LTA5OzA3LTA4OzA2LTA3OzA1LTA2OzA0LTA1OzAzLTA0OzAyLTAzOzAxLTAyOzAwLTAxOzk5LTAwOzk4LTk5Ozk3LTk4Ozk2LTk3Ozk1LTk2Ozk0LTk1OzkzLTk0OzkyLTkzOzkxLTkyOzkwLTkxOzg5LTkwOz47QDw4OTk7ODkxOzg4NTs4NzU7ODczOzY4Mjs2ODE7NjgwOzY3OTs3MDM7NzAyOzcwMTs3MDA7Njk5OzY5ODs2OTc7Njk2OzY5NTs2OTQ7NjkzOz4%2bOz47Oz47dDxwPGw8VGV4dDs%2bO2w8TGlzdCBPZiBFYXJseSBEYXkgTW90aW9uczs%2bPjs7Pjs%2bPjt0PDtsPGk8MT47aTwzPjs%2bO2w8dDx0PDs7bDxpPDA%2bOz4%2bOzs%2bO3Q8dDw7O2w8aTwwPjs%2bPjs7Pjs%2bPjt0PDtsPGk8MT47aTwzPjs%2bO2w8dDw7bDxpPDE%2bO2k8Mz47aTw1PjtpPDc%2bOz47bDx0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztFbmFibGVkO18hU0I7PjtsPDA7UGFnZUZpcnN0RGlzYWJsZWQ7bzxmPjtpPDI%2bOz4%2bOz47Oz47dDxwPHA8bDxDb21tYW5kQXJndW1lbnQ7Q3NzQ2xhc3M7RW5hYmxlZDtfIVNCOz47bDwtMTtQYWdlUHJldkRpc2FibGVkO 288Zj47aTwyPjs%2bPjs%2bOzs%2bO3Q8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO18hU0I7PjtsPDE7UGFnZU5leHRFbmFibGVkO2k8Mj47Pj47Pjs7Pjt0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztfIVNCOz47bDw0MjtQYWdlTGFzdEVuYWJsZWQ7aTwyPjs%2bPjs%2bOzs%2bOz4%2bO3Q8O2w8aTwxPjtpPDM%2bO2k8NT47aTw3Pjs%2bO2w8dDxwPHA8bDxUZXh0Oz47bDwyMTA5Oz4%2bOz47Oz47dDxwPHA8bDxUZXh0Oz47bDxFRE1zIGFuZCBBbWVuZG1lbnRzOz4%2bOz47Oz47dDxwPHA8bDxUZXh0Oz47bDwxOz4%2bOz47Oz47dDxwPHA8bDxUZXh0Oz47bDw1MDs%2bPjs%2bOzs%2bOz4%2bOz4%2bO3Q8O2w8aTwxPjtpPDM%2bOz47bDx0PDtsPGk8MT47aTwzPjtpPDU%2bO2k8Nz47PjtsPHQ8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO0VuYWJsZWQ7XyFTQjs%2bO2w8MDtQYWdlRmlyc3REaXNhYmxlZDtvPGY%2bO2k8Mj47Pj47Pjs7Pjt0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztFbmFibGVkO18hU0I7PjtsPC0xO1BhZ2VQcmV2RGlzYWJsZWQ7bzxmPjtpPDI%2bOz4%2bOz47Oz47dDxwPHA8bDxDb21tYW5kQXJndW1lbnQ7Q3NzQ2xhc3M7XyFTQjs%2bO2w8MTtQYWdlTmV4dEVuYWJsZWQ7aTwyPjs% 2bPjs%2bOzs%2bO3Q8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO18hU0I7PjtsPDQyO1BhZ2VMYXN0RW5hYmxlZDtpPDI%2bOz4%2bOz47Oz47Pj4 7dDxwPHA8bDxWaXNpYmxlOz47bDxvPGY%2bOz4%2bOz47bDxpPDE%2bO2k8Mz47aTw1PjtpPDc%2bOz47bDx0PHA8cDxsPFRleHQ7PjtsPDIxMDk7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPEVETXMgYW5kIEFtZW5kbWVudHM7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPDE7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPDUwOz4%2bOz47Oz47Pj47Pj47Pj47Pj47bDxfTWVudUN0cmw6X0dvVG87Pj5NHcFbPBNzNuwxs7sYLdUE2omkjw%3D%3D&_MenuCtrl%3AddlSession = 875&_MenuCtrl%3A_GoTo.x = 57&_MenuCtrl%3A_GoTo.y = 14&ddlStatus = 1&ddlSortedBy = 1 P>
这是 IE 发送的 RAW 请求:
POST /EDMi/EDMList.aspx HTTP/1.1 接受:图片/gif、图片/jpeg、 图像/pjpeg,图像/pjpeg, 应用程序/x-shockwave-flash, 应用程序/xaml+xml, 应用程序/vnd.ms-xps 文档, 应用程序/x-ms-xbap, 应用程序/x-ms-应用程序, 应用程序/vnd.ms-excel, 应用程序/vnd.ms-powerpoint, 应用程序/msword,/ 引用者: http://edmi.parliament.uk/EDMi/EDMList.aspx 接受语言:en-gb 用户代理: Mozilla/4.0(兼容;MSIE 8.0; 视窗 NT 5.1;三叉戟/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; InfoPath.1; .NET CLR 3.0.04506.648; OfficeLiveConnector.1.3; OfficeLivePatch.0.0; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729) 内容类型: 应用程序/x-www-form-urlencoded 接受编码:gzip,放气主机: edmi.parliament.uk 内容长度: 2431 连接:保持活动编译指示: 无缓存 Cookie: WT_FPC=id=83.217.99.254-2364242496.30021299:lv=1249572414567:ss=1249572414567; ASP.NET_SessionId=vwxgo4rlex1j5m55l0bivrqo
__ EVENTTARGET =&__ EVENTARGUMENT =&__ VIEWSTATE = dDwxMDgyNzIxNDQ2O3Q8O2w8aTwzPjs%2BO2w8dDw7bDxpPDE%2BO2k8Mz47aTw1PjtpPDExPjs%2BO2w8dDw7bDxpPDEzPjtpPDE3Pjs%2BO2w8dDx0PHA8cDxsPERhdGFWYWx1ZUZpZWxkO0RhdGFUZXh0RmllbGQ7PjtsPFNFU1NJT05JRDtJVEVNX1ZBTFVFOz4%2BOz47dDxpPDIwPjtAPDA4LTA5OzA3LTA4OzA2LTA3OzA1LTA2OzA0LTA1OzAzLTA0OzAyLTAzOzAxLTAyOzAwLTAxOzk5LTAwOzk4LTk5Ozk3LTk4Ozk2LTk3Ozk1LTk2Ozk0LTk1OzkzLTk0OzkyLTkzOzkxLTkyOzkwLTkxOzg5LTkwOz47QDw4OTk7ODkxOzg4NTs4NzU7ODczOzY4Mjs2ODE7NjgwOzY3OTs3MDM7NzAyOzcwMTs3MDA7Njk5OzY5ODs2OTc7Njk2OzY5NTs2OTQ7NjkzOz4%2BOz47Oz47dDxwPGw8VGV4dDs%2BO2w8TGlzdCBPZiBFYXJseSBEYXkgTW90aW9uczs%2BPjs7Pjs%2BPjt0PDtsPGk8MT47aTwzPjs%2BO2w8dDx0PDs7bDxpPDA%2BOz4%2BOzs%2BO3Q8dDw7O2w8aTwwPjs%2BPjs7Pjs%2BPjt0PDtsPGk8MT47aTwzPjs%2BO2w8dDw7bDxpPDE%2BO2k8Mz47aTw1PjtpPDc%2BOz47bDx0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztFbmFibGVkO18hU0I7PjtsPDA7UGFnZUZpcnN0RGlzYWJsZWQ7bzxmPjtpPDI%2BOz4%2BOz47Oz47dDxwPHA8bDxDb21tYW5kQXJndW1lbnQ7Q3NzQ2xhc3M7RW5hYmxlZDtfIVNCOz47bDwtMTtQYWdlUHJldkRpc2FibGVkO 288Zj47aTwyPjs%2BPjs%2BOzs%2BO3Q8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO18hU0I7PjtsPDE7UGFnZU5leHRFbmFibGVkO2k8Mj47Pj47Pjs7Pjt0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztfIVNCOz47bDw0MjtQYWdlTGFzdEVuYWJsZWQ7aTwyPjs%2BPjs%2BOzs%2BOz4%2BO3Q8O2w8aTwxPjtpPDM%2BO2k8NT47aTw3Pjs%2BO2w8dDxwPHA8bDxUZXh0Oz47bDwyMTA5Oz4%2BOz47Oz47dDxwPHA8bDxUZXh0Oz47bDxFRE1zIGFuZCBBbWVuZG1lbnRzOz4%2BOz47Oz47dDxwPHA8bDxUZXh0Oz47bDwxOz4%2BOz47Oz47dDxwPHA8bDxUZXh0Oz47bDw1MDs%2BPjs%2BOzs%2BOz4%2BOz4%2BO3Q8O2w8aTwxPjtpPDM%2BOz47bDx0PDtsPGk8MT47aTwzPjtpPDU%2BO2k8Nz47PjtsPHQ8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO0VuYWJsZWQ7XyFTQjs%2BO2w8MDtQYWdlRmlyc3REaXNhYmxlZDtvPGY%2BO2k8Mj47Pj47Pjs7Pjt0PHA8cDxsPENvbW1hbmRBcmd1bWVudDtDc3NDbGFzcztFbmFibGVkO18hU0I7PjtsPC0xO1BhZ2VQcmV2RGlzYWJsZWQ7bzxmPjtpPDI%2BOz4%2BOz47Oz47dDxwPHA8bDxDb21tYW5kQXJndW1lbnQ7Q3NzQ2xhc3M7XyFTQjs%2BO2w8MTtQYWdlTmV4dEVuYWJsZWQ7aTwyPjs% 2BPjs%2BOzs%2BO3Q8cDxwPGw8Q29tbWFuZEFyZ3VtZW50O0Nzc0NsYXNzO18hU0I7PjtsPDQyO1BhZ2VMYXN0RW5hYmxlZDtpPDI%2BOz4%2BOz47Oz47Pj4 7dDxwPHA8bDxWaXNpYmxlOz47bDxvPGY%2BOz4%2BOz47bDxpPDE%2BO2k8Mz47aTw1PjtpPDc%2BOz47bDx0PHA8cDxsPFRleHQ7PjtsPDIxMDk7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPEVETXMgYW5kIEFtZW5kbWVudHM7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPDE7Pj47Pjs7Pjt0PHA8cDxsPFRleHQ7PjtsPDUwOz4%2BOz47Oz47Pj47Pj47Pj47Pj47bDxfTWVudUN0cmw6X0dvVG87Pj5NHcFbPBNzNuwxs7sYLdUE2omkjw%3D%3D&_MenuCtrl%3AddlSession = 885&ddlStatus = 0&ddlSortedBy = 1&_MenuCtrl%3A_GoTo.x = 37&_MenuCtrl%3A_GoTo.y = 12 P>
IE Header 似乎有一个额外的 cookie(WT_FPC=id=83.217.99.254-2364242496.30021299:lv=1249572414567:ss=1249572414567;) 女巫似乎通过 WebTrends Cookie 插件跟踪使用 cookie 的访问者。两个 POST 请求都返回 HTTP 状态代码 302 并重定向到返回状态 200 的 GET 请求。
有什么想法吗?
【问题讨论】:
-
您是否尝试过连接 Fiddler 并将真正的请求与您以编程方式制作的请求进行比较?一定有什么不同。
-
我一直在尝试用 Fiddler 解决这个问题。我将使用请求的 RAW 数据更新帖子。
标签: c# screen-scraping