@H_403_1@我遇到了一个看起来很简单的网站,我非常有信心能够使用HttpWebRequest读取数据,并能够执行GET和POST请求. GET请求工作正常. POST请求也不会产生任何错误,但仍然发布的表单数据对返回的结果没有影响.发布的表单数据具有按日期过滤数据的字段,但无论是否发布了所有必需数据,都不会过滤返回的数据.我添加了每个标题,表单数据以及添加了请求的cookie.
网页的网址为http://www.bseindia.com/corporates/Insider_Trading_new.aspx?expandable=0
这看起来像一个非常普通的网站,但由于它是一个aspx页面,涉及ViewState和事件验证,因此预计这不会很容易.
我的第一步是使用Fiddler分析网站的GET和POST,这让我感到惊讶,因为Fiddler没有为这个网址捕获任何流量.我试过查尔斯,但这本身并没有抓住这个网址.除此之外,这个Url Fiddler和Charles都在捕捉其他一切.我还想提一下,当我使用HttpWebRequest从控制台应用程序调用Url时,Fiddler和Charles都捕获了它,但他们没有从Chrome,FireFox和Internet Explorer 11捕获它.
因此,我使用FireFox中的开发人员工具分析了网络活动,一切都是可见的,包括(标题,参数和Cookie).在Chrome中没有Cookie存在.当我通过创建HttpWebRequest检查cookie并得到响应时,没有cookie存在.所以这个网站真的很奇怪.
我以某种方式设法创建一个简单的函数来创建请求并获得响应.我正在做的是我首先创建一个GET请求并获取网站字符串并从中提取Viewstate,EventValidation等.我使用此信息在第二个HttpWebRequest中使用,这是一个帖子.现在一切正常,我收到的回复却不如预期.我想要两个给出日期之间的记录,我已经在表单数据中指定了这些日期,但POST请求仍然不返回过滤后的数据.我已经提到了我在下面创建的函数,我将非常感谢为什么会发生这种情况以及如何处理它的任何建议.要理解这一点对我来说已经成为一个挑战,因为我无法理解为什么这个简单的网站没有出现在Fiddler中. (这使用Javascript Postback)
代码可能看起来很长而且可怕,但它非常简单直接.
Try
' First GET Request to obtain Viewstate,Eventvalidation etc
Dim objRequest2 As Net.HttpWebRequest = DirectCast(HttpWebRequest.Create("http://www.bseindia.com/corporates/Insider_Trading_new.aspx?expandable=0"),HttpWebRequest)
objRequest2.Method = "GET"
objRequest2.Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
objRequest2.Headers.Add("Accept-Encoding","gzip,deflate")
objRequest2.Headers.Add("Accept-Language","en-GB,en-US;q=0.8,en;q=0.6,ur;q=0.4")
objRequest2.KeepAlive = True
objRequest2.ContentType = "application/x-www-form-urlencoded"
objRequest2.Host = "www.bseindia.com"
objRequest2.UserAgent = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/47.0.2526.106 Safari/537.36"
objRequest2.AutomaticDecompression = DecompressionMethods.Deflate Or DecompressionMethods.GZip
Dim LoginRes2 As Net.HttpWebResponse
Dim sr2 As IO.StreamReader
LoginRes2 = objRequest2.GetResponse()
sr2 = New IO.StreamReader(LoginRes2.GetResponseStream)
Dim getString As String = sr2.ReadToEnd()
Dim getCookieCollection = objRequest2.CookieContainer
' get the page ViewState
Dim viewStateFlag As String = "id=""__VIEWSTATE"" value="""
Dim i As Integer = getString.IndexOf(viewStateFlag) + viewStateFlag.Length
Dim j As Integer = getString.IndexOf("""",i)
Dim viewState As String = getString.Substring(i,j - i)
' get page EventValidation
Dim eventValidationFlag As String = "id=""__EVENTVALIDATION"" value="""
i = getString.IndexOf(eventValidationFlag) + eventValidationFlag.Length
j = getString.IndexOf("""",i)
Dim eventValidation As String = getString.Substring(i,j - i)
' get page EventValidation
Dim viewstateGeneratorFlag As String = "id=""__VIEWSTATEGENERATOR"" value="""
i = getString.IndexOf(viewstateGeneratorFlag) + viewstateGeneratorFlag.Length
j = getString.IndexOf("""",i)
Dim viewStateGenerator As String = getString.Substring(i,j - i)
viewState = System.Web.HttpUtility.UrlEncode(viewState)
eventValidation = System.Web.HttpUtility.UrlEncode(eventValidation)
Dim LoginRes As Net.HttpWebResponse
Dim sr As IO.StreamReader
Dim objRequest As Net.HttpWebRequest
' Second POST request to post the form data along with cookies
objRequest = DirectCast(HttpWebRequest.Create("http://www.bseindia.com/corporates/Insider_Trading_new.aspx?expandable=0"),HttpWebRequest)
Dim formDataCollection As New NameValueCollection
formDataCollection.Add("__EVENTTARGET","")
formDataCollection.Add("__EVENTARGUMENT","")
formDataCollection.Add("__VIEWSTATE",viewState)
formDataCollection.Add("__VIEWSTATEGENERATOR",viewStateGenerator)
formDataCollection.Add("__EVENTVALIDATION",eventValidation)
formDataCollection.Add("fmdate","20160104")
formDataCollection.Add("eddate","20160204")
formDataCollection.Add("hidCurrentDate","2016/02/04")
formDataCollection.Add("ctl00_ContentPlaceHolder1_hdnCode","")
formDataCollection.Add("txtDate","04/01/2016")
formDataCollection.Add("ddlCalMonthDiv3","1")
formDataCollection.Add("ddlCalYearDiv3","2016")
formDataCollection.Add("txtTodate","04/02/2016")
formDataCollection.Add("ddlCalMonthDiv4","2")
formDataCollection.Add("ddlCalYearDiv4","2016")
formDataCollection.Add("Hidden1","")
formDataCollection.Add("ctl00_ContentPlaceHolder1_GetQuote1_smartSearch","Enter Security Name / Code / ID")
formDataCollection.Add("btnSubmit.x","44")
formDataCollection.Add("btnSubmit.y","2")
Dim strFormdata As String = formDataCollection.ToString()
Dim encoding As New ASCIIEncoding
Dim postBytes As Byte() = encoding.GetBytes(strFormdata)
objRequest.Method = "POST"
objRequest.Accept = "text/html,*/*;q=0.8"
objRequest.Headers.Add("Accept-Encoding",deflate")
objRequest.Headers.Add("Accept-Language",ur;q=0.4")
objRequest.Headers.Add("Cache-Control","private,max-age=60")
objRequest.KeepAlive = True
objRequest.ContentType = "application/x-www-form-urlencoded"
objRequest.Host = "www.bseindia.com"
objRequest.Headers.Add("Origin","http://www.bseindia.com")
objRequest.Referer = "http://www.bseindia.com/corporates/Insider_Trading_new.aspx?expandable=0"
objRequest.Headers.Add("Upgrade-Insecure-Requests","1")
objRequest.UserAgent = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/47.0.2526.106 Safari/537.36"
objRequest.ContentType = "text/html; charset=utf-8"
objRequest.Date = "Thu,04 Feb 2016 13:42:04 GMT"
objRequest.Headers.Add("Server","Microsoft-IIS/8.0")
objRequest.Headers.Add("Vary","Accept-Encoding")
objRequest.Headers.Add("X-AspNet-Version","2.0.50727")
objRequest.Headers.Add("ASP.NET","ASP.NET")
objRequest.AutomaticDecompression = DecompressionMethods.Deflate Or DecompressionMethods.GZip
Dim gaCookies As New CookieContainer()
Dim cookie1 As New Cookie("__asc","f673f0d5152a823bc335f575d34")
cookie1.Domain = ".bseindia.com"
cookie1.Path = "/"
gaCookies.Add(cookie1)
Dim cookie2 As New Cookie("__auc","f673f0d5152a823bc335f575d34")
cookie2.Domain = ".bseindia.com"
cookie2.Path = "/"
gaCookies.Add(cookie2)
Dim cookie3 As New Cookie("__utma","253454874.280640365.1454519857.1454519865.1454519865.1")
cookie3.Domain = ".bseindia.com"
cookie3.Path = "/"
gaCookies.Add(cookie3)
Dim cookie4 As New Cookie("__utmb","253454874.1.10.1454519865")
cookie4.Domain = ".bseindia.com"
cookie4.Path = "/"
gaCookies.Add(cookie4)
Dim cookie5 As New Cookie("__utmc","253454874")
cookie5.Domain = ".bseindia.com"
cookie5.Path = "/"
gaCookies.Add(cookie5)
Dim cookie6 As New Cookie("__utmt","1")
cookie6.Domain = ".bseindia.com"
cookie6.Path = "/"
gaCookies.Add(cookie6)
Dim cookie7 As New Cookie("__utmz","253454874.1454519865.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)")
cookie7.Domain = ".bseindia.com"
cookie7.Path = "/"
gaCookies.Add(cookie7)
Dim cookie8 As New Cookie("_ga","GA1.2.280640365.1454519857")
cookie8.Domain = ".bseindia.com"
cookie8.Path = "/"
gaCookies.Add(cookie8)
Dim cookie9 As New Cookie("_gat","1")
cookie9.Domain = ".bseindia.com"
cookie9.Path = "/"
gaCookies.Add(cookie9)
Dim postStream As Stream = objRequest.GetRequestStream()
postStream.Write(postBytes,postBytes.Length)
postStream.Flush()
postStream.Close()
LoginRes = objRequest.GetResponse()
sr = New IO.StreamReader(LoginRes.GetResponseStream)
ReadWebsite = sr.ReadToEnd()
sr.Close()
sr = Nothing
LoginRes.Close()
LoginRes = Nothing
objRequest = Nothing
Exit Function
Catch ex As Exception
ReadWebsite = Nothing
End Try
注意:(没有viewstate和eventvalidation的日期的原始表单数据)
fmdate：20160130
eddate：20160205
hidCurrentDate：2016年2月5日
ctl00_ContentPlaceHolder1_hdnCode：
txtDate：2016年4月1日
ddlCalMonthDiv3：1
ddlCalYearDiv3 2016
txtTodate：2016年4月2日
ddlCalMonthDiv4：2
ddlCalYearDiv4 2016
Hidden1：
ctl00_ContentPlaceHolder1_GetQuote1_smartSearch：输入安全名称/代码/ ID
btnSubmit.x：55
btnSubmit.y：13
