Excel亚马逊卖家Web Scraper问题

Question

我一直在试图让这个代码工作在工作流程效率的目的，但我似乎无法使其正常工作。

步骤： 1.登录到亚马逊卖方

使用顺序在列A中的数字，并将它们置于搜索框，以搜寻

查找“预计交货的元件的innerText ：“并将信息刮到与订单号相邻的列B中

移到下一个订单号并重复处理，直到订单号列为空。

网页代码（我想要获得被高亮显示）：

Option Explicit 

Dim HTMLDoc As HTMLDocument 
Dim MyBrowser As InternetExplorer 

Sub MyAmazonSellereEDD() 

    Dim MyHTML_Element As IHTMLElement 
    Dim MyURL As String 
    Dim oSignInLink As HTMLLinkElement 
    Dim oInputEmail As HTMLInputElement 
    Dim oInputPassword As HTMLInputElement 
    Dim oInputSignInButton As HTMLInputButtonElement 

    'InputSearchOrder will be the destination for order numbers taken from the workbook 
    Dim InputSearchOrder As HTMLInputElement 

    Dim InputSearchButton As HTMLInputButtonElement 
    Dim IE As InternetExplorer 
    Dim AAOrder As Workbook 
    Dim AAws As Worksheet 
    Dim AAws2 As Worksheet 

    Dim R As Range 
    Dim x As Integer 
    Dim i As Long 
    Dim ar As Variant 
    Dim elems As IHTMLElementCollection 
    Dim TDelement As HTMLTableCell 

    Dim ExcludWords() As Variant, a As Range, b As Long, LR As Long 

    ExcludWords = Array("Estimated Delivery:") 


    MyURL = "https://sellercentral.amazon.com/gp/homepage.html" 

    Set IE = New InternetExplorer 

    ' Open the browser and navigate. 
    With IE 
     .Silent = True 
     .navigate MyURL 
     .Visible = True 
     Do 
      DoEvents 
     Loop Until .readyState = READYSTATE_COMPLETE 
    End With 


    ' Get the html document. 
    Set HTMLDoc = IE.document 



    With HTMLDoc 
     .all.Item("username").Value = "blankityblank@blank.net" 
     .all.Item("password").Value = "*********" 
     .all.Item("sign-in-button").Click 
    End With 

     Do 
     DoEvents 
    Loop Until IE.readyState = READYSTATE_COMPLETE 

    Application.Wait (Now + TimeValue("0:00:08")) 

    'Set AAOrder = Application.Workbooks.Open("Z:\Automation Anywhere\5 Automated Tracking Imports\Amazon Prime\PrimeOrdersWithNoFulfillment.csv") 
    'Set AAws = AAOrder.Worksheets("PrimeOrdersWithNoFulfillment") 





    x = 2 
    'Do Until Range("A" & x) = "" 
    If Range("B" & x).Value = "" Then 

     'If AAws.Range("B" & x).Value = "" Then 
     'x = x + 1 
     Do Until Range("A" & x) = "" 
      Set InputSearchOrder = HTMLDoc.getElementById("sc-search-field") 
      InputSearchOrder.Value = Range("A" & x) 

      Set InputSearchButton = HTMLDoc.getElementsByClassName("sc-search-button")(0) 
      InputSearchButton.Click 
       Do 
       DoEvents 
      Loop Until IE.readyState = READYSTATE_COMPLETE 
      Application.Wait (Now + TimeValue("0:00:05")) 


      Set elems = HTMLDoc.getElementsByTagName("td") 


      'ExcludWords = Array("Package Weight:", "Tracking ID:", "Ship Date:", "Carrier:", "Shipping Service:") 


      i = 2 

      For Each TDelement In elems 
       If TDelement.className = "data-display-field" And InStr(TDelement.innerText, "Estimated Delivery:") Then 
        Range("B" & x).Value = TDelement.innerText 
        i = i + 1 
       End If 
      Next 







      LR = Range("B" & Rows.Count).End(xlUp).Row 
      For i = 1 To LR 
      Set a = Cells(i, "B") 
      For b = 0 To UBound(ExcludWords) 
       a.Formula = Replace((a.Formula), ExcludWords(b), "") 
        Next b 
      Next i 


     'End If 
     x = x + 1 
     Loop 


    'Loop 
    End If 

    Err_Clear: 
     If Err <> 0 Then 
      Err.Clear 
      Resume Next 
     End If 

    MsgBox ("Process is done! :)") 


    End Sub 

我的问题是，当刮擦数据中，“预计交货：”并且实际估计的交付日期应该是分开的，但仍然应该包含在B列的输出数据中。它所做的只是查找并插入“Estimated Delivery：”，然后使用代码修剪这些字符按照指示。此后空间依然空白。我不确定问题是什么。

Answer 1

的TDelement您在下面的代码部份仅包括捡“预计交货时间：”在其innerText，随着日期的部分实际上是一个独立的TDelement：

For Each TDelement In elems 
    If TDelement.className = "data-display-field" And InStr(TDelement.innerText, "Estimated Delivery:") Then 
     Range("B" & x).Value = TDelement.innerText 
     i = i + 1 
    End If 
Next 

，因为没有任何独特用于引用TDelement的html代码中的信息（例如id，name等），其中包含您可以使用已有的引用的日期与NextSibling一起使用，以便在包含文本“Estimated交货：”。也许尝试这个（目前无法测试任何东西，但应该工作）：

For Each TDelement In elems 
    If TDelement.className = "data-display-field" And InStr(TDelement.innerText, "Estimated Delivery:") Then 
     Range("B" & x).value = TDelement.NextSibling.innerText 
     i = i + 1 
    End If 
Next