检查值是否存在，如果不添加到列表

Question

我的目标：检查值是否存在，如果值不存在，则添加到 A 列的末尾。如果值存在，则跳过 ID 并检查下一个值。

实际结果：不管值是否存在，ID 都会添加到 A 行的末尾。因此我得到了重复。

我尝试使用“if”，但出现错误。

我的编码：

Option Explicit


Sub ExposeID()

Dim browser As Object   'Aufnehmen der verwendeten Instanz des Browsers (Internet Explorer)
Dim knotenAst As Object 'Aufnehmen einer HTML Struktur aus dem Browser Dokument
Dim n As Integer
Dim url As String       'Aufnehmen der auszulesenden Adresse

Dim ExposeID As String
Dim letztezeile As Integer
Dim nodeList As Object, i As Long

Set browser = CreateObject("internetexplorer.application")
    browser.Visible = False

For n = 0 To 1
    
    url = "https://www.
    browser.navigate url
    Do Until browser.readyState = 4: DoEvents: Loop

    letztezeile = ActiveSheet.Cells(Rows.Count, 1).End(xlUp).Row

Set nodeList = browser.document.querySelectorAll(".result-list__listing[data-id]")

For i = 0 To nodeList.Length - 1

    ''' HERE IS THE PROBLEM '''
    If nodeList.Item(i).getAttribute("data-id") <> Cells.Range("A:A") Then
       Cells(letztezeile + i + 1, 1) = nodeList.Item(i).getAttribute("data-id")
       
    Else
    
    End If
    
Next i

Next n

Set nodeList = Nothing
browser.Quit
  
End Sub

Answer 1

我找到了一种方法。但是有一个问题。它会跳过已经存在一行的每个条目。

Option Explicit

'Version vom 08.05.2020
' Coding funktioniert, aber Leerzeichen


Sub ExposeID()

Dim browser As Object   'Aufnehmen der verwendeten Instanz des Browsers (Internet Explorer)
Dim knotenAst As Object 'Aufnehmen einer HTML Struktur aus dem Browser Dokument
Dim n As Integer
Dim url As String       'Aufnehmen der auszulesenden Adresse

Dim ExposeID As String
Dim letztezeile As Integer
Dim nodeList As Object, i As Long

Set browser = CreateObject("internetexplorer.application")
    browser.Visible = False

For n = 0 To 1

    url = "https://www.immobilienscout24.de/Suche/de/niedersachsen/oldenburg-oldenburg/haus-kaufen?pagenumber=" & n + 1
    browser.navigate url
    Do Until browser.readyState = 4: DoEvents: Loop

    letztezeile = ActiveSheet.Cells(Rows.Count, 1).End(xlUp).Row

Set nodeList = browser.document.querySelectorAll(".result-list__listing[data-id]")

For i = 0 To nodeList.Length - 1
Dim x As Integer

Dim FindString As String
Dim Rng As Range
FindString = nodeList.Item(i).getAttribute("data-id")
If Trim(FindString) <> "" Then
    With Sheets("IDs").Range("A:A") 'searches all of column A
        Set Rng = .Find(What:=FindString, _
                        After:=.Cells(.Cells.Count), _
                        LookIn:=xlValues, _
                        LookAt:=xlWhole, _
                        SearchOrder:=xlByRows, _
                        SearchDirection:=xlNext, _
                        MatchCase:=False)
        If Not Rng Is Nothing Then

        Else
          Cells(letztezeile + i + 1, 1) = nodeList.Item(i).getAttribute("data-id")
        End If
    End With
End If

Next i

Next n

Set nodeList = Nothing
browser.Quit

End Sub

Answer 2

识别为文本的值

您可以使用 Match 函数来比较 cmets 中所写的值：

If IsError(Application.Match(nodeList.Item(i).getAttribute("data-id"), Cells.Range("A:A"), 0)) Then

问题是数据被识别为文本，当写入工作表时，它被转换为整数。您可以使用Val 函数将文本转换为数字。查看代码中的关键行：

Option Explicit

Sub ExposeID()

    Dim browser As Object   'Aufnehmen der verwendeten Instanz des Browsers (Internet Explorer)
    Dim knotenAst As Object 'Aufnehmen einer HTML Struktur aus dem Browser Dokument
    Dim n As Integer
    Dim url As String       'Aufnehmen der auszulesenden Adresse

    Dim ExposeID As String
    Dim letztezeile As Integer
    Dim nodeList As Object, i As Long

    Set browser = CreateObject("internetexplorer.application")
        browser.Visible = False

    For n = 0 To 1

        url = "https://www.immobilienscout24.de/Suche/de/niedersachsen/" _
          & "oldenburg-oldenburg/haus-kaufen?pagenumber=" & n + 1
        browser.navigate url
        Do Until browser.readyState = 4: DoEvents: Loop

        letztezeile = Cells(Rows.Count, 1).End(xlUp).Row

        Set nodeList = browser.document.querySelectorAll( _
          ".result-list__listing[data-id]")

        For i = 0 To nodeList.Length - 1

            If IsError(Application.Match(Val(nodeList.Item(i) _
              .getAttribute("data-id")), Cells.Range("A:A"), 0)).Value Then
                Cells(letztezeile + i + 1, 1).Value = nodeList.Item(i) _
                  .getAttribute("data-id")
            Else

            End If

        Next i

    Next n

    Set nodeList = Nothing
    browser.Quit

End Sub

我认为这个 Internet Explorer 版本太慢了，所以你可以问另一个问题，如何使用 xhr（XML HTTP 请求）来解决这个问题。