Excel VBA：迭代代码，但需要第二或第三个DIV类实例

Question

我有以下代码，根据我之前的问题进行处理，Tim Williams回答道。然而，在它工作几分钟后，我发现了一些新的要求，并没有提出原始问题。鉴于下面的代码和以下HTML结构，我如何修改代码以使用相同的＆＃34;右标题＆＃34;从第二个甚至第三个DIV中提取数据。类？子DIV没有类或ID，它们只是包装器。

这是HTML：

<div class="right-header">
 <div>Entry 1</div>
 <div>Entry 2</div>
 <div>Entry 3</div>
 <div>Entry 4</div>
 <div>Entry 5</div>
 <div>Entry 6</div>
</div>

 <div class="right-header">
 <div>Entry 1</div>
 <div>Entry 2</div>
 <div>Entry 3</div>
 <div>Entry 4</div>
 <div>Entry 5</div>
 <div>Entry 6</div>
</div>

<div class="right-header">
 <div>Entry 1</div>
 <div>Entry 2</div>
 <div>Entry 3</div>
 <div>Entry 4</div>
 <div>Entry 5</div>
 <div>Entry 6</div>
</div>

以下是Tim Williams修改后的VBA：

Sub extract()
Dim IE As InternetExplorer
Dim topDiv, div, childDivs, tc As String, cntr

Set IE = New InternetExplorerMedium
IE.Visible = False
IE.Navigate2 "C:\Users\john\Documents\Test.html"

' Wait while IE loading
Do While IE.Busy
    Application.Wait DateAdd("s", 1, Now)
Loop

Set topDiv = IE.document.getElementsByClassName("right-header")(0)

Set childDivs = topDiv.getElementsByTagName("div")

cntr = 2

For Each div In childDivs
    tc = Trim(div.textContent)
    If tc <> "" Then
        Select Case Right(tc, 1)
            Case "<div>"
                'not sure whether you should be seeing HTML in textcontent...?
                Range("B" & cntr) = CStr(tc)
            Case "%"
                Range("C" & cntr).Value = tc
                cntr = cntr + 1
            Case 0
                Range("C" & cntr).Value = tc
            Case Else
                Range("A" & cntr).Value = tc
        End Select
    End If
    cntr = cntr + 1
Next div

Sheets("Sheet3").Range("A1").Value = topDiv.textContent

'Cleanup
IE.Quit
Set IE = Nothing
End Sub

谢谢大家，对不起原来那么接近的问题。

Answer 1

如果已知div的数量，你可以把它放在一个循环中

    Sub extract()
    Dim IE As InternetExplorer
    Dim topDiv, div, childDivs, tc As String, cntr

    Set IE = New InternetExplorerMedium
    IE.Visible = False
    IE.Navigate2 "C:\Nitesh\test.html"

    ' Wait while IE loading
    Do While IE.Busy
        Application.Wait DateAdd("s", 1, Now)
    Loop

    For i = 0 To 2

        Set topDiv = IE.document.getElementsByClassName("right-header")(i)

        Set childDivs = topDiv.getElementsByTagName("div")

        cntr = 2

        For Each div In childDivs
            tc = Trim(div.textContent)
            If tc <> "" Then
                Select Case Right(tc, 1)
                    Case "<div>"
                        'not sure whether you should be seeing HTML in textcontent...?
                        Range("B" & cntr).Offset(0, i) = CStr(tc)
                    Case "%"
                        Range("C" & cntr).Offset(0, i).Value = tc
                        cntr = cntr + 1
                    Case 0
                        Range("C" & cntr).Offset(0, i).Value = tc
                    Case Else
                        Range("A" & cntr).Offset(0, i).Value = tc
                End Select
            End If
            cntr = cntr + 1
        Next div

    Next i

End Sub

并将所有输出偏移i以将结果输入新列。

Answer 2

Sub extract()
Dim IE As InternetExplorer
Dim topDivs, topDiv, div, childDivs, tc As String, cntr

    Set IE = New InternetExplorerMedium
    IE.Visible = False
    IE.Navigate2 "C:\Users\john\Documents\Test.html"

    ' Wait while IE loading
    Do While IE.Busy
        Application.Wait DateAdd("s", 1, Now)
    Loop

    cntr = 2

    'get all the top-level divs
    Set topDivs = IE.document.getElementsByClassName("right-header")

    'loop over the top-level divs
    For Each topDiv In topDivs

        'get child divs for this top-level div
        Set childDivs = topDiv.getElementsByTagName("div")

        For Each div In childDivs
            tc = Trim(div.textContent)
            If tc <> "" Then
                Select Case Right(tc, 1)
                    Case "<div>"
                        'not sure whether you should be seeing HTML in textcontent...?
                        Range("B" & cntr) = CStr(tc)
                    Case "%"
                        Range("C" & cntr).Value = tc
                        cntr = cntr + 1
                    Case 0
                        Range("C" & cntr).Value = tc
                    Case Else
                        Range("A" & cntr).Value = tc
                End Select
            End If
            cntr = cntr + 1
        Next div

    Next topDiv

    'Sheets("Sheet3").Range("A1").Value = topDiv.textContent

    'Cleanup
    IE.Quit
    Set IE = Nothing

End Sub