如何使用 VBA 读取嵌套表 <td> 值？

Question

任何人在这里帮助我说如何使用 Excel VBA 从第三方应用程序读取嵌套的 html 表值？作为下面的示例，我粘贴了 HTML 源代码的一部分，我想在其中读取所有值并将其存储到 excel 中。但是在这里，所有这些都是他们使用的嵌套表，并且这些表也没有任何名称在我见过的html源代码中。

<td>
<table cellspacing="1" cellpadding="0" class="data">
<tr class="colhead">
<th colspan="3">Expression</th>
 </tr>
<tr class="colhead">
<th>Field</th>
<th>Operator</th>
<th>Answer</th>
</tr>
<tr class="rowLight">
<td width="40%">        
Location Attributes:  LOC - Sub Commodity
</td>
<td width="20%">
= 
</td>
<td width="40%">
Abrasives
</td>
</tr>
<tr class="rowDark">
<td width="40%">
Location Attributes:  LOC - Commodity Tier1
</td>
<td width="20%">
= 
</td>
<td width="40%">
Advertising, Sales &amp; Promotion
</td>
</tr>

谢谢， 奥雅纳

Answer 1

请在下面找到代码：

Option Explicit 

Sub TableExample() 
    Dim IE As Object 
    Dim doc As Object 
    Dim strURL As String 

    strURL = "[URL="http://example.comwww.dectech.org/football/index.php"]http://example.com[/URL]" ' replace with URL of your choice

    Set IE = CreateObject("InternetExplorer.Application") 
    With IE 
         '.Visible = True

        .navigate strURL 
        Do Until .ReadyState = 4: DoEvents: Loop 
            Do While .Busy: DoEvents: Loop 
                Set doc = IE.Document 
                GetAllTables doc 

                .Quit 
            End With 
        End Sub 

        Sub GetAllTables(doc As Object) 

             ' get all the tables from a webpage document, doc, and put them in a new worksheet

            Dim ws As Worksheet 
            Dim rng As Range 
            Dim tbl As Object 
            Dim rw As Object 
            Dim cl As Object 
            Dim tabno As Long 
            Dim nextrow As Long 
            Dim I As Long 

            Set ws = Worksheets.Add 

            For Each tbl In doc.getElementsByTagName("TABLE") 
                tabno = tabno + 1 
                nextrow = nextrow + 1 
                Set rng = ws.Range("B" & nextrow) 
                rng.Offset(, -1) = "Table " & tabno 
                For Each rw In tbl.Rows 
                    For Each cl In rw.Cells 
                        rng.Value = cl.outerText 
                        Set rng = rng.Offset(, 1) 
                        I = I + 1 
                    Next cl 
                    nextrow = nextrow + 1 
                    Set rng = rng.Offset(1, -I) 
                    I = 0 
                Next rw 
            Next tbl 

            ws.Cells.ClearFormats 

        End Sub 

Answer 2

这就是我阅读 HTML 表格的方式：

Sub ReadHTMLtable()
Dim htmldb As New ADODB.Connection
Dim htmlcmd As New ADODB.Command
Dim rs As New ADODB.Recordset

With htmldb
    .Provider = "Microsoft.Jet.OLEDB.4.0"
    .ConnectionString = "Data Source=Z:\filename.html;Extended Properties=""HTML Import;HDR=YES;IMEX=1"""
    .Open
End With

Set htmlcmd.ActiveConnection = htmldb
htmlcmd.CommandType = adCmdText
htmlcmd.CommandText = "Select * from [table]"
rs.CursorLocation = adUseClient
rs.CursorType = adOpenDynamic
rs.LockType = adLockOptimistic
rs.Open htmlcmd

'process rs here

End Sub

这使用了 ADO，但是对于 DAO 应该是一样的

Answer 3

这需要将引用设置为Microsoft HTML Object Library 和Microsoft Internet Controls

Sub Extract_TD_text()

    Dim URL As String
    Dim IE As InternetExplorer
    Dim HTMLdoc As HTMLDocument
    Dim TDelements As IHTMLElementCollection
    Dim TDelement As HTMLTableCell
    Dim r As Long

    'Saved from www vbaexpress com/forum/forumdisplay.php?f=17
    URL = "your file pathe/URL"

    Set IE = New InternetExplorer

    With IE
        .navigate URL
        .Visible = True

        'Wait for page to load
        While .Busy Or .readyState <> READYSTATE_COMPLETE: DoEvents: Wend

        Set HTMLdoc = .document
    End With

    Set TDelements = HTMLdoc.getElementsByTagName("TD")

    Sheet1.Cells.ClearContents

    r = 1
    For Each TDelement In TDelements
        'Look for required TD elements - this check is specific to VBA Express forum - modify as required
            If TDelement.ParentNode.ParentNode.ParentNode.Title = "table you want's title" Then
                Sheet1.Range("A1").Offset(r, 0).Formula = "=" & Chr(34) & TDelement.innerText & Chr(34)
                r = r + 1
            End If
    Next

    IE.Quit
    Set IE = Nothing  
End Sub

我基于this page