Question

我创建了一个脚本，该脚本从网站的表格中抓取数据，并将其复制到Excel工作表中。基本上，它会执行以下操作

转到链接，
填写文本框并从下拉菜单中选择一个值，然后按一个按钮，
获取数据。前两个部分运行正常，但是数据抓取无效。下面是我的代码

Private Sub CommandButton1_Click()
Sheets("Sheet1").Select
Range(Cells(7, 1), Cells(ActiveSheet.UsedRange.Rows.Count, ActiveSheet.UsedRange.Columns.Count)).Delete
 'Sheets("Sheet1").Range("A3") = "Symbol"
 'Cells(3, 1).Font.Bold = True
Dim i As Long, strText As String

Dim doc As Object, hTable As Object, hBody As Object, hTR As Object, hTD As Object
 Dim tb As Object, bb As Object, Tr As Object, Td As Object

Dim y As Long, z As Long, wb As Excel.Workbook, ws As Excel.Worksheet

'Shell "RunDll32.exe Inetcpl.cpl,ClearMyTracksByProcess 11"

Set wb = Excel.ActiveWorkbook
 Set ws = wb.ActiveSheet

Set ie = CreateObject("InternetExplorer.Application")
    my_url = "https://www1.nseindia.com/products/content/equities/equities/eq_security.htm"

    With ie
        .Visible = True
        .navigate my_url
        .Top = 50
        .Left = 530
        .Height = 400
        .Width = 400

    Do Until Not ie.busy And ie.readyState = 4
        DoEvents
    Loop

    End With
' Input the userid and password
    'ie.document.getElementById("symbol").Value = Worksheets("Sheet1").Range("B1")
    ie.document.getElementById("symbol").Value = TextBox1.Text
    ie.document.getElementById("dateRange").selectedIndex = "4"
    ie.document.getElementById("get").Click
    

While ie.busy
 DoEvents
 Wend


 
 Set doc = ie.document
 Set hTable = doc.getElementsByTagName("table")


 y = 2 'Column B in Excel
 z = 3 'Row 3 in Excel
 For Each tb In hTable
 Set hHead = tb.getElementsByTagName("th")
 For Each hh In hHead
 Set hTR = hh.getElementsByTagName("tr")
 For Each Tr In hTR


 Set hTD = Tr.getElementsByTagName("th")
 y = 1 ' Resets back to column A
 For Each th In hTD
 ws.Cells(z, y).Value = th.innerText
 y = y + 1
 Next th
 DoEvents
 z = z + 1
 Next Tr
 Exit For
 Next hh
 Exit For

 Set hBody = tb.getElementsByTagName("tbody")
 For Each bb In hBody

 Set hTR = bb.getElementsByTagName("tr")
 For Each Tr In hTR


 Set hTD = Tr.getElementsByTagName("td")
 y = 1 ' Resets back to column A
 For Each Td In hTD
 ws.Cells(z, y).Value = Td.innerText
 y = y + 1
 Next Td
 DoEvents
 z = z + 1
 Next Tr
 Exit For
 Next bb
 z = z + 1
 Exit For
 Next tb
End Sub

有人可以帮我吗.. !!

Answer 1

尝试使用F12开发人员工具检查Table HTML元素，我们可以看到在tbody中只有一个<table>标签和一个<tbody>元素，第一行是标题行，其他是数据行。在标题行中，我们可以看到<th>元素不包含<tr>标签

 Set hTable = doc.getElementsByTagName("table")
 
 y = 2 'Column B in Excel
 z = 3 'Row 3 in Excel
 For Each tb In hTable
 Set hHead = tb.getElementsByTagName("th")
 For Each hh In hHead
 Set hTR = hh.getElementsByTagName("tr")
 For Each Tr In hTR

因此，如果我们使用上面的代码，则在找到<th>元素之后，它不会深入遍历表。

尝试引用以下代码：

Sub Test()
    Dim IE As Object
 
    Sheets("Sheet1").Select
    Dim i As Long, strText As String

    'Dim doc As Object, hTable As Object, hBody As Object, hTR As Object, hTD As Object
    'Dim tb As Object, bb As Object, tr As Object, Td As Object

    Dim y As Long, z As Long, wb As Excel.Workbook, ws As Excel.Worksheet

    'Shell "RunDll32.exe Inetcpl.cpl,ClearMyTracksByProcess 11"

    Set wb = Excel.ActiveWorkbook
    Set ws = wb.ActiveSheet

    Set IE = CreateObject("InternetExplorer.Application")
    my_url = "https://www1.nseindia.com/products/content/equities/equities/eq_security.htm"

    With IE
        .Visible = True
        .navigate my_url
        .Top = 50
        .Left = 530
        .Height = 800
        .Width = 800

    Do Until Not IE.busy And IE.readyState = 4
        DoEvents
    Loop

    End With
    ' Input the userid and password
    'ie.document.getElementById("symbol").Value = Worksheets("Sheet1").Range("B1")
    IE.document.getElementById("symbol").Value = "BAJFINANCE"
    IE.document.getElementById("dateRange").selectedIndex = "4"
    IE.document.getElementById("get").Click
    

    While IE.busy
        DoEvents
    Wend
 
    Set doc = IE.document
     
    y = 2
    z = 3
    
    Dim table As Object, tbody As Object, datarow As Object, thlist As Object, trlist As Object
    
    Application.Wait Now + TimeValue("00:00:02")
    
    'find the tbody. Since it only conatin one table and tbody
    Set tbody = IE.document.getElementsByTagName("table")(0).getElementsByTagName("tbody")(0)
    'find tha theader
    Set thlist = tbody.getElementsByTagName("tr")(0).getElementsByTagName("th")
     
    'Debug.Print thlist.Length
    
    'loop through the header column and capture the value.
    Dim ii As Integer
    For ii = 0 To thlist.Length - 1
        ws.Cells(z, y).Value = thlist(ii).innerText
        y = y + 1
    Next ii
    
    'get all data row
    Set datarow = tbody.getElementsByTagName("tr")
    
    'init the data row index and column index.
    y = 2
    z = 4
    
    'loop through the data row and get all td. and then capture the value.
    Dim jj As Integer
    Dim datarowtdlist As Object
    
    For jj = 1 To datarow.Length - 1
        Set datarowtdlist = datarow(jj).getElementsByTagName("td")
        
        'the x variable is used to set the column index.
        Dim hh As Integer, x As Integer
        x = y
        For hh = 0 To datarowtdlist.Length - 1
            ws.Cells(z, x).Value = datarowtdlist(hh).innerText
            x = x + 1
        Next hh
        z = z + 1
    Next jj
     
    Set IE = Nothing
    
End Sub

结果：

使用VBA抓取网页表数据

1 个答案: