Question

正如我先前的问题所指出的那样，我一直在尝试从Web站点抓取数据。由于社区的原因，我能够弄清楚我的问题是什么，但是现在我面临另一个问题。
这次我没有收到任何错误，但是程序没有将任何值导出到excel，我的页面仍然全部空白。
在我抓取的另一个网站上，HTML.Elements是divs，现在是spans，是因为这个原因吗？
这是我的代码：

Option Explicit
Public Sub Loiça()
    Dim data As Object, i As Long, html As HTMLDocument, r As Long, c As Long, item As Object, div As Object
    Set html = New HTMLDocument                  '<== VBE > Tools > References > Microsoft HTML Object Library

    Dim IE As New InternetExplorer
    Dim numPages As Long
    numPages = GetNumberOfPages

With CreateObject("MSXML2.XMLHTTP")
       ' numResults = arr(UBound(arr))
       ' numPages = 1

        For i = 1 To numPages
             If i > 1 Then
                .Open "GET", Replace$("https://mediamarkt.pt/pages/search-results-page?q=maquina+roupa&page=1", "page=1", "page=" & i), False
                .setRequestHeader "User-Agent", "Mozilla/5.0"
                .send
                 html.body.innerHTML = .responseText
            End If
            Set data = html.getElementsByClassName("snize-title")
            For Each item In data
                r = r + 1: c = 1
                For Each div In item.getElementsByTagName("span")
                    With ThisWorkbook.Worksheets("Loiça")
                        .Cells(r, c) = div.innerText
                    End With
                    c = c + 1
                Next
            Next
        Next
    End With
    '----------------------------------------------------------------------------------------------------------------------------------------------------------------------'
End Sub
Public Function GetNumberOfPages() As Long
    Dim IE As New InternetExplorer
    With IE
        .Visible = False
        .Navigate2 "https://mediamarkt.pt/pages/search-results-page?q=maquina+roupa&page=1"

        While .Busy Or .readyState < 4: DoEvents: Wend

        Dim numPages As Long, numResults As Long, arr() As String
        arr = Split(.document.querySelector(".snize-search-results-header").innerText, Chr$(32))
        numResults = arr(LBound(arr))
        GetNumberOfPages = numResults
        .Quit
    End With
End Function

Answer 1

该信息是动态加载的。您需要始终使用IE。另外，更改您的CSS选择器

Option Explicit

Public Sub WriterResults()
    Dim IE As New InternetExplorer, i As Long, data As Object, span As Object, item As Object, r As Long, c As Long
    With IE
        .Visible = True
        .Navigate2 "https://mediamarkt.pt/pages/search-results-page?q=maquina+roupa&page=1"

        While .Busy Or .readyState < 4: DoEvents: Wend

        Dim numPages As Long, numResults As Long, arr() As String
        arr = Split(.document.querySelector(".snize-search-results-header").innerText, Chr$(32))
        numResults = arr(LBound(arr))
        Dim resultsPerPage As Long
        resultsPerPage = .document.querySelectorAll(".snize-overhidden").Length
        numPages = Application.RoundUp(numResults / resultsPerPage, 0)
        For i = 1 To numPages
            If i > 1 Then
                .Navigate2 Replace$("https://mediamarkt.pt/pages/search-results-page?q=maquina+roupa&page=1", "page=1", "page=" & i)
                While .Busy Or .readyState < 4: DoEvents: Wend
            End If
            Set data = .document.getElementsByClassName("snize-overhidden")
            For Each item In data
                r = r + 1: c = 1
                For Each span In item.getElementsByTagName("span")
                    With ThisWorkbook.Worksheets("Loiça")
                        .Cells(r, c) = span.innerText
                    End With
                    c = c + 1
                Next
            Next
        Next
        .Quit
    End With
End Sub

VBA WebScraping没有返回任何优势

1 个答案: