VBA Web Scraping 脚本返回超出范围的下标

Question

问题：

我一直在尝试从网站上抓取数据，但它总是给我一个错误 Subscript OutOf Range。我不知道为什么。我在另一个网站上使用完全相同的代码，它工作得非常好。

是的，我已将 divs 更改为我想从中抓取的新网站。

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

    Const START_URL As String = "https://mediamarkt.pt/pages/search-results-page?q=maquina+roupa&page=1"

    With CreateObject("MSXML2.XMLHTTP")
        .Open "GET", START_URL, False
        .setRequestHeader "User-Agent", "Mozilla/5.0"
        .send
        html.body.innerHTML = .responseText
        Dim numPages As Long, numResults As Long, arr() As String
        arr = Split(html.querySelector(".snize-search-results-header").innerText, Chr$(32))
        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-four-columns")
            For Each item In data
                r = r + 1: c = 1
                For Each div In item.getElementsByTagName("div")
                    With ThisWorkbook.Worksheets("Loiça")
                        .Cells(r, c) = div.innerText
                    End With
                    c = c + 1
                Next
            Next
        Next
    End With
    '----------------------------------------------------------------------------------------------------------------------------------------------------------------------'
End Sub

Answer 1

这个

html.querySelector(".snize-search-results-header").innerText

返回一个空字符串，因此当您拆分时，您的 arr 中会出现 -1。

这个值可能需要 javascript 才能在页面上运行。检查返回的 html。我认为没有返回任何价值。使用 selenium 或 IE 之类的方法，让 js 在页面上运行并使用值更新内容

在这种情况下，你还需要 lbound，这样你就可以使用一个函数来返回使用 IE 的值

numPages  =  GetNumberOfPages 

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

对于下一页，您正在查看不同的类名（我认为）

Set data = html.getElementsByClassName("snize-product")

检查 html 以进行验证。