VBA scrape src instead of href

Question

I am using the code below code but it brings the value of 'src' instead of 'href' for some reason. Anyone can help please?

Sub bringfox(txt As String)

Dim oHtml       As HTMLDocument
Dim oElement    As Object
Set oHtml = New HTMLDocument

maintext2 = "https://www.jjfox.co.uk/cigars/show/all.html"

With CreateObject("WINHTTP.WinHTTPRequest.5.1")
    .Open "GET", maintext2 & gr, False
    .send
    oHtml.body.innerHTML = .responseText
End With



counter = cnt
'oElement(i).Children(0).getAttribute ("href")
Set oElement = oHtml.getElementsByClassName("products-grid products-grid--max-3-col")(0).getElementsByTagName("a")
i = 0
While i < oElement.Length
    Debug.Print oElement(i).Children(0).getAttribute("href")

    i = i + 1

Wend


End Sub

Answer 1

You could try using a CSS selector.

#wrapper div.category-products > ul a

This is a reduced version of the full selector that targets a tags within the products category. You then parse the outerHTML for the hrefs as that is where the information is located.

---

Site image (Sample view)

---

Output from code (Sample view)

---

Code

Option Explicit
Public Sub GetInfo()
    Dim oHtml As HTMLDocument, nodeList As Object, currentItem As Long
    Const URL As String = "https://www.jjfox.co.uk/cigars/show/all.html"
    Set oHtml = New HTMLDocument
    With CreateObject("WINHTTP.WinHTTPRequest.5.1")
        .Open "GET", URL, False
        .send
        oHtml.body.innerHTML = .responseText
    End With

    Set nodeList = oHtml.querySelectorAll("#wrapper div.category-products > ul a")
    For currentItem = 0 To nodeList.Length - 1
        On Error Resume Next
        Debug.Print Split(Split(nodeList.item(currentItem).outerHTML, "<A href=")(1), ">")(0)
        On Error GoTo 0
    Next currentItem
End Sub

---

Or more simply, use the following

For currentItem = 0 To nodeList.Length - 1
    On Error Resume Next
    Debug.Print nodeList.item(currentItem).href
    On Error GoTo 0
Next currentItem