Extract hyperlink using CSS selector query - excel

Question

I would like to extract the hyperlink from a webpage by using queryselector all, but there are no results coming out.
Below is my code.
Sub ScrapLink()
Application.ScreenUpdating = False
Dim IE As New InternetExplorer, html As HTMLDocument
Dim x As Long
Application.ScreenUpdating = False
With IE
IE.Visible = True
IE.Navigate "http://www.bursamalaysia.com/market/listed-companies/company-announcements/5978065"
While .Busy Or .ReadyState < 4: DoEvents: Wend
Application.Wait Now + TimeSerial(0, 0, 1)
DoEvents
With .Document.getElementById("bm_ann_detail_iframe").contentDocument
Dim links As Object, i As Long
Set links = .Document.querySelectorAll("p.att_download_pdf[href^='/FileAccess/apbursaweb/']")
For i = 1 To links.Length
With ThisWorkbook.Worksheets("Sheet1")
Range("A" & Rows.Count).End(xlUp).Offset(1).Value = links.Item(i - 1)
End With
Next i
.Quit
End With
End With
End Sub

Answer 1

You could just avoid the initial page and use the URL direct from the frame. This would be my preference unless you don't know, for some reason, this URL.
Option Explicit
Public Sub GetInfo()
Dim IE As New InternetExplorer, nodeList As Object, i As Long
With IE
.Visible = True
.navigate2 "http://disclosure.bursamalaysia.com/FileAccess/viewHtml?e=2906127"
While .Busy Or .readyState < 4: DoEvents: Wend
Set nodeList = .document.querySelectorAll(".att_download_pdf [href^='/FileAccess/apbursaweb/download']")
For i = 0 To nodeList.Length - 1
Debug.Print nodeList.item(i).href
Next
.Quit
End With
End Sub
Or you can jump right on over to the iframe src after page load:
Option Explicit
Public Sub GetInfo()
Dim IE As New InternetExplorer, nodeList As Object, i As Long
With IE
.Visible = True
.Navigate2 "http://www.bursamalaysia.com/market/listed-companies/company-announcements/5978065"
While .Busy Or .readyState < 4: DoEvents: Wend
.Navigate2 .document.querySelector("iframe").src
While .Busy Or .readyState < 4: DoEvents: Wend
Set nodeList = .document.querySelectorAll(".att_download_pdf [href^='/FileAccess/apbursaweb/download']")
For i = 0 To nodeList.Length - 1
Debug.Print nodeList.item(i).href
Next
.Quit
End With
End Sub

Answer 2

Try the following. It should fetch you the links you wish to grab:
Sub ScrapLink()
Dim IE As New InternetExplorer, Html As HTMLDocument
Dim frame As Object, i As Long
With IE
.Visible = True
.navigate "http://www.bursamalaysia.com/market/listed-companies/company-announcements/5978065"
While .Busy Or .readyState < 4: DoEvents: Wend
Set Html = .document
End With
Application.Wait Now + TimeValue("00:00:03") 'This delay may vary in your case
Set frame = Html.getElementById("bm_ann_detail_iframe").contentWindow.document
With frame.querySelectorAll("p.att_download_pdf a")
For i = 0 To .Length - 1
Cells(i + 1, 1) = .item(i).getAttribute("href")
Next i
End With
End Sub
If you wish to kick out the delay then try changing the portion below with the above one:
Do: Set frame = Html.getElementById("bm_ann_detail_iframe"): DoEvents: Loop While frame Is Nothing
With frame.contentWindow.document.querySelectorAll("p.att_download_pdf a")
For i = 0 To .Length - 1
Cells(i + 1, 1) = .item(i).getAttribute("href")
Next i
End With