Web scraping with getElementsByTagName() - excel

Question

I want to import restaurant data like Restaurant name, phone number, website & address to excel but unfortunately I am getting ads & garbage data. I have created a code using http://automatetheweb.net/vba-getelementsbytagname-method/ website but it is not helping out. Please rectify the issue in my code.
Website:https://www.yellowpages.com/atlanta-ga/attorneys
Please donot refer json as it is not working on other webs.
Sub Yellowcom()
'Dim ieObj As InternetExplorer
Dim htmlELe As IHTMLElement
Dim HTML As HTMLDocument
Dim i As Integer
Dim URL As String
Dim URLParameter As String
Dim page As Long
Dim links As Object
Dim IE As Object
i = 1
Set IE = CreateObject("InternetExplorer.Application")
'Set ieObj = New InternetExplorer
IE.Visible = True
URL = "https://www.yellowpages.com/atlanta-ga/attorneys"
'Application.Wait Now + TimeValue("00:00:05")
For page = 2 To 4
If page > 1 Then URLParameter = "?page=" & page
IE.navigate URL & URLParameter
' Wait for the browser to load the page
Do Until IE.readyState = 4
DoEvents
Loop
Set HTML = IE.document
Set links = HTML.getElementsByClassName("info")
For Each htmlELe In links
With ActiveSheet
.Range("A" & i).Value = htmlELe.Children(0).textContent
.Range("B" & i).Value = htmlELe.getElementsByTagName("a")(0).href
.Range("C" & i).Value = htmlELe.Children(2).textContent
.Range("D" & i).Value = htmlELe.Children(2).querySelector("a[href]")
'links2 = htmlELe.getElementsByClassName("links")(1)
' .Range("D" & i).Value = links2.href
End With
i = i + 1
Next htmlELe
Next page
IE.Quit
Set IE = Nothing
End Sub
Required Output should be like this

Answer 1

I would use xhr rather than a browser and store data in an array for each page and write that out to sheet. You could really dimension one array to hold all results in advance based on results per page and number of pages but the below is still efficient
Option Explicit
Public Sub GetListings()
Dim html As HTMLDocument, page As Long, html2 As HTMLDocument
Dim results As Object, headers(), ws As Worksheet, i As Long
Const START_PAGE As Long = 1
Const END_PAGE As Long = 2
Set ws = ThisWorkbook.Worksheets("Sheet1")
headers = Array("Name", "Phone", "Website", "Address")
Application.ScreenUpdating = False
Set html = New HTMLDocument
Set html2 = New HTMLDocument
ws.Cells(1, 1).Resize(1, UBound(headers) + 1) = headers
With CreateObject("MSXML2.XMLHTTP")
For page = START_PAGE To END_PAGE
.Open "GET", "https://www.yellowpages.com/atlanta-ga/attorneys?page=" & page, False
.send
html.body.innerHTML = .responseText
Set results = html.querySelectorAll(".organic .result")
Dim output(), r As Long
ReDim output(1 To results.Length, 1 To 4)
r = 1
For i = 0 To results.Length - 1
On Error Resume Next
html2.body.innerHTML = results.item(i).outerHTML
output(r, 1) = html2.querySelector(".business-name").innerText
output(r, 2) = html2.querySelector(".phone").innerText
output(r, 3) = html2.querySelector(".track-visit-website").href
output(r, 4) = html2.querySelector(".street-address").innerText & " " & html2.querySelector(".locality").innerText
On Error GoTo 0
r = r + 1
Next
ws.Cells(GetLastRow(ws, 1) + 1, 1).Resize(UBound(output, 1), UBound(output, 2)) = output
Next
End With
Application.ScreenUpdating = True
End Sub
Public Function GetLastRow(ByVal ws As Worksheet, Optional ByVal columnNumber As Long = 1) As Long
With ws
GetLastRow = .Cells(.rows.Count, columnNumber).End(xlUp).Row
End With
End Function
Sample of output:

Answer 2

The info class is also used for the advertisements. You first need to go to the collection where the classname is "search-results organic" and in there find all the "info" classes.
This means that you need an extra collection variable:
Set HTML = IE.document
Set OrganicLinks = HTML.getElementsByClassName("search-results organic")
Set links = OrganicLinks.item(0).getElementsByClassName("info")
For getting the right website, you need to use another reference. It's better to get it by classname, since that one is more unique:
On Error Resume Next
.Range("B" & i).Value = htmlELe.getElementsByClassName("track-visit-website")(0).href
On Error GoTo 0