shahin
Active Member
Hi there! I've written some code to parse Name, Address and Phone number of different shops from yell.com. If any link is given to my crawler It parses the whole content irrespective of how many pages it has spread across. However, the only problem I could find out is that it always skips the content of first page, as in if there are 10 pages, my crawler scrapes last 9 pages. A little twitch might lead me to get a workaround. Here is the complete code. Thanks in advance.
Code:
Sub YellUK()
Const mlink = "https://www.yell.com"
Dim http As New MSXML2.XMLHTTP60, html As New HTMLDocument, htm As New HTMLDocument
Dim post As HTMLHtmlElement, page As Object, newlink As String
With http
.Open "GET", "https://www.yell.com/ucs/UcsSearchAction.do?keywords=pizza&location=United+Kingdom&scrambleSeed=1426936001", False
.send
html.body.innerHTML = .responseText
End With
Set page = html.getElementsByClassName("row pagination")(0).getElementsByTagName("a")
For i = 0 To page.Length - 1
newlink = mlink & Replace(page(i).href, "about:", "")
With http
.Open "GET", newlink, False
.send
htm.body.innerHTML = .responseText
End With
For Each post In htm.getElementsByClassName("js-LocalBusiness")
x = x + 1
With post.getElementsByClassName("row businessCapsule--title")(0).getElementsByTagName("a")
If .Length Then Cells(x + 1, 1) = .Item(0).innerText
End With
With post.getElementsByClassName("col-sm-10 col-md-11 col-lg-12 businessCapsule--address")(0).getElementsByTagName("span")
If .Length > 1 Then Cells(x + 1, 2) = .Item(1).innerText
End With
With post.getElementsByClassName("col-sm-10 col-md-11 col-lg-12 businessCapsule--address")(0).getElementsByTagName("span")
If .Length > 2 Then Cells(x + 1, 3) = .Item(2).innerText
End With
With post.getElementsByClassName("col-sm-10 col-md-11 col-lg-12 businessCapsule--address")(0).getElementsByTagName("span")
If .Length > 3 Then Cells(x + 1, 4) = .Item(3).innerText
End With
With post.getElementsByClassName("businessCapsule--tel")
If .Length > 1 Then Cells(x + 1, 5) = .Item(1).innerText
End With
Next post
Next i
End Sub
Last edited by a moderator:
