Get pictures links from Google Search - excel

I am trying to get the pictures links from a searched link through google and this is my try
Sub Test()
Const sURL As String = "https://www.google.com.eg/search?q=baby&sxsrf=ALeKk01tyfvvxyYjaC0YctjxaY0RlvPnuw:1586804351129&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjB77TtiuboAhUl5uAKHR5KA2wQ_AUoAXoECBQQAw&biw=1280&bih=881"
Dim http As MSXML2.XMLHTTP60, html As MSHTML.HTMLDocument
Set http = New MSXML2.XMLHTTP60
Set html = New MSHTML.HTMLDocument
With http
.Open "Get", sURL, False
.send
html.body.innerHTML = .responseText
End With
Dim post As Object, i As Long
Set post = html.querySelectorAll(".mM5pbd .bRMDJf")
For i = 0 To post.Length - 1
Debug.Print post.Item(i).innerHTML
Next i
Stop
End Sub
First I got the post.Length only 20 while I expect about 300
Second I can't get the correct link for the picture as it seems it is base64 encrypted or something similar (I am not sure)
How can I get the real links for the picture and get all the links for all the pictures related?
I think it is solved for one point
Set post = html.querySelectorAll("a.VFACy.kGQAp")
For i = 0 To post.Length - 1
Debug.Print post.Item(i).href
Next i
But how to get all the links instead of the 20 links only?
** The links are not totally right, for example I got this link
https://www.fool.com/taxes/2018/03/27/are-you-having-a-baby-here-are-the-tax-breaks-you.aspx
While the correct link is
https://g.foolcdn.com/editorial/images/466737/new-parents-holding-newborn-baby-mom-dad-father-mother.jpg
** I tried using IE
Sub TestIE()
Dim ie As New InternetExplorer
Dim lastrow As Long
Dim i As Long
Dim j As Long
lastrow = Range("A" & Rows.Count).End(xlUp).Row
For i = 2 To lastrow
ie.Visible = True
ie.navigate "https://www.google.com.eg/search?q=baby&sxsrf=ALeKk01tyfvvxyYjaC0YctjxaY0RlvPnuw:1586804351129&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjB77TtiuboAhUl5uAKHR5KA2wQ_AUoAXoECBQQAw&biw=1280&bih=881"
While ie.Busy Or ie.readyState < 4: DoEvents: Wend
'querySelectorAll("a.VFACy.kGQAp")
Dim post As Object
Set post = ie.document.querySelectorAll("a.VFACy.kGQAp")
For j = 0 To post.Length - 1
Debug.Print post.Item(i).innerHTML
Next j
Next
End Sub
But in results I got the same innerhtml for all
<div class="sMi44c lNHeqe"><div class="WGvvNb" dir="ltr">Baby colic - Wikipedia</div><div class="fxgdke"><span dir="ltr">en.wikipedia.org</span></div>
</div>
Is using QuerySelectorAll different when dealing with IE?
** Another try
Dim post As Object
Set post = ie.document.querySelectorAll(".bRMDJf img")
Dim r As Long
For j = 0 To post.Length - 1
r = r + 1
Cells(r, 1).Value = post.Item(i).getAttribute("src")
Next j
Now I got 100 but not the links, it is base64 encryption for the pictures, moreover I found out the output is the same for all the pictures. I could decrypt the pictures but the quality is low .. and I got only 100 .. How can I increase the number of results and get the correct links?

Related

Webscrape inside a for loop - Follow up

Following my previous question Webscrape VBA with condition, I started trying to automate the procedure for a list of url from this website here that I prepared in my excel document. When I tried for 20 and 30 url it worked perfectly, yet when I increased it, a "Script out of range error" occurred concerning the ReDim in the GetNodesTextAsArray, do you have any idea why ?
After some research I Tried to replace it by a for loop but it doesn't chagne anything.
Public Sub WindInfo()
'VBE> Tools > References:
'1. Microsoft, XML v6
'2. Microsoft HTML Object Library
'3. Microsoft Scripting Runtime
Dim xhr As MSXML2.XMLHTTP60: Set xhr = New MSXML2.XMLHTTP60
Dim html As MSHTML.HTMLDocument: Set html = New MSHTML.HTMLDocument
Dim ws As Worksheet: Set ws = ThisWorkbook.Worksheets("Sheet1")
Dim url As String
Dim j As Integer
Dim r As Long
r = 1
For j = 1 To 20
url = Worksheets("List").Cells(j, 1).Value
With xhr
.Open "GET", url, False
.send
html.body.innerHTML = .responseText
End With
Dim generalities As Object, arrGen(), partsList As Object
Set generalities = html.querySelectorAll("#bloc_texte table ~ table li")
arrGen = GetNodesTextAsArray(generalities)
Dim parts As Object, numberOfParts As Long
Set partsList = html.querySelectorAll("h1 ~ h3, ul ~ h3")
If partsList.Length > 0 Then
numberOfParts = html.querySelectorAll("h1 ~ h3, ul ~ h3").Length / 2
Set parts = html.querySelectorAll("h3 + ul")
Dim i As Long, liNodes As Object, arr()
Dim html2 As MSHTML.HTMLDocument: Set html2 = New MSHTML.HTMLDocument
For i = 0 To numberOfParts - 1
ws.Cells(r, 1).Resize(1, UBound(arrGen)) = arrGen
html2.body.innerHTML = parts.Item(i).outerHTML & parts.Item(i + numberOfParts).outerHTML
Set liNodes = html2.querySelectorAll("li")
arr = GetNodesTextAsArray(liNodes)
ws.Cells(r, 5).Resize(1, UBound(arr)) = arr
r = r + 1
Next
Else
arr = GetNodesTextAsArray(html.querySelectorAll("#bloc_texte h1 + ul").Item(1).getElementsByTagName("li"))
ws.Cells(r, 1).Resize(1, UBound(arrGen)) = arrGen
ws.Cells(r, 5).Resize(1, UBound(arr)) = arr
r = r + 1
End If
Application.Wait (Now + TimeValue("0:00:01"))
Next
End Sub
Public Function GetNodesTextAsArray(ByVal nodeList As Object) As Variant()
Dim i As Long, results()
ReDim results(1 To nodeList.Length)
For i = 0 To nodeList.Length - 1
results(i + 1) = nodeList.Item(i).innerText
Next i
GetNodesTextAsArray = results
End Function
9/10 the problem with VBA webscraping is page loading related.
So what you want to do is try an error handler that Loops while the page loads, and then tests to see if the element appears on the page.
I'll leave the code to you, but the timing here is essentially everything since even status code checking and waiting for the document to be loaded checking, is not a guarantee everything you need is loaded.
Even with great tools like selenium and puppeteer you still need to check / handle element loading and timing, and cant just assume, since document loaded, the element is there.
makes sense?

eBay Product scraper

I am very limited on VBA,
The Code is in a Module, the code has a sub process as well, so sorry if I post the code wrong
A) open IE
B) Subprocess gets the data.
The code works fine on ebay.com but NOT for ebay.co.uk - can't work out why, also it converts urls to hyperlinks
It only does the first page, I need it to go through an X amount of pages - have a code but can't get it to work so have removed it.
Can the search query be run AFTER Ebay opens, so it opens, then search item is input to ebay and then code runs, or to run from a cell, IF its Cell A1 the data extracted needs to be pasted in A2 and below.
I have looked at elements for ebay.com and ebay.co.uk and they look the same to me, so can't work out why its not working as it works for 1 and not the other.
I did input the code for getting data from several pages it did not work. I know this code works as I have it for when I fetch urls from google
Public IE As New SHDocVw.InternetExplorer
Sub GetData()
Dim HTMLdoc As MSHTml.HTMLDocument
Dim othwb As Variant
Dim objShellWindows As New SHDocVw.ShellWindows
Set IE = CreateObject("internetexplorer.application")
With IE
.Visible = True
'.Navigate "https://www.ebay.co.uk/sch/i.html?_from=R40&_trksid=m570.l1313&_nkw=jackets&_sacat=0"
.Navigate "https://www.ebay.com/sch/i.html_from=R40&_nkw=ralph+lauren&_sacat=1059&LH_TitleDesc=0&_dmd=1&rt=nc"
While .Busy Or .readyState <> 4: DoEvents: Wend
Set HTMLdoc = IE.document
ProcessHTMLPage HTMLdoc
.Quit
End With
End Sub
code here
enter
'''''' THIS IS THE SUB PROCESS '''''
Sub ProcessHTMLPage(HTMLPage As MSHTml.HTMLDocument)
Dim HTMLItem As MSHTml.IHTMLElement
Dim HTMLItems As MSHTml.IHTMLElementCollection
Dim HTMLInput As MSHTml.IHTMLElement
Dim rownum As Long
rownum = 1
Set HTMLItems = HTMLPage.getElementsByClassName("s-item__title")
For Each HTMLItem In HTMLItems
Cells(rownum, 1).Value = HTMLItem.innerText
rownum = rownum + 1
Next HTMLItem
rownum = 1
Set HTMLItems = HTMLPage.getElementsByClassName("s-item__price")
For Each HTMLItem In HTMLItems
Cells(rownum, 2).Value = HTMLItem.innerText
rownum = rownum + 1
Next HTMLItem
rownum = 1
Set HTMLItems = HTMLPage.getElementsByClassName("s-item__link")
For Each HTMLItem In HTMLItems
Cells(rownum, 3).Value = HTMLItem.href
rownum = rownum + 1
Next HTMLItem
'Converts each text hyperlink selected into a working hyperlink from C1 to 25000 rows
Range("C1:C25000").Select
For Each xCell In Selection
ActiveSheet.Hyperlinks.Add Anchor:=xCell, Address:=xCell.Formula
Next xCell
Range("C1").Select
End Sub
Code for going to next page
pageNumber = 1
'i = 2
If pageNumber >= 6 Then Exit Do 'the first 6 pages
internetdata.getElementById("pnnext").click 'next web page
Do While internet.Busy Or internet.readyState <> 4
DoEvents
Loop
Set internetdata = internet.document
pageNumber = pageNumber + 1
Loop
Does not work on Ebay.co.uk - NO RESULTS ARE EXTRACTED - Works fine in ebay.com
Need it to get data from X amount of pages and NOT just 1 page
Can the search query be run AFTER Ebay opens, so it opens, then search item is input to ebay and then code runs, or to run from a cell, IF its Cell A1 the data extracted needs to be pasted in A2 and below.
This is my code for google search, I have got it working so the search comes from cell A1, I am look for something like this, I am going to see if I can use the ebay code with this. As this also does the first 25 pages in google search
enter Sub webpage()
Dim ie As Object
Dim htmlDoc As Object
Dim nextPageElement As Object
Dim div As Object
Dim link As Object
Dim url As String
Dim pageNumber As Long
Dim i As Long
' Takes seach from A1 and places it into google
url = "https://www.google.co.uk/search?q=" & Replace(Worksheets("Sheet1").Range("A1").Value, " ", "+")
Set ie = CreateObject("InternetExplorer.Application")
With ie
.Visible = True
.navigate url
Do While .Busy Or .readyState <> 4
DoEvents
Loop
End With
Application.Wait Now + TimeSerial(0, 0, 5)
Set htmlDoc = ie.document
pageNumber = 1
i = 2
Do
For Each div In htmlDoc.getElementsByTagName("div")
If div.getAttribute("class") = "r" Then
Set link = div.getElementsByTagName("a")(0)
Cells(i, 2).Value = link.getAttribute("href")
i = i + 1
End If
Next div
If pageNumber >= 25 Then Exit Do 'the first 25 pages
Set nextPageElement = htmlDoc.getElementById("pnnext")
If nextPageElement Is Nothing Then Exit Do
' Clicks web next page
nextPageElement.Click 'next web page
Do While ie.Busy Or ie.readyState <> 4
DoEvents
Loop
Application.Wait Now + TimeSerial(0, 0, 5)
Set htmlDoc = ie.document
pageNumber = pageNumber + 1
Loop
MsgBox "All Done"
Set ie = Nothing
Set htmlDoc = Nothing
Set nextPageElement = Nothing
Set div = Nothing
Set link = Nothing
End Sub
code here
Question 1: Why does it work for one domain but not the other?
To answer question 1 (the other questions should be new posts) - the html is not the same at all. The classes which work for ebay.com are not found in ebay.co.uk; So, your loop over collections doesn't do anything because they are count 0 (or length 0 with nodeLists if using querySelectorAll). Instead, you need branched code. Set your selectors based on the url domain.
I have used css selectors as this is the easiest, and fastest way, to select the required elements whilst maintaining the flexibility of a code re-factor to reduce the lines of repeated code.
Side note:
If you are unsure about whether your selection method will work across different pages you can do at least two things:
Right click > inspect element > visually check the class names are the same for the elements you are attempting to compare. So, if you are looking at product names, are the class names in the html the same on both pages?
You can use the search facility of the browser > open element tab via F12 then press Ctrl+F to pull up search box > enter your class name from the first page into this box in the second page and hit enter. You can also enter css selectors here and some cases regex. You will get a hit count telling you how many matches found. You can keep pressing enter to cycle through matches and each match will be highlighted in the html above, so you can easily compare if matched results are what you expected.
click image to enlarge
img url: https://i.stack.imgur.com/MWkEx.png
VBA:
Option Explicit
Public Sub GetData()
Dim htmlDoc As MSHTML.HTMLDocument, ie As SHDocVw.InternetExplorer, ws As Worksheet
Set ie = New SHDocVw.InternetExplorer
Set htmlDoc = New MSHTML.HTMLDocument
Set ws = ThisWorkbook.Worksheets("Sheet1")
With ie
.Visible = True
'.Navigate2 "https://www.ebay.co.uk/sch/i.html?_from=R40&_trksid=m570.l1313&_nkw=jackets&_sacat=0"
.Navigate2 "https://www.ebay.com/sch/i.html_from=R40&_nkw=ralph+lauren&_sacat=1059&LH_TitleDesc=0&_dmd=1&rt=nc"
While .Busy Or .readyState <> 4: DoEvents: Wend
Dim index As Long, HTMLItems As Object, rowNum As Long, xCell As Range
Dim cssSelectors(), i As Long
Select Case True
Case InStr(.document.URL, "ebay.co.uk") > 0
cssSelectors = Array(".gvtitle a", ".amt", ".gvtitle a")
Case InStr(.document.URL, "ebay.com") > 0
cssSelectors = Array(".s-item__title", ".s-item__price", ".s-item__link")
End Select
With ws
For i = LBound(cssSelectors) To UBound(cssSelectors)
rowNum = 1
Set HTMLItems = ie.document.querySelectorAll(cssSelectors(i))
For index = 0 To HTMLItems.length - 1
.Cells(rowNum, i + 1).Value = IIf(i = 2, HTMLItems.item(index).getAttribute("href"), HTMLItems.item(index).innerText)
rowNum = rowNum + 1
Next
Next
For Each xCell In .Range("C1:C25000") '<= all these really?
.Hyperlinks.Add Anchor:=xCell, Address:=xCell.Formula
Next xCell
End With
.Quit
End With
End Sub
If this works on eBay then you need to find out yourself why it's not working on ebay.co.uk. My point is if the code itself works than there is nothing we can help you with here. You need to take some time to investigate ebay.co.uk and find the differences as I am sure it's something minor. I can't help u fix code that isn't actually broken. I wish you luck though.

Excel Macro To Pull Google Image Links

The goal is to get images from Google Images that match the part numbers in my database. My code runs, and it pulls up the correct Google pages but refuses to put the links into the spreadsheet. I have tried everything I can think of, but as of now, I keep on getting Error 1004 (Application-defined or Object-defined error).`
Sub SearchBotGoogleImgLink()
Dim objIE As Object
Set IE = CreateObject("InternetExplorer.Application")
Dim HTMLdoc As HTMLDocument
Dim imgElements As IHTMLElementCollection
Dim imgElement As HTMLImg
Dim aElement As HTMLAnchorElement
Dim n As Integer
Dim i As Integer
Dim url As String
Dim url2 As String
Dim m As Long
Dim lastRow As Long
Dim url3 As String
Dim SearchRow As Long
Dim aEle As HTMLLinkElement
Worksheets("Sheet1").Select
SearchRow = 1
Do Until IsEmpty(ActiveSheet.Cells(SearchRow, 1))
Sheets("Sheet1").Select
Application.StatusBar = SearchRow - 1 & " of " & "4368" & " Items Done"
Item = Trim(ActiveSheet.Cells(SearchRow, 1))
url = "https://www.google.com/search?hl=en&biw=1600&bih=796&tbm=isch&sa=1&ei=CTOpW_2jO6nAjwT67rqACw&q=A2N0015C3KUU&oq=" & Cells(SearchRow, 1) & "&oq=A2N0015C3KUU&gs_l=img.12...0.0..1704...0.0..0.0.0.......1......gws-wiz-img.9wB6WwQJhwA"
Set objIE = New InternetExplorer
objIE.Visible = True
objIE.navigate url
Do While objIE.Busy = True Or objIE.readyState <> 4: DoEvents: Loop
For Each aEle In objIE.document.getElementsByTagName("IMG")
result = aEle
Sheets("Sheet1").Range(SearchRow & "C").Value = result
Sheets("Sheet1").Range(SearchRow & "D") = aEle.innerHTML
Sheets("Sheet1").Range(SearchRow & "F").Value = aEle.innerText
Debug.Print aEle.innerText
Next
Loop
'For i = 1 To lastRow
'url = "https://www.google.com/search?hl=en&biw=1600&bih=796&tbm=isch&sa=1&ei=CTOpW_2jO6nAjwT67rqACw&q=A2N0015C3KUU&oq=" & Cells(SearchRow, 1) & "&oq=A2N0015C3KUU&gs_l=img.12...0.0..1704...0.0..0.0.0.......1......gws-wiz-img.9wB6WwQJhwA"
Set HTMLdoc = objIE.document
Set imgElements = HTMLdoc.getElementsByTagName("IMG")
n = 1
For Each imgElement In imgElements
If InStr(ingElement.src, sImageSearchString) Then
If imgElement.ParentNode.nodeName = "A" Then
Set aElement = imgElement.ParentNode
If n = 2 Then
url2 = aElement.href 'imgElement.src
url3 = imgElement.src 'aElement.href
n = n + 1
End If
End If
End If
Next
Cells(SearchRow, 5) = url2
IE.Quit
Set IE = Nothing
End Sub
Notes on your code:
You need Option Explicit at the top of your code to check on variable declarations and typos amongst other advantages. There are a number of missing declarations e.g. result, and used ones later e.g. Set IE = CreateObject("InternetExplorer.Application"). You have two different variables (one late bound and one early) both creating IE instances. You only in fact use one.
Your current error may be down to you trying to work with an object here:
result = aEle which won't work without the Set keyword to provide the required reference.
Without example URLs and expected output it is difficult to advise on the later loops in your code. You appear to have a duplicate loop over IMG elements but this time with some restrictions. It is likely these loops can be merged.
An example:
The following uses an arbitrary concatenation in to pull the img src links in from search results based on A2N0015C3KUU.
It uses a CSS selector combination of #ires img[src] to target elements with img tags and src attributes within the parent element with id ires (search results).
It is to demonstrate the principle of gathering aNodeList of matching elements and writing out to a sheet. The querySelectorAll method applied the CSS selector combination to the HTMLDocument and returns the nodeList. The nodeList is looped along its .Length, with items accessed by index starting at 0.
Option Explicit
Public Sub GetInfo()
Dim IE As New InternetExplorer
With IE
.Visible = True
.navigate "https://www.google.com/search?hl=en&biw=1600&bih=796&tbm=isch&sa=1&ei=CTOpW_2jO6nAjwT67rqACw&q=A2N0015C3KUU&oq=1&%20%22&oq=A2N0015C3KUU&gs_l=img.12...0.0..1704...0.0..0.0.0.......1......gws-wiz-img.9wB6WwQJhwA"
While .Busy Or .readyState < 4: DoEvents: Wend
Dim aNodeList As Object, i As Long
Set aNodeList = IE.document.querySelectorAll("#ires img[src]")
For i = 0 To aNodeList.Length - 1
ActiveSheet.Cells(i + 2, 4) = aNodeList.item(i).src
Next
'Quit '<== Remember to quit application
End With
End Sub

Object does not support this property of method, while parsing html document

I want to scrap every post heading form this blog. I am using the code bellow but it's giving me an error "Run time error 438 object does not support this property or method" in line
Cells(i, 1).Value = ele.getElementsByClassName("entry-title")(0).getElementsByTagName("a")(0).innerText
The code is:
Private Sub CommandButton1_Click()
Dim bot As Object
Dim doc As New HTMLDocument
Dim ele As HTMLElementCollection
Dim i As Long
Set bot = CreateObject("MSXML2.XMLHTTP")
bot.Open "GET", "http://themakeupblogger.com/makeup/", False
bot.send
doc.body.innerHTML = bot.responseText
For Each ele In doc.getElementsByTagName("article")
i = Cells(Rows.Count, 1).End(xlUp).Row + 1
Cells(i, 1).Value = ele.getElementsByClassName("entry-title")(0).getElementsByTagName("a")(0).innerText
Next ele
End Sub
Give this a shot and get all the titles you are after.
Sub demo()
Dim http As New XMLHTTP60, html As New HTMLDocument
Dim r As Long, ele As Object
With http
.Open "GET", "http://themakeupblogger.com/makeup/", False
.send
html.body.innerHTML = .responseText
End With
For Each elem In html.getElementsByClassName("entry-title")
With elem.getElementsByTagName("a")
If .Length Then r = r + 1: Cells(r, 1) = .Item(0).innerText
End With
Next elem
End Sub
Reference to add to the library:
1. Microsoft XML, v6.0
2. Microsoft HTML Object Library
Partial results:
4 High-Coverage Foundations That Might As Well Be Skincare
10 Memorial Day Beauty Essentials That Belong In Your Beach Bag
Don’t Get Married Without These Wedding Day Makeup Tips (Courtesy of a Makeup Artist)
To get the articles from that page you can do something like:
Sub demo()
Dim http As New InternetExplorer, html As New HTMLDocument
Dim r As Long, elem As Object
With http
.Visible = False
.navigate "http://themakeupblogger.com/makeup/"
Do Until .readyState = READYSTATE_COMPLETE: Loop
Set html = .document
End With
For Each elem In html.getElementsByTagName("article")
With elem.getElementsByTagName("h1")
If .Length Then r = r + 1: Cells(r, 1) = .Item(0).getElementsByTagName("a")(0).innerText
End With
With elem.getElementsByTagName("div")(3).getElementsByTagName("p")
If .Length Then Cells(r, 2) = .Item(0).innerText
End With
Next elem
End Sub
This time the reference you should add to the library:
1. Microsoft Internet Controls
2. Microsoft HTML Object Library

web scraping using excel and VBA

i wrote my VBA code in excel sheet as below but it is not scrape data for me and also i don't know why please any one help me. it gave me reullt as "click her to read more" onlyi want to scrape enitre data such as first name last name state zip code and so on
Sub extractTablesData()
Dim IE As Object, obj As Object
Dim myState As String
Dim r As Integer, c As Integer, t As Integer
Dim elemCollection As Object
Set IE = CreateObject("InternetExplorer.Application")
myState = InputBox("Enter the city where you wish to work")
With IE
.Visible = True
.navigate ("http://www.funeralhomes.com/go/listing/Search? name=&city=&state=&country=USA&zip=&radius=")
While IE.readyState <> 4
DoEvents
Wend
For Each obj In IE.document.all.item("state").Options
If obj.innerText = myState Then
obj.Selected = True
End If
Next obj
IE.document.getElementsByValue("Search").item.Click
Do While IE.Busy: DoEvents: Loop
ThisWorkbook.Sheets("Sheet1").Range("A1:K1500").ClearContents
Set elemCollection = IE.document.getElementsByTagName("TABLE")
For t = 0 To (elemCollection.Length - 1)
For r = 0 To (elemCollection(t).Rows.Length - 1)
For c = 0 To (elemCollection(t).Rows(r).Cells.Length - 1)
ThisWorkbook.Worksheets(1).Cells(r + 1, c + 1) = elemCollection(t).Rows(r).Cells(c).innerText
Next c
Next r
Next t
End With
Set IE = Nothing
End Sub
Using the same URL as the answer already given you could alternatively select with CSS selectors to get the elements of interest, and use split to get just the names and address parts from the text. We can also do away with the browser altogether to get faster results from first results page.
Business name:
You can get the name with the following selector (using paid listing example):
div.paid-listing .listing-title
This selects (sample view)
Try
Address info:
The associated descriptive information can be retrieved with the selector:
div.paid-listing .address-summary
And then using split we can parse this into just the address information.
Code:
Option Explicit
Public Sub GetTitleAndAddress()
Dim oHtml As HTMLDocument, nodeList1 As Object, nodeList2 As Object, i As Long
Const URL As String = "http://www.funeralhomes.com/go/listing/ShowListing/USA/New%20York/New%20York"
Set oHtml = New HTMLDocument
With CreateObject("WINHTTP.WinHTTPRequest.5.1")
.Open "GET", URL, False
.send
oHtml.body.innerHTML = .responseText
End With
Set nodeList1 = oHtml.querySelectorAll("div.paid-listing .listing-title")
Set nodeList2 = oHtml.querySelectorAll("div.paid-listing .address-summary")
With Worksheets("Sheet3")
.UsedRange.ClearContents
For i = 0 To nodeList1.Length - 1
.Range("A" & i + 1) = nodeList1.Item(i).innerText
.Range("B" & i + 1) = Split(nodeList2.Item(i).innerText, Chr$(10))(0)
Next i
End With
End Sub
Example output:
Yeah, without an API, this can be very tricky at best, and very inconsistent at worst. For now, you can try the script below.
Sub DumpData()
Set IE = CreateObject("InternetExplorer.Application")
IE.Visible = True
URL = "http://www.funeralhomes.com/go/listing/ShowListing/USA/New%20York/New%20York"
'Wait for site to fully load
IE.Navigate2 URL
Do While IE.Busy = True
DoEvents
Loop
RowCount = 1
With Sheets("Sheet1")
.Cells.ClearContents
RowCount = 1
For Each itm In IE.document.all
If itm.classname Like "*free-listing*" Or itm.classname Like "*paid-listing*" Then
.Range("A" & RowCount) = itm.classname
.Range("B" & RowCount) = Left(itm.innertext, 1024)
RowCount = RowCount + 1
End If
Next itm
End With
End Sub
You probably want some kind of input box to capture the city and state and radius from the user, or capture those variable in cells in your worksheet.
Notice, the '%20' is a space character.
I got this idea from a friend of mine, Joel, a long time ago. That guy is great!

Resources