How do I copy and paste data from pdf to excel? - excel

Question

Scenario: I have tons of Invoices received in my e-mail and saving them in a folder("C:\Users\Vbattul2\Desktop\Invoices\") and manually opening them one by one copying the needed data and pasting them to my excel tracker. Note that all the invoices have the same formats.
Opportunity to Automate: Automate the process of copy and paste of needed data from pdf and paste it to excel dummy worksheet(data delimited with colon & blank) and paste cell references in Excel invoice tracker.
Design: I will need to copy the pdf and paste it to a dummy worksheet then paste it to my excel invoice tracker.
I tried running this code from a thread posted 3 years ago:
VBA Copying data from pdf
I couldn't seem to understand this line, so it is returning me an
error: 1004 Method 'Range' of object'_Global failed
Line Error: For Each fName In Range("path")
I also tried replacing the ("path") to my folder path where I save all the invoices but it doesn't work.
Sub StartAdobe1()
Dim fName As Variant
Dim wbTransfer As Excel.Workbook
Dim wsNew As Excel.Worksheet
Dim dOpenCol As Double
Dim oPDFApp As AcroApp
Dim oAVDoc As AcroAVDoc
Dim oPDDoc As AcroPDDoc
'Define your spreadsheet
Set wbTransfer = Workbooks("transfer.xlsm")
Set wsNew = wbTransfer.Sheets("new")
'Find first open column
dOpenCol = wsNew.Cells(1, Columns.Count).End(xlToLeft).Column + 1
'Instantiate Acrobat Objects
Set oPDFApp = CreateObject("AcroExch.App")
Set oAVDoc = CreateObject("AcroExch.AVDoc")
Set oPDDoc = CreateObject("AcroExch.PDDoc")
For Each fName In Range("path")
'Open the PDF file. The AcroAVDoc.Open function returns a true/false
'to tell you if it worked
If oAVDoc.Open(fName.Text, "") = True Then
Set oPDDoc = oAVDoc.GetPDDoc
Else
Debug.Assert False
End If
'Copy all using Acrobat menu
oPDFApp.MenuItemExecute ("SelectAll")
oPDFApp.MenuItemExecute ("Copy")
'Paste into open column
wbTransfer.Activate
wsNew.Cells(1, dOpenCol).Select
ActiveSheet.Paste
'Select next open column
dOpenCol = dOpenCol + 1
oAVDoc.Close (1) '(1)=Do not save changes
oPDDoc.Close
Next
'Clean up
Set wbTransfer = Nothing
Set wsNew = Nothing
Set oPDFApp = Nothing
Set oAVDoc = Nothing
Set oPDDoc = Nothing
End Sub
i have uploaded an attachment where the actual result in dummy worksheet(paste as delimited values - colon & blank) should look like and the excel invoice tracker.
here are the links.
https://www.dropbox.com/preview/Marketing/desired%20output%20from%20pdf%20to%20excel.xlsm?role=work
https://www.dropbox.com/preview/Marketing/MRC%201380%20INVENTORY%202019.xlsb?role=work

Answer 1

So , what do you have now, all Excel files or all text files?
If all Excel files, try this.
Note: Copy all code below in a normal module of your workbook
#If VBA7 Then
Declare PtrSafe Function SetCurrentDirectoryA Lib _
"kernel32" (ByVal lpPathName As String) As Long
#Else
Declare Function SetCurrentDirectoryA Lib _
"kernel32" (ByVal lpPathName As String) As Long
#End If
Sub ChDirNet(szPath As String)
SetCurrentDirectoryA szPath
End Sub
Sub Basic_Example_2()
Dim MyPath As String
Dim SourceRcount As Long, Fnum As Long
Dim mybook As Workbook, BaseWks As Worksheet
Dim sourceRange As Range, destrange As Range
Dim rnum As Long, CalcMode As Long
Dim SaveDriveDir As String
Dim FName As Variant
'Change ScreenUpdating, Calculation and EnableEvents
With Application
CalcMode = .Calculation
.Calculation = xlCalculationManual
.ScreenUpdating = False
.EnableEvents = False
End With
SaveDriveDir = CurDir
ChDirNet "C:\Users\Ron\test"
FName = Application.GetOpenFilename(filefilter:="Excel Files (*.xl*), *.xl*", _
MultiSelect:=True)
If IsArray(FName) Then
'Add a new workbook with one sheet
Set BaseWks = Workbooks.Add(xlWBATWorksheet).Worksheets(1)
rnum = 1
'Loop through all files in the array(myFiles)
For Fnum = LBound(FName) To UBound(FName)
Set mybook = Nothing
On Error Resume Next
Set mybook = Workbooks.Open(FName(Fnum))
On Error GoTo 0
If Not mybook Is Nothing Then
On Error Resume Next
With mybook.Worksheets(1)
Set sourceRange = .Range("A1:C1")
End With
If Err.Number > 0 Then
Err.Clear
Set sourceRange = Nothing
Else
'if SourceRange use all columns then skip this file
If sourceRange.Columns.Count >= BaseWks.Columns.Count Then
Set sourceRange = Nothing
End If
End If
On Error GoTo 0
If Not sourceRange Is Nothing Then
SourceRcount = sourceRange.Rows.Count
If rnum + SourceRcount >= BaseWks.Rows.Count Then
MsgBox "Sorry there are not enough rows in the sheet"
BaseWks.Columns.AutoFit
mybook.Close savechanges:=False
GoTo ExitTheSub
Else
'Copy the file name in column A
With sourceRange
BaseWks.Cells(rnum, "A"). _
Resize(.Rows.Count).Value = FName(Fnum)
End With
'Set the destrange
Set destrange = BaseWks.Range("B" & rnum)
'we copy the values from the sourceRange to the destrange
With sourceRange
Set destrange = destrange. _
Resize(.Rows.Count, .Columns.Count)
End With
destrange.Value = sourceRange.Value
rnum = rnum + SourceRcount
End If
End If
mybook.Close savechanges:=False
End If
Next Fnum
BaseWks.Columns.AutoFit
End If
ExitTheSub:
'Restore ScreenUpdating, Calculation and EnableEvents
With Application
.ScreenUpdating = True
.EnableEvents = True
.Calculation = CalcMode
End With
ChDirNet SaveDriveDir
End Sub
If all text files, try this.
Option Explicit
#If VBA7 Then
Private Declare PtrSafe Function OpenProcess Lib "kernel32" _
(ByVal dwDesiredAccess As Long, _
ByVal bInheritHandle As Long, _
ByVal dwProcessId As Long) As Long
Private Declare PtrSafe Function GetExitCodeProcess Lib "kernel32" _
(ByVal hProcess As Long, _
lpExitCode As Long) As Long
#Else
Private Declare Function OpenProcess Lib "kernel32" _
(ByVal dwDesiredAccess As Long, _
ByVal bInheritHandle As Long, _
ByVal dwProcessId As Long) As Long
Private Declare Function GetExitCodeProcess Lib "kernel32" _
(ByVal hProcess As Long, _
lpExitCode As Long) As Long
#End If
Public Const PROCESS_QUERY_INFORMATION = &H400
Public Const STILL_ACTIVE = &H103
Public Sub ShellAndWait(ByVal PathName As String, Optional WindowState)
Dim hProg As Long
Dim hProcess As Long, ExitCode As Long
'fill in the missing parameter and execute the program
If IsMissing(WindowState) Then WindowState = 1
hProg = Shell(PathName, WindowState)
'hProg is a "process ID under Win32. To get the process handle:
hProcess = OpenProcess(PROCESS_QUERY_INFORMATION, False, hProg)
Do
'populate Exitcode variable
GetExitCodeProcess hProcess, ExitCode
DoEvents
Loop While ExitCode = STILL_ACTIVE
End Sub
Sub Merge_CSV_Files()
Dim BatFileName As String
Dim TXTFileName As String
Dim XLSFileName As String
Dim FileExtStr As String
Dim FileFormatNum As Long
Dim DefPath As String
Dim Wb As Workbook
Dim oApp As Object
Dim oFolder
Dim foldername
'Create two temporary file names
BatFileName = Environ("Temp") & _
"\CollectCSVData" & Format(Now, "dd-mm-yy-h-mm-ss") & ".bat"
TXTFileName = Environ("Temp") & _
"\AllCSV" & Format(Now, "dd-mm-yy-h-mm-ss") & ".txt"
'Folder where you want to save the Excel file
DefPath = Application.DefaultFilePath
If Right(DefPath, 1) <> "\" Then
DefPath = DefPath & "\"
End If
'Set the extension and file format
If Val(Application.Version) < 12 Then
'You use Excel 97-2003
FileExtStr = ".xls": FileFormatNum = -4143
Else
'You use Excel 2007 or higher
FileExtStr = ".xlsx": FileFormatNum = 51
'If you want to save as xls(97-2003 format) in 2007 use
'FileExtStr = ".xls": FileFormatNum = 56
End If
'Name of the Excel file with a date/time stamp
XLSFileName = DefPath & "MasterCSV " & _
Format(Now, "dd-mmm-yyyy h-mm-ss") & FileExtStr
'Browse to the folder with CSV files
Set oApp = CreateObject("Shell.Application")
Set oFolder = oApp.BrowseForFolder(0, "Select folder with CSV files", 512)
If Not oFolder Is Nothing Then
foldername = oFolder.Self.Path
If Right(foldername, 1) <> "\" Then
foldername = foldername & "\"
End If
'Create the bat file
Open BatFileName For Output As #1
Print #1, "Copy " & Chr(34) & foldername & "*.csv" _
& Chr(34) & " " & TXTFileName
Close #1
'Run the Bat file to collect all data from the CSV files into a TXT file
ShellAndWait BatFileName, 0
If Dir(TXTFileName) = "" Then
MsgBox "There are no csv files in this folder"
Kill BatFileName
Exit Sub
End If
'Open the TXT file in Excel
Application.ScreenUpdating = False
Workbooks.OpenText Filename:=TXTFileName, Origin:=xlWindows, StartRow _
:=1, DataType:=xlDelimited, TextQualifier:=xlDoubleQuote, _
ConsecutiveDelimiter:=False, Tab:=False, Semicolon:=False, Comma:=True, _
Space:=False, Other:=False
'Save text file as a Excel file
Set Wb = ActiveWorkbook
Application.DisplayAlerts = False
Wb.SaveAs Filename:=XLSFileName, FileFormat:=FileFormatNum
Application.DisplayAlerts = True
Wb.Close savechanges:=False
MsgBox "You find the Excel file here: " & vbNewLine & XLSFileName
'Delete the bat and text file you temporary used
Kill BatFileName
Kill TXTFileName
Application.ScreenUpdating = True
End If
End Sub
See the link below for all details.
https://www.rondebruin.nl/win/section3.htm
Also, consider using this very useful Excel AddIn.
https://www.rondebruin.nl/win/addins/rdbmerge.htm

Answer 2

You would probably well served if you first convert all PDF files into text files, and import all data from all text files into Multiple sheets in Excel.
Sub convertpdf2()
Dim AcroXApp As Acrobat.AcroApp
Dim AcroXAVDoc As Acrobat.AcroAVDoc
Dim AcroXPDDoc As Acrobat.AcroPDDoc
Dim Filename As String
Dim jsObj As Object
Dim NewFileName As String
Filename = "C:\your_path_here\test.pdf"
NewFileName = "C:\your_path_here\Desktop\test.txt"
Set AcroXApp = CreateObject("AcroExch.App")
'AcroXApp.Show
Set AcroXAVDoc = CreateObject("AcroExch.AVDoc")
AcroXAVDoc.Open Filename, "Acrobat"
Set AcroXPDDoc = AcroXAVDoc.GetPDDoc
Set jsObj = AcroXPDDoc.GetJSObject
jsObj.SaveAs NewFileName, "com.adobe.acrobat.plain-text"
AcroXAVDoc.Close False
AcroXApp.Hide
AcroXApp.Exit
End Sub
Or, put everything in all the text files into one single sheet in Excel, assuming all files have the same schema, of course.
Import several test files into separate sheets in Excel.
Sub CombineTextFiles()
'updateby Extendoffice 20151015
Dim xFilesToOpen As Variant
Dim I As Integer
Dim xWb As Workbook
Dim xTempWb As Workbook
Dim xDelimiter As String
Dim xScreen As Boolean
On Error GoTo ErrHandler
xScreen = Application.ScreenUpdating
Application.ScreenUpdating = False
xDelimiter = "|"
xFilesToOpen = Application.GetOpenFilename("Text Files (*.txt), *.txt", , "Kutools for Excel", , True)
If TypeName(xFilesToOpen) = "Boolean" Then
MsgBox "No files were selected", , "Kutools for Excel"
GoTo ExitHandler
End If
I = 1
Set xTempWb = Workbooks.Open(xFilesToOpen(I))
xTempWb.Sheets(1).Copy
Set xWb = Application.ActiveWorkbook
xTempWb.Close False
xWb.Worksheets(I).Columns("A:A").TextToColumns _
Destination:=Range("A1"), DataType:=xlDelimited, _
TextQualifier:=xlDoubleQuote, _
ConsecutiveDelimiter:=False, _
Tab:=False, Semicolon:=False, _
Comma:=False, Space:=False, _
Other:=True, OtherChar:="|"
Do While I < UBound(xFilesToOpen)
I = I + 1
Set xTempWb = Workbooks.Open(xFilesToOpen(I))
With xWb
xTempWb.Sheets(1).Move after:=.Sheets(.Sheets.Count)
.Worksheets(I).Columns("A:A").TextToColumns _
Destination:=Range("A1"), DataType:=xlDelimited, _
TextQualifier:=xlDoubleQuote, _
ConsecutiveDelimiter:=False, _
Tab:=False, Semicolon:=False, _
Comma:=False, Space:=False, _
Other:=True, OtherChar:=xDelimiter
End With
Loop
ExitHandler:
Application.ScreenUpdating = xScreen
Set xWb = Nothing
Set xTempWb = Nothing
Exit Sub
ErrHandler:
MsgBox Err.Description, , "Kutools for Excel"
Resume ExitHandler
End Sub
If you have Acrobat installed, you can try the script below.
Sub Convert_to_TXT()
Dim AcroXApp As Acrobat.AcroApp
Dim AcroXAVDoc As Acrobat.AcroAVDoc
Dim AcroXPDDoc As Acrobat.AcroPDDoc
Dim Filename As String
Dim jsObj As Object
Dim NewFileName As String
Const sPath = "C:\Users\Excel\Desktop\test\"
Const sExt = ".pdf"
Const dPath = "C:\Users\Excel\Desktop\test\"
Const dExt = ".txt"
Dim sName As String, dName As String, fCount As Long
'loop through all files in source
sName = Dir(sPath & "*" & sExt)
Do While sName <> ""
fCount = fCount + 1
'we have sName. Now figure out dName
dName = Left(sName, InStrRev(sName, ".") - 1) & dExt
Set AcroXApp = CreateObject("AcroExch.App")
'AcroXApp.Show
Set AcroXAVDoc = CreateObject("AcroExch.AVDoc")
AcroXAVDoc.Open sName, "Acrobat"
Set AcroXPDDoc = AcroXAVDoc.GetPDDoc
Set jsObj = AcroXPDDoc.GetJSObject
jsObj.SaveAs dName, "com.adobe.acrobat.plain-text"
'find the next file
sName = Dir
Loop
AcroXAVDoc.Close False
AcroXApp.Hide
AcroXApp.Exit
MsgBox "Found " & fCount & " files."
End Sub
If you do NOT have Acrobat installed, you can try the script below
Sub ConvertToTXT()
Dim file As Variant, wdDoc As Document
file = Dir("C:\your_path\" & "*.pdf") 'txt path
Do While (file <> "")
Set wdDoc = Documents.Open(Filename:="C:\your_path\" & file, ReadOnly:=True, _
AddToRecentFiles:=False, Format:=wdOpenFormatAuto, Visible:=False)
wdDoc.SaveAs2 Filename:="C:\your_path\" & Replace(file, ".pdf", ".txt"), _
FileFormat:=wdFormatPDF, AddToRecentFiles:=False
wdDoc.Close False
file = Dir
Loop
End Sub