[英]How do I copy and paste data from pdf to excel?
場景:我在電子郵件中收到了大量的發票,並將它們保存在一個folder("C:\\Users\\Vbattul2\\Desktop\\Invoices\\")
然后手動手動打開它們,將所需的數據復制並粘貼到我的Excel跟蹤器。 請注意,所有發票都具有相同的格式。
自動化的機會:自動化從pdf復制和粘貼所需數據並將其粘貼到excel虛擬工作表(數據用冒號和空白分隔)的過程,並在Excel發票跟蹤器中粘貼單元格引用。
設計:我將需要復制pdf並將其粘貼到虛擬工作表中,然后將其粘貼到我的excel發票跟蹤器中。
我嘗試從3年前發布的線程運行此代碼:
我似乎無法理解這條線,因此它使我回想起
error: 1004 Method 'Range' of object'_Global failed
Line Error: For Each fName In Range("path")
我也嘗試將(“ path”)替換為我保存所有發票的文件夾路徑,但是它不起作用。
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
我上傳了一個附件,其中虛擬工作表中的實際結果(粘貼為定界值-冒號和空白)應與excel發票跟蹤器相似。
這里是鏈接。
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
如果您首先將所有PDF文件轉換為文本文件,然后將所有文本文件中的所有數據導入Excel中的多頁工作表,則可能會為您服務。
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
或者,當然,假設所有文件都具有相同的架構,請將所有文本文件中的所有內容放入Excel中的一張紙中。
將幾個測試文件導入Excel中的單獨工作表中。
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
如果您安裝了Acrobat,則可以嘗試以下腳本。
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
如果您尚未安裝Acrobat,則可以嘗試以下腳本
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
那么,您現在擁有所有Excel文件或所有文本文件嗎?
如果所有的都是Excel文件,請嘗試此操作。
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
如果所有文本文件,請嘗試此。
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
有關所有詳細信息,請參見下面的鏈接。
https://www.rondebruin.nl/win/section3.htm
另外,請考慮使用此非常有用的Excel加載項。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.