Find string in PDF and return page number

masterc

New Member
Joined
Feb 12, 2019
Messages
5
Dear all,

I new tothe forum so please excuse me if this question has been asked.


I am looking for a macro that searches in a PDF file.
The strings are specified strings in column A of excel file
The pdf I select by button for example.
It should loop trough the rows with strings.

This is what I have so far however does not work in excel2016 and adobe reader DC. I can't see pdf file when I run it

Sub BatchRenameCS()
Dim objApp As Object
Dim objPDDoc As Object
Dim objjso As Object
Dim newPDF As Acrobat.CAcroPDDoc
Dim lastrow2 As Long
Dim strFileName As String
Dim Folder As String
Dim Page As Long
Dim Cell As Long
Dim PDFCharacterCount() As Long
Dim CharacterCount As Long
Dim i As Integer
Dim c As Integer
Dim x As Integer
Dim strSource As String
Dim strResult As String
Dim PDFCharacters As String
Dim PDFCharacters2 As String
Dim PDFPasteData() As String
Dim PasteDataPage As Integer
Dim LastRow As Long
Dim NewName As String
Dim NewNamePageNum As Integer
Dim Check()

Sheets("Sheet1").Range("C:D").ClearContents
strFileName = selectFile()
Folder = GetFolder()

'create array with pdf word count
Set objApp = CreateObject("AcroExch.App")
Set objPDDoc = CreateObject("AcroExch.PDDoc")
'AD.1 open file, if =false file is damage
If objPDDoc.Open(strFileName) Then
Set objjso = objPDDoc.GetJSObject

ReDim PDFCharacterCount(1 To objPDDoc.GetNumPages) As Long
For Page = 1 To objPDDoc.GetNumPages
PDFCharacters = ""
PDFCharacters2 = ""
For c = 0 To objjso.GetPageNumWords(Page - 1)
PDFCharacters = PDFCharacters & objjso.getPageNthWord(Page - 1, c)
Next c
For i = 1 To Len(PDFCharacters)
Select Case Asc(Mid(PDFCharacters, i, 1))
Case 48 To 57, 65 To 90, 97 To 122:
PDFCharacters2 = PDFCharacters2 & (Mid(PDFCharacters, i, 1))
Case Else
PDFCharacters2 = PDFCharacters2 & ""
End Select
Next
PDFCharacterCount(Page) = Len(PDFCharacters2)

Next Page
lastrow2 = Sheets("Sheet2").Cells(Rows.Count, "A").End(xlUp).Row
Page = 1
ReDim PDFPasteData(1 To objPDDoc.GetNumPages) As String
For Cell = 1 To lastrow2
strResult = ""
strSource = Sheets("Sheet2").Cells(Cell, 1).Text
PDFPasteData(Page) = PDFPasteData(Page) & " " & strSource
For i = 1 To Len(strSource)
Select Case Asc(Mid(strSource, i, 1))
Case 48 To 57, 65 To 90, 97 To 122:
strResult = strResult & (Mid(strSource, i, 1))
Case Else
strResult = strResult & ""
End Select
Next

CharacterCount = CharacterCount + Len(strResult)
If CharacterCount = PDFCharacterCount(Page) Then
CharacterCount = 0
Page = Page + 1
End If

Next Cell
ReDim Check(2, objPDDoc.GetNumPages)
LastRow = Sheets("Sheet1").Cells(Rows.Count, "A").End(xlUp).Row
For Each LookUpCell In Worksheets("Sheet1").Range("A2:A" & LastRow)
For PasteDataPage = 1 To objPDDoc.GetNumPages
If InStr(PDFPasteData(PasteDataPage), LookUpCell.Value) Then
Check(1, PasteDataPage) = Check(1, PasteDataPage) + 1
Check(2, PasteDataPage) = Check(2, PasteDataPage) & LookUpCell.Offset(0, 1).Value & Chr(10)
If FileExist(Folder & "" & LookUpCell.Offset(0, 1) & ".pdf") Then

Set newPDF = CreateObject("AcroExch.pdDoc")
NewName = Folder & "" & LookUpCell.Offset(0, 1) & ".pdf"
newPDF.Open (NewName)
newPDF.InsertPages newPDF.GetNumPages - 1, objPDDoc, PasteDataPage - 1, 1, 0
newPDF.Save 1, NewName
newPDF.Close
Set newPDF = Nothing
Else
Set newPDF = CreateObject("AcroExch.PDDoc")
newPDF.Create
NewName = Folder & "" & LookUpCell.Offset(0, 1) & ".pdf"
newPDF.InsertPages -1, objPDDoc, PasteDataPage - 1, 1, 0
newPDF.Save 1, NewName
newPDF.Close
Set newPDF = Nothing
End If
End If
Next PasteDataPage
Next LookUpCell
x = 1
For PasteDataPage = 1 To objPDDoc.GetNumPages
If Check(1, PasteDataPage) <> 1 Then
Sheets("Sheet1").Cells(x, 3) = PasteDataPage
Sheets("Sheet1").Cells(x, 4) = Check(2, PasteDataPage)
x = x + 1
End If
Next PasteDataPage
End If
MsgBox "Done"
End Sub
Function FileExist(path As String) As Boolean
If Dir(path) <> vbNullString Then FileExist = True
End Function
Function selectFile()
Dim fd As FileDialog, fileName As String
On Error GoTo ErrorHandler
Set fd = Application.FileDialog(msoFileDialogFilePicker)
fd.AllowMultiSelect = False
If fd.Show = True Then
If fd.SelectedItems(1) <> vbNullString Then
fileName = fd.SelectedItems(1)
End If
Else
'Exit code if no file is selected
End
End If
'Return Selected FileName
selectFile = fileName
Set fd = Nothing
Exit Function
ErrorHandler:
Set fd = Nothing
MsgBox "Error " & Err & ": " & Error(Err)
End Function
Function GetFolder() As String
Dim fldr As FileDialog
Dim sItem As String
Set fldr = Application.FileDialog(msoFileDialogFolderPicker)
With fldr
.Title = "Select the Folder where you want you new PDFs to go"
.AllowMultiSelect = False
.InitialFileName = Application.DefaultFilePath
If .Show <> -1 Then GoTo NextCode
sItem = .SelectedItems(1)
End With
NextCode:
GetFolder = sItem
Set fldr = Nothing

End Function




 

Excel Facts

What is =ROMAN(40) in Excel?
The Roman numeral for 40 is XL. Bill "MrExcel" Jelen's 40th book was called MrExcel XL.

Forum statistics

Threads
1,224,823
Messages
6,181,183
Members
453,020
Latest member
Mohamed Magdi Tawfiq Emam

We've detected that you are using an adblocker.

We have a great community of people providing Excel help here, but the hosting costs are enormous. You can help keep this site running by allowing ads on MrExcel.com.
Allow Ads at MrExcel

Which adblocker are you using?

Disable AdBlock

Follow these easy steps to disable AdBlock

1)Click on the icon in the browser’s toolbar.
2)Click on the icon in the browser’s toolbar.
2)Click on the "Pause on this site" option.
Go back

Disable AdBlock Plus

Follow these easy steps to disable AdBlock Plus

1)Click on the icon in the browser’s toolbar.
2)Click on the toggle to disable it for "mrexcel.com".
Go back

Disable uBlock Origin

Follow these easy steps to disable uBlock Origin

1)Click on the icon in the browser’s toolbar.
2)Click on the "Power" button.
3)Click on the "Refresh" button.
Go back

Disable uBlock

Follow these easy steps to disable uBlock

1)Click on the icon in the browser’s toolbar.
2)Click on the "Power" button.
3)Click on the "Refresh" button.
Go back
Back
Top