Reading data from PDF and writing to a text file using QTP.

See main post here.



'Reading for example first three word of the first page of abc2.pdf and writing to r.txt.

strFileName = "C:\abc2.pdf"
Set AcroApp = CreateObject("AcroExch.App")
AcroApp.Show
Set AcroAVDoc = CreateObject("AcroExch.AVDoc")
AcroAVDoc.Open strFileName,""
Set AcroAVDoc = AcroApp.GetActiveDoc
Set AcroPDDoc = AcroAVDoc.GetPDDoc

For i = 0 To AcroPDDoc.GetNumPages - AcroPDDoc.GetNumPages

  ' AcquirePage: Acquires the specified page. The first page in a PDDoc is always 0. returns true if 
successful and false otherwise.

  Set PageNumber = AcroPDDoc.AcquirePage(i)

  'the Hilite list object is being created

   Set PageContent = CreateObject("AcroExch.HiliteList")
   PageContent.Add 0, 20 ' getting 3 words of first page.

 'text selection AcroTextSelect is being created

   Set AcroTextSelect = PageNumber.CreateWordHilite(PageContent)

   'GetNumText: Gets the number of text elements in a text selection. Use this method to 
determine how many times to call the PDTextSelect.GetText method to obtain all of a text selection’s text.

   For j = 0 To AcroTextSelect.GetNumText -1
        Content = Content & AcroTextSelect.GetText(j)
    Next
Next

msgbox Content

strFile = "c:\r.txt"
strText = Content

Set objFSO = CreateObject("Scripting.FileSystemObject")
Const ForAppending = 8

Set objTextFile = objFSO.OpenTextFile (strFile, ForAppending, True)
objTextFile.WriteLine(strText)
objTextFile.Close

AcroAVDoc.Close True
AcroApp.Exit
Set AcroDoc = Nothing
Set AcroApp = Nothing