Xbase++ Requires Chilkat v11.7.0+

Extract Text from Specific PDF Pages

See more PDF Text Extraction Examples

Demonstrates the "pages" option, which selects the pages to extract (a list of pages and ranges, or "first", "last", "odd", "even"), the "pageSeparator" option, and how to get the text of each page separately. Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL oJson
LOCAL oJsonOut
LOCAL i
LOCAL nCount_i

nSuccess := 0

//  This example requires the Chilkat API to have been previously unlocked.
//  See Global Unlock Sample for sample code.

//  The four-page PDF used in this example is available at four_pages.pdf

oPdf := CreateObject("Chilkat.Pdf")
nSuccess := oPdf:LoadFile("qa_data/pdf/four_pages.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

oJson := CreateObject("Chilkat.JsonObject")
oJsonOut := CreateObject("Chilkat.JsonObject")

//  Pages are numbered from 1.  The "pages" option can be "all" (the default), "first", "last",
//  "odd", "even", or a list such as "1,3,5-9,12-".  Here we extract pages 2 and 3.
oJson:UpdateString("pages", "2-3")

//  By default the pages in the joined text are separated by a form feed character.
//  Use any string instead:
oJson:UpdateString("pageSeparator", Chr(10) + "----- next page -----" + Chr(10))

nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? oJsonOut:StringOf("text")
? ""

//  The "pages" array has the text of each extracted page with its page number.
//  This is the way to keep the text of each page separate.
oJson:UpdateString("pages", "1,4")
nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

i := 0
nCount_i := oJsonOut:SizeOfArray("pages")
DO WHILE i < nCount_i
    oJsonOut:I := i
    ? "Page " + Str(oJsonOut:IntOf("pages[i].page")) + ": " + oJsonOut:StringOf("pages[i].text")
    i := i + 1
ENDDO

//  Sample output:

//  Chapter Two: The Crossing
//  
//  This is page two of four. The crossing takes forty minutes in calm weather. Today the sea was flat and the gulls followed the boat the whole way.
//  
//  ----- next page -----
//  Chapter Three: Arrival
//  
//  This is page three of four. The island harbor was busy with the morning catch being unloaded. The potatoes went straight up the hill to the store on a hand cart.
//  
//  
//  Page 1: Chapter One: Departure
//  
//  This is page one of four. The ferry left the north pier at seven in the morning with eleven passengers, two dogs and a crate of seed potatoes for the island store.
//  
//  Page 4: Chapter Four: Return
//  
//  This is page four of four. The ferry turned round within the hour and sailed back with the mail, three passengers and an empty crate.

oPdf:destroy()
oJson:destroy()
oJsonOut:destroy()