Xbase++ Requires Chilkat v11.7.0+

Extract Text from a PDF that Forbids Copying

See more PDF Text Extraction Examples

Demonstrates a PDF that opens without a password but whose permissions do not allow copying text. The "text", "markdown", "search" and "tables" operations fail with that reason; "assess" always works. Loading the PDF with the OwnerPassword property set grants owner rights, and extraction works. Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL oJson
LOCAL oJsonOut

nSuccess := 0

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

//  The PDF used in this example (owner password: owner-secret; copying not permitted) is available at no_copy_permission.pdf

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

//  The PDF opens without a password.
nSuccess := oPdf:LoadFile("qa_data/pdf/no_copy_permission.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

//  Extracting text is refused, because the PDF's permissions do not allow copying.
nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? "Extraction refused: " + oPdf:LastErrorText
ENDIF

//  "assess" reports only counts and ratings, never text, so it is always allowed.
nSuccess := oPdf:ExtractText("assess", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "rating: " + oJsonOut:StringOf("quality.rating")

//  Load with the owner password to get owner rights, which include copying.
oPdf:OwnerPassword := "owner-secret"
nSuccess := oPdf:LoadFile("qa_data/pdf/no_copy_permission.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

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

? oJsonOut:StringOf("text")

//  Sample output:

//  Extraction refused: ChilkatLog:
//    ExtractText:
//      ...
//        The PDF's permissions do not allow copying or extracting text (load it with the owner password to extract).
//      ...
//  rating: good
//  Visitor Leaflet
//  
//  Welcome to the harbor lighthouse. The tower is open on weekends from July to September.
//  
//  Please keep to the marked paths and do not climb on the breakwater.
//  
//  The lantern room is closed in high winds.

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