Tcl 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. Tcl

load ./chilkat.dll

set success 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

set pdf [new_CkPdf]

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The PDF opens without a password.
set success [CkPdf_LoadFile $pdf "qa_data/pdf/no_copy_permission.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

#  Extracting text is refused, because the PDF's permissions do not allow copying.
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts "Extraction refused: [CkPdf_lastErrorText $pdf]"
}

#  "assess" reports only counts and ratings, never text, so it is always allowed.
set success [CkPdf_ExtractText $pdf "assess" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "rating: [CkJsonObject_stringOf $jsonOut quality.rating]"

#  Load with the owner password to get owner rights, which include copying.
CkPdf_put_OwnerPassword $pdf "owner-secret"
set success [CkPdf_LoadFile $pdf "qa_data/pdf/no_copy_permission.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts [CkJsonObject_stringOf $jsonOut 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.

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut