Tcl Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. 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 packing slip used in this example is available at packing_slip.pdf

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/packing_slip.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The packing slip has the captions "Bill To" and "Ship To" side by side,
#  each with an address block below it.
CkJsonObject_UpdateString $json "label" "Ship To"

#  "below" means the value is the block of text directly under the label.
CkJsonObject_UpdateString $json "labelValue" "below"

#  With the default "flow" layout the lines of the block would be joined into one paragraph.
#  "lines" keeps each line of the address on its own line.
CkJsonObject_UpdateString $json "layout" "lines"

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 "Ship To:"
puts [CkJsonObject_stringOf $jsonOut text]
puts ""

CkJsonObject_UpdateString $json "label" "Bill To"
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 "Bill To:"
puts [CkJsonObject_stringOf $jsonOut text]
puts ""

#  A caption over a short paragraph works the same way.  Here the flow layout is better,
#  because the two lines are one piece of text.
CkJsonObject_UpdateString $json "label" "Special Instructions"
CkJsonObject_UpdateString $json "layout" "flow"
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 "Special Instructions:"
puts [CkJsonObject_stringOf $jsonOut text]

#  Sample output:

#  Ship To:
#  Frank Delgado
#  c/o Harbor Pet Boarding
#  9 Ferry Lane
#  Portside, WA 98001
#  
#  Bill To:
#  Frank Delgado
#  Apartment 3B
#  41 Mill Street
#  Portside, WA 98000
#  
#  Special Instructions:
#  Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut