Tcl Requires Chilkat v11.7.0+

Extract the Values of PDF Form Fields

See more PDF Text Extraction Examples

Demonstrates the "formFields" filter. The values of AcroForm fields (text fields, choices, check boxes) are not part of the page's text and are left out by default; "include" places each value at its field's position in the reading order, where a label capture can pick it up. 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 filled-in form used in this example is available at filled_form.pdf

set pdf [new_CkPdf]

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

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  By default only the page's own text is returned: the captions, without the values typed into the fields.
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 "---- default ----"
puts [CkJsonObject_stringOf $jsonOut text]

#  With formFields included, each field's value appears where the field is on the page.
#  A checked check box appears as [x]; an unchecked one has no value.
CkJsonObject_UpdateString $json "formFields" "include"
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 "---- formFields: include ----"
puts [CkJsonObject_stringOf $jsonOut text]

#  A field value can be captured by the caption beside it, as for any other text.
CkJsonObject_UpdateString $json "label" "Email"
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 "Email: [CkJsonObject_stringOf $jsonOut text]"

#  Sample output:

#  ---- default ----
#  Membership Application
#  Name:
#  Email:
#  Phone:
#  Newsletter: Yes, send me the monthly newsletter
#  Volunteer: I am willing to volunteer
#  ---- formFields: include ----
#  Membership Application
#  Name: Dana Whitfield
#  Email: dana.whitfield@example.com
#  Phone: 555-0142
#  Newsletter: [x] Yes, send me the monthly newsletter
#  Volunteer: I am willing to volunteer
#  Email: dana.whitfield@example.com

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut