How to edit checkboxes and save changes in an editable pdf using the python pdfrw library?

Question

I am trying to edit checkboxes on an editable pdf according to user input. I am able to edit text fields using pdfrw as shown here: https://bostata.com/how-to-populate-fillable-pdfs-with-python/

#! /usr/bin/python

import os
import pdfrw


INVOICE_TEMPLATE_PATH = 'invoice_template.pdf'
INVOICE_OUTPUT_PATH = 'invoice.pdf'


ANNOT_KEY = '/Annots'
ANNOT_FIELD_KEY = '/T'
ANNOT_VAL_KEY = '/V'
ANNOT_RECT_KEY = '/Rect'
SUBTYPE_KEY = '/Subtype'
WIDGET_SUBTYPE_KEY = '/Widget'


def write_fillable_pdf(input_pdf_path, output_pdf_path, data_dict):
    template_pdf = pdfrw.PdfReader(input_pdf_path)
    annotations = template_pdf.pages[0][ANNOT_KEY]
    for annotation in annotations:
        if annotation[SUBTYPE_KEY] == WIDGET_SUBTYPE_KEY:
            if annotation[ANNOT_FIELD_KEY]:
                key = annotation[ANNOT_FIELD_KEY][1:-1]
                if key in data_dict.keys():
                    annotation.update(
                        pdfrw.PdfDict(AP=data_dict[key], V=data_dict[key])
                    )
    pdfrw.PdfWriter().write(output_pdf_path, template_pdf)


data_dict = {
   'business_name_1': 'Bostata',
   'customer_name': 'company.io',
   'customer_email': 'joe@company.io',
   'invoice_number': '102394',
   'send_date': '2018-02-13',
   'due_date': '2018-03-13',
   'note_contents': 'Thank you for your business, Joe',
   'item_1': 'Data consulting services',
   'item_1_quantity': '10 hours',
   'item_1_price': '$200/hr',
   'item_1_amount': '$2000',
   'subtotal': '$2000',
   'tax': '0',
   'discounts': '0',
   'total': '$2000',
   'business_name_2': 'Bostata LLC',
   'business_email_address': 'hi@bostata.com',
   'business_phone_number': '(617) 930-4294'
}

if __name__ == '__main__':
    write_fillable_pdf(INVOICE_TEMPLATE_PATH, INVOICE_OUTPUT_PATH, data_dict)

However, I am still having issues with saving the changes to checkbox values. Locally I am able to see the changes on a checkbox in my output file. However when I upload the file to an AWS S3 bucket, the changes are not saved. I am not sure what the issue is. Any help would be appreciated. Thank you!

tomatoeshift · Answer 1 · 2022-10-09T09:02:29.937

I will be refering to this PDF reference manual

Checkboxses are of type button (See reference manual Table 220).

Further, see chapter "12.7.4.2.3 Checkboxses".

Thus, fields "Apperance streams" (/AS) and "value" (/V) shall be set.

(Further, see chapter "12.5.5 Apperance streams". for info of that.)

field /AS needs to be set with pdfrw.PdfName.

Lastly, Acroform field NeedAppearances can be set to true, so all fields are visible by default (Reference manual table 218).

full code:

import os
import pdfrw

INVOICE_TEMPLATE_PATH = 'invoice_template.pdf'
INVOICE_OUTPUT_PATH   = 'invoice_output.pdf'

ANNOT_KEY = '/Annots'           # key for all annotations within a page
ANNOT_FIELD_KEY = '/T'          # Name of field. i.e. given ID of field
ANNOT_FORM_type = '/FT'         # Form type (e.g. text/button)
ANNOT_FORM_button = '/Btn'      # ID for buttons, i.e. a checkbox
ANNOT_FORM_text = '/Tx'         # ID for textbox
SUBTYPE_KEY = '/Subtype'
WIDGET_SUBTYPE_KEY = '/Widget'

def write_fillable_pdf(input_pdf_path, output_pdf_path, data_dict):
    template_pdf = pdfrw.PdfReader(input_pdf_path)
    for Page in template_pdf.pages:
        if Page[ANNOT_KEY]:
            for annotation in Page[ANNOT_KEY]:
                if annotation[ANNOT_FIELD_KEY] and annotation[SUBTYPE_KEY] == WIDGET_SUBTYPE_KEY :
                    key = annotation[ANNOT_FIELD_KEY][1:-1] # Remove parentheses
                    if key in data_dict.keys():
                        if annotation[ANNOT_FORM_type] == ANNOT_FORM_button:
                            # button field i.e. a checkbox
                            annotation.update( pdfrw.PdfDict( V=pdfrw.PdfName(data_dict[key]) , AS=pdfrw.PdfName(data_dict[key]) ))
                        elif annotation[ANNOT_FORM_type] == ANNOT_FORM_text:
                            # regular text field
                            annotation.update( pdfrw.PdfDict( V=data_dict[key], AP=data_dict[key]) )
    template_pdf.Root.AcroForm.update(pdfrw.PdfDict(NeedAppearances=pdfrw.PdfObject('true')))
    pdfrw.PdfWriter().write(output_pdf_path, template_pdf)

data_dict = {
    'item_1_amount': '123',
    'CheckBox1': 'Yes',
    'CheckBox2': 'Off'  }

if __name__ == '__main__':
    write_fillable_pdf(INVOICE_TEMPLATE_PATH, INVOICE_OUTPUT_PATH, data_dict)

How to edit checkboxes and save changes in an editable pdf using the python pdfrw library?

1 Answers1