main.py

"""
Testing PDF Plumber and other methods on insurance claim forms
https://pypi.org/project/pdfplumber/
https://trepo.tuni.fi/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3
https://github.com/jsvine/pdfplumber
"""

import pdfplumber
from pdfplumber.utils.pdfinternals import resolve_and_decode, resolve

#pdf = pdfplumber.open("data/mib_claim_form_v0618_v2a.pdf")
pdf = pdfplumber.open("data/BPAAS12529.pdf")

def parse_field_helper(form_data, field, prefix=None):
    """ appends any PDF AcroForm field/value pairs in `field` to provided `form_data` list

        if `field` has child fields, those will be parsed recursively.
    """
    resolved_field = field.resolve()
    field_name = '.'.join(filter(lambda x: x, [prefix, resolve_and_decode(resolved_field.get("T"))]))
    if "Kids" in resolved_field:
        for kid_field in resolved_field["Kids"]:
            parse_field_helper(form_data, kid_field, prefix=field_name)
    if "T" in resolved_field or "TU" in resolved_field:
        # "T" is a field-name, but it's sometimes absent.
        # "TU" is the "alternate field name" and is often more human-readable
        # your PDF may have one, the other, or both.
        alternate_field_name  = resolve_and_decode(resolved_field.get("TU")) if resolved_field.get("TU") else None
        field_value = resolve_and_decode(resolved_field["V"]) if 'V' in resolved_field else None
        form_data.append([field_name, alternate_field_name, field_value])


form_data = []
fields = resolve(resolve(pdf.doc.catalog["AcroForm"])["Fields"])
for field in fields:
    parse_field_helper(form_data, field)

print(form_data)


"""
import pdfplumber

pdf_path = "data/mib_claim_form_v0618_v2a.pdf"

with pdfplumber.open(pdf_path) as pdf:
    page = pdf.pages[0]
    print(page.chars[0])

tablefinder = page.debug_tablefinder()
cells = tablefinder.cells
print("Cells")
print(cells)

image = page.to_image()
print(image)
table = page.extract_table()
print(table)

"""