Parse SUPER U monmagasin U ticket

main.py

#!/usr/bin/env python3

from asyncore import read
import argparse
from PyPDF2 import PdfReader
import re
import json

if __name__ == "__main__":

    parser = argparse.ArgumentParser(description="Parse super u ticket to json")
    parser.add_argument('filename', help="ticket pdf filename")
    args = parser.parse_args()

    filepath = args.filename

    reader = PdfReader(filepath)

    def to_float(number):
        comma = number.replace(',','.')
        return float(comma)

    for page in reader.pages:
        lines = page.extractText().split('\n')
        lines = [line for line in lines if line.strip()]

        # Remove useless
        is_ticket_find = False
        is_end_find = False
        filtered_lines = []
        for line in lines:
            if "ticket" in line.lower():
                is_ticket_find = True
            
            if "===" in line.lower():
                is_end_find = True

            if is_ticket_find and not is_end_find:
                filtered_lines.append(' '.join(line.split()))

        # keep only needed
        filtered_lines = filtered_lines[2:]

        # keep all on one line
        reduced_lines = []
        for index, line in enumerate(filtered_lines):
            if "€" in line:
                prev_line = filtered_lines[index-1]
                if "€" not in prev_line:
                    reduced_lines.append(f"{prev_line} {line}")
                else:
                    reduced_lines.append(line)

        products = []
        # parse all
        for line in reduced_lines:
            product = {}
            # parse name
            name = re.sub(r"(\s\d+,\d+\s€.*)", '', line)
            product['name'] = re.sub(r"(\s\d+\sx)", '', name)
            # parse prices
            prices = re.findall(r"(\d+,\d+)\s€", line)
            if len(prices) == 1:
                product['unit_price'] = to_float(prices[0])
                product['total_price'] = to_float(prices[0])
            elif len(prices) == 2:
                product['unit_price'] = to_float(prices[0])
                product['total_price'] = to_float(prices[1])
            else:
                print('not handled')

            products.append(product)

Just use main.py <ticket.pdf>