parse_perfect_metaprint.py

import pdfplumber
import pandas as pd

def parse_perfect_metaprint(pdf_path):
    columns = [
        "Purchase Order No", "Purchase Order Date", "S. No", "Material No",
        "Material Description", "Qty", "Price", "Delivery Date", "Total Value", 
        "Vat%", "Amount Incl. VAT"
    ]
    data = []

    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            table = page.extract_table()
            if table:
                for row in table[1:]:  # Skip header row
                    data.append(row)

    # Create a DataFrame
    df = pd.DataFrame(data, columns=columns)
    return df