others.py

import pdfplumber
import pandas as pd

def extract_others_table(pdf_file):
    """Extracts general tabular data for unknown PO formats."""
    rows = []
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            table = page.extract_table()
            if table:
                rows.extend(table[1:])  # Skip header row

    # Use generic column names
    columns = [f"Column {i + 1}" for i in range(len(rows[0]))] if rows else []
    df = pd.DataFrame(rows, columns=columns)
    return df