parse_bhel.py

import pdfplumber
import pandas as pd

def parse_bhel_pdf(pdf_path):
    columns = [
        "Purchase Order No", "Date", "Sl No", "Material Description", 
        "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value"
    ]
    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