app.py

import pdfplumber
import pandas as pd
import re
import gradio as gr

def extract_data_from_pdf(pdf_file):
    data = []
    po_number = None

    # Open PDF file directly
    with pdfplumber.open(pdf_file.name) as pdf:
        for page in pdf.pages:
            text = page.extract_text()

            # Extract PO number (only once at the start)
            if po_number is None:
                po_match = re.search(r"Purchase Order : (\w+)", text)
                po_number = po_match.group(1) if po_match else "N/A"

            # Regex pattern for extracting rows
            row_pattern = re.compile(
                r"(\d+)\s+(\d{9})\s+(\w+)\s+(\d{4}-\d{2}-\d{2})\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)\s+INR\s+([\d.]+)"
            )

            # Extract each row using the pattern
            for match in row_pattern.finditer(text):
                pos, item_code, unit, delivery_date, quantity, basic_price, discount, amount = match.groups()

                # Extract subtotal if present
                sub_total_match = re.search(r"SUB TOTAL : ([\d.]+)", text)
                sub_total = sub_total_match.group(1) if sub_total_match else "0.0"

                # Append data for each matched row
                data.append({
                    "Purchase Order": po_number,
                    "Pos.": pos,
                    "Item Code": item_code,
                    "Unit": unit,
                    "Delivery Date": delivery_date,
                    "Quantity": quantity,
                    "Basic Price": basic_price,
                    "Discount": discount,
                    "Amount": amount,
                    "SUB TOTAL": sub_total,
                })

    # Convert data to DataFrame and save to Excel
    df = pd.DataFrame(data)
    output_file = "output.xlsx"
    df.to_excel(output_file, index=False)
    return output_file

# Gradio Interface
iface = gr.Interface(
    fn=extract_data_from_pdf,
    inputs=gr.File(label="Upload PDF"),
    outputs=gr.File(label="Download Excel"),
    title="PDF Data Extractor",
    description="Extract structured data from a PDF and output it as an Excel file.",
)
iface.launch()