app.py

import gradio as gr
import PyPDF2
import json

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    try:
        pdf_reader = PyPDF2.PdfReader(pdf_file)
        extracted_text = ""
        for page in pdf_reader.pages:
            extracted_text += page.extract_text()
        
        # Basic parsing example (can be expanded for specific fields like "Invoice Number")
        parsed_data = {
            "Total Pages": len(pdf_reader.pages),
            "Extracted Text Preview": extracted_text[:500]  # Show first 500 characters
        }
        return json.dumps(parsed_data, indent=2)
    except Exception as e:
        return f"Error processing file: {str(e)}"

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Curify Parse Prototype")
    gr.Markdown("Upload a PDF document to extract and view structured data.")
    
    with gr.Row():
        pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
        result_output = gr.Textbox(label="Extracted Data", lines=20)
    
    extract_button = gr.Button("Extract Data")
    extract_button.click(extract_text_from_pdf, inputs=pdf_input, outputs=result_output)

demo.launch(share=True)