app.py

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

# Individual processing functions
def process_bhel(pdf_file):
    # Place the BHEL-specific code logic here
    return process_common(pdf_file, "BHEL Output.xlsx")

def process_federal_electric(pdf_file):
    # Place the Federal Electric-specific code logic here
    return process_common(pdf_file, "Federal Electric Output.xlsx")

def process_al_nisf(pdf_file):
    # Place the AL-NISF-specific code logic here
    return process_common(pdf_file, "AL-NISF Output.xlsx")

def process_common(pdf_file, output_name):
    """
    Generalized function for processing PDFs
    """
    # Replace this with common or specific processing logic
    with pdfplumber.open(pdf_file.name) as pdf:
        text = ""
        for page in pdf.pages:
            text += page.extract_text()

    # Example: Create dummy DataFrame
    data = {"Text": text}
    df = pd.DataFrame([data])
    df.to_excel(output_name, index=False)
    return output_name

# Dropdown processing function
def main_process(pdf_file, format_choice):
    if format_choice == "BHEL":
        return process_bhel(pdf_file)
    elif format_choice == "Federal Electric":
        return process_federal_electric(pdf_file)
    elif format_choice == "AL-NISF":
        return process_al_nisf(pdf_file)
    else:
        return None

# Gradio interface
iface = gr.Interface(
    fn=main_process,
    inputs=[
        gr.File(label="Upload PDF", file_types=[".pdf"]),
        gr.Dropdown(choices=["BHEL", "Federal Electric", "AL-NISF"], label="Select Format")
    ],
    outputs=gr.File(label="Download Processed File"),
    title="Consolidated PO Data Extractor",
    description="Select the format and upload a PDF to extract and download the data."
)

if __name__ == "__main__":
    iface.launch()