app.py

import gradio as gr
import fitz  # PyMuPDF
import pandas as pd

# Function to convert PDF to DataFrame
def pdf_to_dataframe(pdf_path):
    # Open the PDF document
    doc = fitz.open(pdf_path)
    
    # Initialize an empty list to store text blocks
    text_blocks = []
    
    # Iterate through each page in the PDF
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        text = page.get_text("text")
        text_blocks.append(text)
    
    # Join all text blocks into a single string
    full_text = "\n".join(text_blocks)
    
    # Split the text into lines
    lines = full_text.split('\n')
    
    # Create a DataFrame from the lines
    df = pd.DataFrame(lines, columns=['Text'])
    
    return df

# Function to save DataFrame to Excel
def dataframe_to_excel(df, excel_path):
    # Save the DataFrame to an Excel file
    df.to_excel(excel_path, index=False)

# Main function
def main():
    def pdf_to_excel_function(pdf_file):
        # Save the uploaded PDF to a temporary file
        pdf_path = "temp.pdf"
        with open(pdf_path, "wb") as f:
            f.write(pdf_file.read())
        
        # Convert PDF to DataFrame
        df = pdf_to_dataframe(pdf_path)
        
        # Save DataFrame to Excel
        excel_path = "output.xlsx"
        dataframe_to_excel(df, excel_path)
        
        return excel_path
    
    # Create the Gradio interface
    iface = gr.Interface(
        fn=pdf_to_excel_function,
        inputs=gr.File(label="Upload PDF File"),
        outputs=gr.File[label="Download Excel File"],
        title="PDF to Excel Converter",
        description="Convert a PDF file to an Excel file."
    )
    
    # Launch the interface
    iface.launch()

if __name__ == "__main__":
    main()