app.py

import fitz  # PyMuPDF
import pandas as pd

def extract_tables_from_pdf(pdf_path):
    # Open the PDF
    doc = fitz.open(pdf_path)

    tables = []

    # Iterate through the pages to extract text or structured data
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        
        # Get the text from the page, you can then parse it for tables
        text = page.get_text("text")
        
        # Example: Extracting data from text and forming a table
        # You might need to apply custom parsing depending on the structure of your PDF
        rows = text.split("\n")  # Split by newlines
        table_data = [row.split() for row in rows if row]  # Split by spaces, or another delimiter

        if table_data:
            tables.append(table_data)
    
    return tables

def save_tables_to_excel(tables, excel_output_path):
    with pd.ExcelWriter(excel_output_path, engine='openpyxl') as writer:
        for i, table in enumerate(tables):
            df = pd.DataFrame(table)  # Create a DataFrame from the table
            df.to_excel(writer, sheet_name=f"Sheet{i+1}", index=False)
    
    print(f"Excel file saved as: {excel_output_path}")

# Example usage
pdf_path = "your_pdf_file.pdf"
tables = extract_tables_from_pdf(pdf_path)
excel_output_path = "output.xlsx"
save_tables_to_excel(tables, excel_output_path)