import fitz  # PyMuPDF
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
import io

def extract_and_recreate_pdf(input_pdf, output_pdf):
    # Open the input PDF
    doc = fitz.open(input_pdf)
    
    # List to store extracted images
    extracted_images = []
    output_streams = []

    # Extract text and images from each page
    for page_num in range(len(doc)):
        page = doc[page_num]
        text = page.get_text("text")  # Extract text
        images = page.get_images(full=True)

        # Extract images
        for img_index, img in enumerate(images):
            xref = img[0]
            base_image = doc.extract_image(xref)
            image_bytes = base_image["image"]
            extracted_images.append(io.BytesIO(image_bytes))

        # Store text and image streams for later
        output_streams.append((text, extracted_images))

    # Generate the new PDF
    c = canvas.Canvas(output_pdf, pagesize=letter)
    width, height = letter

    # Add extracted content to the new PDF
    for page_num, (text, images) in enumerate(output_streams):
        c.drawString(50, height - 50, f"Page {page_num + 1}")  # Page number
        c.drawString(50, height - 100, text)  # Add text

        # Add images
        for idx, img_stream in enumerate(images):
            img_stream.seek(0)
            img = fitz.Pixmap(img_stream)
            if img.n >= 4:  # Convert CMYK to RGB
                img = fitz.Pixmap(fitz.csRGB, img)
            img.save(f"temp_image_{idx}.png")  # Save as temp PNG
            c.drawImage(f"temp_image_{idx}.png", 50, height - 300 - (idx * 200), width=200, height=200)

        c.showPage()  # Add new page

    c.save()

# Specify input and output file paths
input_pdf_path = "input.pdf"  # Replace with your uploaded PDF file
output_pdf_path = "output_editable.pdf"
extract_and_recreate_pdf(input_pdf_path, output_pdf_path)
print("Editable PDF created successfully.")