app.py

import fitz  # PyMuPDF for PDF processing
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
import streamlit as st
import tempfile
import os
from PIL import Image


def convert_pdf_to_images(pdf_path):
    """
    Converts PDF pages to images using PyMuPDF (fitz).
    """
    doc = fitz.open(pdf_path)
    image_paths = []
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        pix = page.get_pixmap(dpi=300)
        temp_image_path = f"temp_page_{page_num + 1}.png"
        pix.save(temp_image_path)
        image_paths.append(temp_image_path)
    return image_paths


def ocr_text_from_image(image_path):
    """
    Perform OCR on the given image to extract text.
    """
    image = Image.open(image_path)
    text = pytesseract.image_to_string(image, lang="eng")  # Use English OCR
    return text


def extract_to_editable_pdf(uploaded_file, output_pdf_path):
    """
    Extracts text using OCR and diagrams separately, and saves as an editable PDF.
    """
    # Save uploaded file temporarily
    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
        temp_file.write(uploaded_file.read())
        temp_file_path = temp_file.name

    # Convert PDF pages to images for OCR
    images = convert_pdf_to_images(temp_file_path)
    c = canvas.Canvas(output_pdf_path, pagesize=letter)

    for i, image_path in enumerate(images):
        # Extract text from the image using OCR
        text = ocr_text_from_image(image_path)

        # Write extracted text to the PDF
        c.drawString(50, 750, f"Page {i + 1}")  # Page header
        text_lines = text.split("\n")
        y = 730
        for line in text_lines:
            c.drawString(50, y, line)
            y -= 12  # Line spacing

        # Overlay original page image for diagrams
        c.drawImage(image_path, 50, 300, width=500, height=400)  # Adjust coordinates

        # Cleanup temporary image
        os.remove(image_path)

    c.save()

    # Cleanup temporary PDF
    os.remove(temp_file_path)


def main():
    """
    Streamlit app for converting PDFs into editable formats.
    """
    st.title("PDF to Editable CorelDRAW Converter")
    st.write("Upload a vector-based PDF to convert it into editable formats.")

    # File uploader for the user to upload a PDF
    uploaded_file = st.file_uploader("Upload PDF", type=["pdf"])

    if uploaded_file:
        # Process the uploaded PDF
        with st.spinner("Processing..."):
            output_pdf_path = "editable_output.pdf"
            extract_to_editable_pdf(uploaded_file, output_pdf_path)

        st.success("Processing complete!")

        # Provide a download button for the generated editable PDF
        with open(output_pdf_path, "rb") as f:
            st.download_button(
                label="Download Editable PDF",
                data=f,
                file_name="editable_output.pdf",
                mime="application/pdf"
            )

        # Cleanup generated output file
        os.remove(output_pdf_path)


if __name__ == "__main__":
    main()