Update app.py

app.py

@@ -3,13 +3,14 @@ import datetime
 from PIL import Image
 from fpdf import FPDF
 import gradio as gr
+from PyPDF2 import PdfReader, PdfWriter
 
 # Folder paths
 INPUT_FOLDER = "./input/"
 OUTPUT_FOLDER = "./output/"
 LOG_FOLDER = "./logs/"
 PROCESSED_IMAGE = os.path.join(OUTPUT_FOLDER, "processed_image.png")
-OUTPUT_PDF = os.path.join(OUTPUT_FOLDER, "processed_image.pdf")
+OUTPUT_PDF = os.path.join(OUTPUT_FOLDER, "processed_file.pdf")
 LOG_FILE = os.path.join(LOG_FOLDER, "conversion_log.txt")
 
 # Ensure required folders exist
@@ -18,56 +19,74 @@ os.makedirs(OUTPUT_FOLDER, exist_ok=True)
 os.makedirs(LOG_FOLDER, exist_ok=True)
 
 # Function to log conversion steps
-def log_conversion(status, input_image, output_file):
+def log_conversion(status, input_file, output_file):
     with open(LOG_FILE, "a") as log_file:
         log_file.write(f"{datetime.datetime.now()} - Status: {status}\n")
-        log_file.write(f"Input Image: {input_image}\n")
+        log_file.write(f"Input File: {input_file}\n")
         log_file.write(f"Output File: {output_file}\n\n")
 
-# Processing function
-def process_image(uploaded_image, width_inches, height_inches, dpi=300):
+# Processing function for PDF
+def process_pdf(uploaded_pdf, width_inches, height_inches, dpi=300):
     try:
-        # Save the uploaded image temporarily
-        input_image_path = os.path.join(INPUT_FOLDER, "uploaded_image.png")
-        uploaded_image.save(input_image_path)
-
-        # Convert inches to pixels (1 inch = dpi pixels)
-        width_pixels = int(width_inches * dpi)
-        height_pixels = int(height_inches * dpi)
-
-        # Open and process the image
-        with Image.open(input_image_path) as img:
-            grayscale_image = img.convert("L")  # Convert to grayscale
-            resized_image = grayscale_image.resize((width_pixels, height_pixels))  # Resize
-            resized_image.save(PROCESSED_IMAGE)
-
-        # Convert the processed image to PDF
-        pdf = FPDF(unit="in", format=(width_inches, height_inches))
-        pdf.add_page()
-        pdf.image(PROCESSED_IMAGE, x=0, y=0, w=width_inches, h=height_inches)
-        pdf.output(OUTPUT_PDF)
+        # Save the uploaded PDF temporarily
+        input_pdf_path = os.path.join(INPUT_FOLDER, "uploaded_file.pdf")
+        with open(input_pdf_path, "wb") as f:
+            f.write(uploaded_pdf.read())
+
+        # Read the PDF
+        reader = PdfReader(input_pdf_path)
+        writer = PdfWriter()
+
+        for page_num, page in enumerate(reader.pages):
+            # Extract the image from the PDF page
+            if "/XObject" in page["/Resources"]:
+                xObject = page["/Resources"]["/XObject"].get_object()
+                for obj in xObject:
+                    if xObject[obj]["/Subtype"] == "/Image":
+                        size = (xObject[obj]["/Width"], xObject[obj]["/Height"])
+                        data = xObject[obj].get_data()
+                        img = Image.frombytes("RGB", size, data)
+
+                        # Convert the image to grayscale and resize
+                        grayscale_image = img.convert("L")
+                        width_pixels = int(width_inches * dpi)
+                        height_pixels = int(height_inches * dpi)
+                        resized_image = grayscale_image.resize((width_pixels, height_pixels))
+
+                        # Save processed image temporarily
+                        processed_image_path = os.path.join(OUTPUT_FOLDER, f"processed_page_{page_num + 1}.png")
+                        resized_image.save(processed_image_path)
+
+                        # Add the processed image to the new PDF
+                        pdf = FPDF(unit="in", format=(width_inches, height_inches))
+                        pdf.add_page()
+                        pdf.image(processed_image_path, x=0, y=0, w=width_inches, h=height_inches)
+
+                        # Save the final PDF
+                        pdf.output(OUTPUT_PDF)
 
         # Log success
-        log_conversion("Success", input_image_path, OUTPUT_PDF)
+        log_conversion("Success", input_pdf_path, OUTPUT_PDF)
 
         # Return processed PDF and log file
         return OUTPUT_PDF, LOG_FILE
+
     except Exception as e:
-        log_conversion("Failed", "Uploaded Image", "Processing Error")
+        log_conversion("Failed", "Uploaded PDF", "Processing Error")
         return None, f"Error: {str(e)}"
 
 # Gradio Interface
 def gradio_app():
     with gr.Blocks() as demo:
-        gr.Markdown("# Image Grayscale Converter and Resizer (Inches to PDF)")
+        gr.Markdown("# PDF Grayscale Converter and Resizer")
 
         with gr.Row():
-            image_input = gr.Image(type="pil", label="Upload Image")
+            pdf_input = gr.File(type="file", label="Upload PDF File")
             with gr.Column():
                 width_input = gr.Number(value=8.5, label="Width (in inches)")
                 height_input = gr.Number(value=11.0, label="Height (in inches)")
 
-        process_button = gr.Button("Process Image to PDF")
+        process_button = gr.Button("Process PDF")
 
         with gr.Row():
             pdf_output = gr.File(label="Download Processed PDF")
@@ -75,8 +94,8 @@ def gradio_app():
 
         # Define the button click functionality
         process_button.click(
-            process_image,
-            inputs=[image_input, width_input, height_input],
+            process_pdf,
+            inputs=[pdf_input, width_input, height_input],
             outputs=[pdf_output, log_file_output],
         )