pdf to image

app.py

@@ -1,62 +1,68 @@
 import gradio as gr
-import cv2
-import numpy as np
+import fitz  # PyMuPDF
 from PIL import Image
+import io
 
-def process_image(image):
+def convert_pdf_to_image(pdf_file):
     """
-    Process the uploaded image and return basic analysis
+    Convert PDF to image(s) and return the first page as PIL Image
     """
-    if image is None:
-        return "Please upload an image first.", None
+    if pdf_file is None:
+        return "Please upload a PDF file first.", None
     
-    # Convert PIL image to numpy array
-    img_array = np.array(image)
-    
-    # Basic image analysis
-    height, width = img_array.shape[:2]
-    channels = img_array.shape[2] if len(img_array.shape) > 2 else 1
-    
-    # Calculate basic statistics
-    mean_color = np.mean(img_array, axis=(0, 1))
-    
-    # Create a simple edge detection visualization
-    if len(img_array.shape) == 3:
-        gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
-    else:
-        gray = img_array
-    
-    edges = cv2.Canny(gray, 50, 150)
-    edges_colored = cv2.cvtColor(edges, cv2.COLOR_GRAY2RGB)
-    
-    # Create analysis text
-    analysis_text = f"""
-    **Image Analysis:**
-    - Dimensions: {width} x {height} pixels
-    - Channels: {channels}
-    - Mean Color: R={mean_color[0]:.1f}, G={mean_color[1]:.1f}, B={mean_color[2]:.1f}
-    """
-    
-    return analysis_text, edges_colored
+    try:
+        # Open the PDF file
+        pdf_document = fitz.open(pdf_file.name)
+        
+        # Get the first page
+        first_page = pdf_document[0]
+        
+        # Convert page to image (pixmap)
+        pix = first_page.get_pixmap(matrix=fitz.Matrix(2, 2))  # 2x zoom for better quality
+        
+        # Convert pixmap to PIL Image
+        img_data = pix.tobytes("png")
+        img = Image.open(io.BytesIO(img_data))
+        
+        # Close the PDF document
+        pdf_document.close()
+        
+        # Get PDF info
+        pdf_info = f"""
+        **PDF Conversion Results:**
+        - Total pages: {len(pdf_document)}
+        - First page converted to image
+        - Image size: {img.width} x {img.height} pixels
+        - Format: PNG
+        """
+        
+        return pdf_info, img
+        
+    except Exception as e:
+        return f"Error processing PDF: {str(e)}", None
 
 # Create the Gradio interface
-with gr.Blocks(title="Image Processor") as demo:
-    gr.Markdown("# 🖼️ Image Processor")
-    gr.Markdown("Upload an image to analyze it!")
+with gr.Blocks(title="PDF to Image Converter") as demo:
+    gr.Markdown("# 📄 PDF to Image Converter")
+    gr.Markdown("Upload a PDF file to convert the first page to an image!")
     
     with gr.Row():
         with gr.Column():
-            input_image = gr.Image(label="Upload Image", type="pil")
-            process_btn = gr.Button("Process Image", variant="primary")
+            pdf_input = gr.File(
+                label="Upload PDF File", 
+                file_types=[".pdf"],
+                file_count="single"
+            )
+            convert_btn = gr.Button("Convert to Image", variant="primary")
         
         with gr.Column():
-            analysis_output = gr.Markdown(label="Analysis Results")
-            processed_image = gr.Image(label="Processed Image (Edge Detection)")
+            conversion_output = gr.Markdown(label="Conversion Results")
+            converted_image = gr.Image(label="Converted Image (First Page)")
     
-    process_btn.click(
-        fn=process_image,
-        inputs=[input_image],
-        outputs=[analysis_output, processed_image]
+    convert_btn.click(
+        fn=convert_pdf_to_image,
+        inputs=[pdf_input],
+        outputs=[conversion_output, converted_image]
     )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,4 +1,3 @@
 gradio==5.49.0
-opencv-python==4.8.1.78
-Pillow==10.0.1
-numpy==1.24.3
+PyMuPDF==1.23.8
+Pillow==10.0.1