Update app.py

app.py

@@ -1,75 +1,58 @@
 import streamlit as st
 from PIL import Image
-import pytesseract  # For basic text extraction (optional)
-import pdfkit  # For PDF generation
-import os  # For temporary file handling
+import pdfkit
+import os
 
 # Function to process a single image with user-provided sequence number
 def process_image(image_file, sequence_number):
     image = Image.open(image_file)
-
-    # Optionally extract text using Tesseract (if needed for layout)
-    # text = pytesseract.image_to_string(image)  # May require Tesseract installation
-
-    # Consider techniques for layout analysis and image manipulation (if complex)
-
-    return image, sequence_number  # Return the image and its sequence number
+    return image, sequence_number
 
 # Function to generate the PDF
 def generate_pdf(images_with_sequence):
     pdf_name = "output.pdf"
 
-    # Create a temporary directory to store intermediate images (if needed)
-    # temp_dir = os.path.join(os.getcwd(), "temp_images")
-    # os.makedirs(temp_dir, exist_ok=True)
-
-    # Sort images by sequence number
     images_with_sequence.sort(key=lambda x: x[1])
 
+    config = pdfkit.configuration(wkhtmltopdf=r'/usr/bin/wkhtmltopdf') #provide your wkhtmltopdf path here
     pdf_options = {
         "margin-top": "0.5in",
         "margin-right": "0.5in",
         "margin-bottom": "0.5in",
         "margin-left": "0.5in",
         "encoding": "UTF-8",
-        "dpi": 300,  # Adjust as needed
+        "dpi": 300,
     }
-
-    # Generate PDF content (consider layout strategies if necessary)
-    pdfkit.from_file(
-        [image[0] for image in images_with_sequence],
-        pdf_name,
-        options=pdf_options,
-    )
-
-    # Clean up temporary files (if used)
-    # for filename in os.listdir(temp_dir):
-    #     os.remove(os.path.join(temp_dir, filename))
-
-    return pdf_name
+    try:
+        pdfkit.from_file([image[0] for image in images_with_sequence], pdf_name, options=pdf_options, configuration=config)
+        return pdf_name
+    except Exception as e:
+        st.error(f"Error generating PDF: {e}")
+        return None
 
 st.title("Image to PDF Converter (Multiple Images)")
 
 uploaded_images = st.file_uploader("Upload Images", type=["jpg", "jpeg", "png"], accept_multiple=True)
 
 if uploaded_images:
-    images_with_sequence = []
-
-    for image_file in uploaded_images:
-        st.image(image_file, width=250)  # Display uploaded images
-
-        sequence_options = [str(i) for i in range(1, len(uploaded_images) + 1)]
-        sequence_number = st.selectbox("Sequence Number", sequence_options)
-
-        processed_image, processed_sequence = process_image(image_file, int(sequence_number))
-        images_with_sequence.append((processed_image, processed_sequence))
-
-    if st.button("Generate PDF"):
-        pdf_name = generate_pdf(images_with_sequence)
-        st.success(f"PDF generated! Download: {pdf_name}")
-
-        with open(pdf_name, "rb") as pdf_file:
-            st.download_button("Download PDF", pdf_file, file_name=pdf_name)
-
-        # Delete the generated PDF after download (optional)
-        # os.remove(pdf_name)
+    num_images = len(uploaded_images)
+    if num_images > 0: #check if any image is uploaded
+        images_with_sequence = []
+
+        for i, image_file in enumerate(uploaded_images):
+            st.image(image_file, width=250)
+            sequence_options = [str(j) for j in range(1, num_images + 1)]
+            default_index = i #set default selection of sequence as the order of upload
+            sequence_number = st.selectbox(f"Sequence Number for Image {i+1}", sequence_options, index = default_index)
+            processed_image, processed_sequence = process_image(image_file, int(sequence_number))
+            images_with_sequence.append((processed_image, processed_sequence))
+
+        if st.button("Generate PDF"):
+            pdf_name = generate_pdf(images_with_sequence)
+            if pdf_name: #check if pdf is generated successfully
+                st.success(f"PDF generated! Download: {pdf_name}")
+                with open(pdf_name, "rb") as pdf_file:
+                    st.download_button("Download PDF", pdf_file, file_name=pdf_name)
+                os.remove(pdf_name) #remove the file after download
+else:
+    st.write("Please upload images to continue")