Update app.py

app.py

@@ -1049,17 +1049,62 @@ def imprint_marks_using_mapping(pdf_path, grading_json, output_pdf, expected_ids
 def extract_pdf_pages_as_images(pdf_path, page_numbers, prefix):
     """
     Extracts unique pages (1-based) from a PDF as images, saves as PNG, returns list of file paths.
+    Handles cases where requested pages don't exist in the PDF.
     """
+    if not page_numbers:
+        print(f"⚠️ No page numbers provided for extraction")
+        return []
+    
     unique_pages = sorted(set(page_numbers))
-    images = convert_from_path(pdf_path, dpi=200, first_page=min(unique_pages), last_page=max(unique_pages))
+    
+    # First, get the total page count to validate requested pages
+    try:
+        from PyPDF2 import PdfReader
+        reader = PdfReader(pdf_path)
+        total_pages = len(reader.pages)
+        print(f"📄 PDF has {total_pages} total pages")
+        
+        # Filter out invalid page numbers
+        valid_pages = [p for p in unique_pages if 1 <= p <= total_pages]
+        invalid_pages = [p for p in unique_pages if p not in valid_pages]
+        
+        if invalid_pages:
+            print(f"⚠️ Skipping invalid page numbers (out of range): {invalid_pages}")
+        
+        if not valid_pages:
+            print(f"❌ No valid pages to extract from {pdf_path}")
+            return []
+        
+        unique_pages = valid_pages
+    except Exception as e:
+        print(f"⚠️ Could not validate page numbers: {e}. Proceeding with extraction...")
+    
+    # Extract the pages
+    try:
+        images = convert_from_path(pdf_path, dpi=200, first_page=min(unique_pages), last_page=max(unique_pages))
+    except Exception as e:
+        print(f"❌ Failed to convert PDF pages to images: {e}")
+        return []
+    
     out_paths = []
     for idx, page_num in enumerate(unique_pages):
         img_idx = page_num - min(unique_pages)
-        img = images[img_idx]
-        out_path = f"{prefix}_page_{page_num}.png"
-        img.save(out_path, "PNG")
-        print(f"📤 Extracted graph page {page_num} from {pdf_path} as {out_path}")
-        out_paths.append(out_path)
+        
+        # Bounds check to prevent index errors
+        if img_idx >= len(images):
+            print(f"⚠️ Page {page_num} not found in extracted images (index {img_idx} >= {len(images)}). Skipping...")
+            continue
+        
+        try:
+            img = images[img_idx]
+            out_path = f"{prefix}_page_{page_num}.png"
+            img.save(out_path, "PNG")
+            print(f"📤 Extracted graph page {page_num} from {pdf_path} as {out_path}")
+            out_paths.append(out_path)
+        except Exception as e:
+            print(f"❌ Failed to save page {page_num}: {e}")
+            continue
+    
     return out_paths
 
 # ---------------- PIPELINE ----------------
@@ -1189,9 +1234,9 @@ def align_and_grade_pipeline(qp_path, ms_path, ans_path, subject="Maths", imprin
         return f"❌ Error: {e}", None, None, None, None, {}
 
 # ---------------- GRADIO UI ---------------- 
-with gr.Blocks(title="AI Grading") as demo: 
-    gr.Markdown("## 📘 AI Grading ") 
-  
+with gr.Blocks(title="AI Grading (Pandoc + pdflatex)") as demo: 
+    gr.Markdown("## 📘 AI Grading — Using Pandoc + pdflatex for PDF Generation") 
+    gr.Markdown("**✅ Now using Pandoc with pdflatex for professional-quality PDF outputs!**")
     
     if supabase_client:
         gr.Markdown("**☁️ Supabase Storage: Enabled** - All files will be uploaded to cloud storage")