Update app.py

app.py

@@ -128,6 +128,9 @@ async def download_and_save_pdf(session, title, paper_info, directory):
         async with session.get(pdf_url) as response:
             pdf_content = await response.read()
         
+        if len(pdf_content) < 2048:  # Check if the PDF is less than 2KB
+            return f"Downloaded PDF for {title} is too small (less than 2KB). Skipping."
+        
         safe_title = safe_filename(title)
         filename = f"{safe_title}.pdf"
         filepath = os.path.join(directory, filename)
@@ -155,14 +158,16 @@ async def process_papers(data, directory, progress=gr.Progress()):
     return "\n".join(results)
 
 def zip_directory(directory):
-    """Zip the entire directory."""
+    """Zip the entire directory, excluding files smaller than 2KB."""
     zip_filename = f"{directory}.zip"
     with zipfile.ZipFile(zip_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
         for root, _, files in os.walk(directory):
             for file in files:
-                zipf.write(os.path.join(root, file), 
-                           os.path.relpath(os.path.join(root, file), 
-                                           os.path.join(directory, '..')))
+                file_path = os.path.join(root, file)
+                if os.path.getsize(file_path) >= 2048:  # Only include files 2KB or larger
+                    zipf.write(file_path, 
+                               os.path.relpath(file_path, 
+                                               os.path.join(directory, '..')))
     return zip_filename
 
 def get_base64_download_link(file_path):
@@ -196,7 +201,10 @@ def download_all_papers(progress=gr.Progress()):
     
     existing_links = get_existing_zip_links()
     
-    return f"All papers have been downloaded and saved in {zip_file}\n\n{results}", f"{download_link}<br><br>Previous downloads:<br>{existing_links}"
+    # Count successful downloads
+    successful_downloads = sum(1 for result in results.split('\n') if result.startswith("Successfully saved:"))
+    
+    return f"Papers downloaded: {successful_downloads} out of {len(all_data)}\nAll papers have been processed and saved in {zip_file}\n\n{results}", f"{download_link}<br><br>Previous downloads:<br>{existing_links}"
 
 with gr.Blocks() as demo:
     gr.Markdown("<h1><center>Papers Leaderboard</center></h1>")