Update app.py

app.py

@@ -5,6 +5,16 @@ import gradio as gr
 import time
 import os
 import json
+import PyPDF2
+import io
+import asyncio
+import aiohttp
+import aiofiles
+from concurrent.futures import ThreadPoolExecutor
+import re
+from datetime import datetime
+import zipfile
+import base64
 
 def get_rank_papers(url, progress=gr.Progress(track_tqdm=True)):
     base_url = "https://paperswithcode.com"
@@ -99,6 +109,103 @@ def load_all_data():
     greatest_count, greatest_html = update_display("greatest")
     return top_count, top_html, new_count, new_html, greatest_count, greatest_html
 
+def safe_filename(title):
+    """Convert a string to a safe filename."""
+    return re.sub(r'[^\w\-_\. ]', '_', title)
+
+def create_date_directory():
+    """Create a directory named with the current date."""
+    date_str = datetime.now().strftime("%Y-%m-%d")
+    os.makedirs(date_str, exist_ok=True)
+    return date_str
+
+async def download_and_save_pdf(session, title, paper_info, directory):
+    pdf_url = paper_info['pdf_link']
+    if not pdf_url:
+        return f"No PDF link available for: {title}"
+    
+    try:
+        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)
+        
+        async with aiofiles.open(filepath, 'wb') as f:
+            await f.write(pdf_content)
+        
+        return f"Successfully saved: {filename}"
+    except Exception as e:
+        return f"Error saving PDF for {title}: {str(e)}"
+
+async def process_papers(data, directory, progress=gr.Progress()):
+    async with aiohttp.ClientSession() as session:
+        tasks = []
+        for title, paper_info in data.items():
+            task = asyncio.ensure_future(download_and_save_pdf(session, title, paper_info, directory))
+            tasks.append(task)
+        
+        results = []
+        for i, task in enumerate(asyncio.as_completed(tasks), start=1):
+            result = await task
+            results.append(result)
+            progress(i / len(tasks), f"Processed {i}/{len(tasks)} papers")
+    
+    return "\n".join(results)
+
+def zip_directory(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:
+                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):
+    """Create a base64 download link for a file."""
+    with open(file_path, "rb") as file:
+        content = file.read()
+        b64 = base64.b64encode(content).decode()
+        return f'<a href="data:application/zip;base64,{b64}" download="{os.path.basename(file_path)}">Download {os.path.basename(file_path)}</a>'
+
+def get_existing_zip_links():
+    """Get download links for existing zip files."""
+    links = []
+    for file in os.listdir('.'):
+        if file.endswith('.zip') and os.path.isfile(file):
+            links.append(get_base64_download_link(file))
+    return "<br>".join(links)
+
+def download_all_papers(progress=gr.Progress()):
+    all_data = {}
+    for category in ["top", "latest", "greatest"]:
+        cache_file = f"{category}_papers_cache.json"
+        data = load_cached_data(cache_file)
+        if data:
+            all_data.update(data)
+    
+    date_directory = create_date_directory()
+    results = asyncio.run(process_papers(all_data, date_directory, progress))
+    
+    zip_file = zip_directory(date_directory)
+    download_link = get_base64_download_link(zip_file)
+    
+    existing_links = get_existing_zip_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>")
     
@@ -120,6 +227,11 @@ with gr.Blocks() as demo:
         greatest_button = gr.Button("Refresh Leaderboard")
         greatest_button.click(fn=lambda: update_display("greatest"), inputs=None, outputs=[greatest_count, greatest_html])
 
+    download_button = gr.Button("📚 Download All Papers", variant="primary")
+    download_output = gr.Textbox(label="Download Status")
+    download_links = gr.HTML(label="Download Links")
+    download_button.click(fn=download_all_papers, inputs=None, outputs=[download_output, download_links])
+
     # Load initial data for all tabs
     demo.load(fn=load_all_data, outputs=[top_count, top_html, new_count, new_html, greatest_count, greatest_html])