Update app.py

app.py

@@ -10,28 +10,164 @@ import io
 import asyncio
 import aiohttp
 import aiofiles
-from concurrent.futures import ThreadPoolExecutor
 import re
 from datetime import datetime
 import base64
 
-# ... (keep all the previous functions up to create_date_directory)
+# 🧙‍♂️ Magical Utility Functions 🧙‍♂️
+
+def safe_filename(title):
+    """Convert a string to a safe filename. No more 'file not found' nightmares! 🙅‍♂️📁"""
+    return re.sub(r'[^\w\-_\. ]', '_', title)
+
+def create_date_directory():
+    """Create a directory named with the current date. It's like a time capsule for your downloads! 🗓️📦"""
+    date_str = datetime.now().strftime("%Y-%m-%d")
+    os.makedirs(date_str, exist_ok=True)
+    return date_str
+
+def get_base64_download_link(content, filename):
+    """Create a base64 download link for text content. It's like teleportation for your files! 🌟📲"""
+    b64 = base64.b64encode(content.encode()).decode()
+    return f'<a href="data:text/plain;base64,{b64}" download="{filename}">Download {filename}</a>'
+
+# 🎬 Animated Banner Messages 🎬
+def animated_banner(message, emoji):
+    """Create an animated banner message. It's like a tiny parade for your console! 🎉🚩"""
+    frames = [
+        f"╔════ {emoji} ════╗\n║ {message:^16} ║\n╚════════════╝",
+        f"╔════ {emoji} ════╗\n║ {message:^16} ║\n╚════════════╝",
+        f"╔════{emoji}════╗\n║ {message:^14} ║\n╚══════════╝",
+        f"╔═══{emoji}═══╗\n║ {message:^12} ║\n╚════════╝",
+        f"╔══{emoji}══╗\n║ {message:^10} ║\n╚══════╝",
+        f"╔═{emoji}═╗\n║ {message:^8} ║\n╚════╝",
+        f"╔{emoji}╗\n║ {message:^6} ║\n╚══╝",
+    ]
+    return frames
+
+# 🕵️‍♂️ Data Fetching and Caching Shenanigans 🕵️‍♂️
+
+def get_rank_papers(url, progress=gr.Progress(track_tqdm=True)):
+    """Fetch papers from the interwebs. It's like fishing, but for knowledge! 🎣📚"""
+    base_url = "https://paperswithcode.com"
+    session = requests.Session()
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
+        'Cache-Control': 'no-cache'
+    }
+    print("Time run at : ", time.ctime())
+    offset = 0
+    data_list = {}
+    break_duplicate = 10
+    
+    while True:
+        response = session.get(url, headers=headers, params={'page': offset})
+        if response.status_code != 200:
+            print('Failed to retrieve data')
+            break
+        soup = BeautifulSoup(response.text, 'html.parser')
+        paper_info = soup.find_all('div', class_='row infinite-item item paper-card')
+        if not paper_info:
+            break
+        for ppr in paper_info:
+            title = ppr.find('h1').text.strip()
+            
+            if "paper" in ppr.find('a')['href']:
+                link = base_url + ppr.find('a')['href']
+            else:
+                link = ppr.find('a')['href'] 
+            Github_Star = ppr.find('span', class_='badge badge-secondary').text.strip().replace(',', '')
+            pdf_link = ''
+            try:
+                response_link = session.get(link, headers=headers)
+                soup_link = BeautifulSoup(response_link.text, 'html.parser')
+                paper_info_link = soup_link.find_all('div', class_='paper-abstract')
+                pdf_link = paper_info_link[0].find('div', class_='col-md-12').find('a')['href']
+            except:
+                pass
+            if title not in data_list:
+                data_list[title] = {'link': link, 'Github Star': int(Github_Star), 'pdf_link': pdf_link.strip()}
+            else:
+                break_duplicate -= 1
+                if break_duplicate == 0:
+                    return data_list
+        offset += 1 
+        progress.update(offset)
+    print('Data retrieval complete')   
+    return data_list
+
+def load_cached_data(cache_file):
+    """Load cached data. It's like finding money in your old jeans! 💰🧵"""
+    if os.path.exists(cache_file):
+        with open(cache_file, 'r') as f:
+            return json.load(f)
+    return None
+
+def save_cached_data(data, cache_file):
+    """Save data to cache. Future you will thank present you! 🦸‍♂️🕰️"""
+    with open(cache_file, 'w') as f:
+        json.dump(data, f)
+
+def load_and_cache_data(url, cache_file):
+    """Load data from cache or fetch new data. It's like a time machine for your data! ⏰🔄"""
+    cached_data = load_cached_data(cache_file)
+    
+    if cached_data:
+        print(f"Loading cached data from {cache_file}")
+        return cached_data
+    
+    print(f"Fetching new data from {url}")
+    new_data = get_rank_papers(url)
+    save_cached_data(new_data, cache_file)
+    return new_data
+
+# 📊 Data Processing and Display Magic 📊
+
+def format_dataframe(data):
+    """Format data into a pretty DataFrame. It's like giving your data a makeover! 💅📈"""
+    df = pd.DataFrame(data).T
+    df['title'] = df.index
+    df = df[['title', 'Github Star', 'link', 'pdf_link']]
+    df = df.sort_values(by='Github Star', ascending=False)
+    df['link'] = df['link'].apply(lambda x: f'<a href="{x}" target="_blank">Link</a>')
+    df['pdf_link'] = df['pdf_link'].apply(lambda x: f'<a href="{x}" target="_blank">{x}</a>')
+    return df
+
+def update_display(category):
+    """Update the display for a category. Freshen up your data like it's spring cleaning! 🧹🌸"""
+    cache_file = f"{category}_papers_cache.json"
+    url = f"https://paperswithcode.com/{category}" if category != "top" else "https://paperswithcode.com/"
+    
+    data = load_and_cache_data(url, cache_file)
+    df = format_dataframe(data)
+    
+    return len(df), df.to_html(escape=False, index=False)
+
+def load_all_data():
+    """Load data for all categories. It's like a buffet for your brain! 🧠🍽️"""
+    top_count, top_html = update_display("top")
+    new_count, new_html = update_display("latest")
+    greatest_count, greatest_html = update_display("greatest")
+    return top_count, top_html, new_count, new_html, greatest_count, greatest_html
+
+# 🚀 Asynchronous Paper Processing Wizardry 🚀
 
 async def download_and_process_pdf(session, title, paper_info, directory):
+    """Download and process a PDF. It's like turning lead into gold, but with papers! 📜✨"""
     pdf_url = paper_info['pdf_link']
     if not pdf_url:
-        return f"No PDF link available for: {title}", None, None
+        return f"🚫 No PDF link for: {title}. It's playing hide and seek! 🙈", None, None
     
     try:
         timeout = aiohttp.ClientTimeout(total=60)  # 60 seconds timeout
         async with session.get(pdf_url, timeout=timeout) as response:
             if response.status != 200:
-                return f"Failed to download PDF for {title}: HTTP {response.status}", None, None
+                return f"🚨 Failed to grab PDF for {title}: HTTP {response.status}. The internet gremlins strike again! 👹", None, None
             pdf_content = await response.read()
         
         file_length = len(pdf_content)
         if file_length < 5000:  # Check if the PDF is less than 5KB
-            return f"Downloaded PDF for {title} is too small ({file_length} bytes). Skipping.", None, None
+            return f"🐜 PDF for {title} is tiny ({file_length} bytes). It's like a paper for ants! 🐜📄", None, None
         
         # Convert PDF to text
         pdf_file = io.BytesIO(pdf_content)
@@ -41,7 +177,7 @@ async def download_and_process_pdf(session, title, paper_info, directory):
             text += page.extract_text()
         
         if len(text) < 5000:  # Check if the extracted text is less than 5KB
-            return f"Extracted text for {title} is too small ({len(text)} characters). Skipping.", None, None
+            return f"📉 Extracted text for {title} is too small ({len(text)} characters). It's not you, it's the PDF! 💔", None, None
         
         safe_title = safe_filename(title)
         txt_filename = f"{safe_title}.txt"
@@ -50,13 +186,14 @@ async def download_and_process_pdf(session, title, paper_info, directory):
         async with aiofiles.open(txt_filepath, 'w', encoding='utf-8') as f:
             await f.write(text)
         
-        return f"Successfully processed: {txt_filename} (File length: {file_length} bytes)", txt_filepath, text
+        return f"🎉 Successfully processed: {txt_filename} (File length: {file_length} bytes). It's alive! 🧬", txt_filepath, text
     except asyncio.TimeoutError:
-        return f"Timeout while downloading PDF for {title}", None, None
+        return f"⏳ Timeout for {title}. The PDF is playing hard to get! 💃", None, None
     except Exception as e:
-        return f"Error processing PDF for {title}: {str(e)}", None, None
+        return f"💥 Oops! Error processing {title}: {str(e)}. Gremlins in the system! 🛠️", None, None
 
 async def process_papers(data, directory, progress=gr.Progress()):
+    """Process multiple papers asynchronously. It's like juggling papers, but faster! 🤹‍♂️📚"""
     async with aiohttp.ClientSession() as session:
         tasks = []
         for title, paper_info in data.items():
@@ -73,16 +210,19 @@ async def process_papers(data, directory, progress=gr.Progress()):
                 successful_downloads.append((filepath, text))
             else:
                 errors.append(result)
-            progress(i / len(tasks), f"Processed {i}/{len(tasks)} papers")
+            progress(i / len(tasks), f"🚀 Processed {i}/{len(tasks)} papers. Science waits for no one!")
+            
+            # Display animated banner
+            banner_frames = animated_banner("Processing", "📄")
+            for frame in banner_frames:
+                print(frame, end='\r')
+                await asyncio.sleep(0.1)
+            print(" " * len(banner_frames[-1]), end='\r')  # Clear the last frame
     
     return results, successful_downloads, errors
 
-def get_base64_download_link(content, filename):
-    """Create a base64 download link for text content."""
-    b64 = base64.b64encode(content.encode()).decode()
-    return f'<a href="data:text/plain;base64,{b64}" download="{filename}">Download {filename}</a>'
-
 def download_all_papers(progress=gr.Progress()):
+    """Download and process all papers. It's like hosting a paper party, and everyone's invited! 🎉📚"""
     all_data = {}
     for category in ["top", "latest", "greatest"]:
         cache_file = f"{category}_papers_cache.json"
@@ -93,20 +233,22 @@ def download_all_papers(progress=gr.Progress()):
     date_directory = create_date_directory()
     results, successful_downloads, errors = asyncio.run(process_papers(all_data, date_directory, progress))
     
-    summary = f"Papers processed: {len(all_data)}\n"
-    summary += f"Successfully downloaded and converted: {len(successful_downloads)}\n"
-    summary += f"Errors: {len(errors)}\n\n"
-    summary += "Error List:\n" + "\n".join(errors) if errors else "No errors occurred."
+    summary = f"📊 Papers processed: {len(all_data)} (We're basically librarians now!)\n"
+    summary += f"✅ Successfully downloaded and converted: {len(successful_downloads)} (Take that, PDF gremlins!)\n"
+    summary += f"❌ Errors: {len(errors)} (Even superheroes have off days)\n\n"
+    summary += "🚨 Error List (AKA 'The Wall of Shame'):\n" + "\n".join(errors) if errors else "No errors occurred. It's a miracle! 🙌"
     
     download_links = []
     text_contents = []
     for filepath, text in successful_downloads:
         filename = os.path.basename(filepath)
         download_links.append(get_base64_download_link(text, filename))
-        text_contents.append(f"--- {filename} ---\n\n{text[:1000]}...\n\n")  # Show first 1000 characters
+        text_contents.append(f"--- {filename} ---\n\n{text[:1000]}... (There's more, but we don't want to spoil the ending! 📚🔮)\n\n")
     
     return summary, "<br>".join(download_links), "\n".join(text_contents)
 
+# 🎭 Gradio Interface: Where the Magic Happens 🎭
+
 with gr.Blocks() as demo:
     gr.Markdown("<h1><center>Papers Leaderboard</center></h1>")
     
@@ -135,7 +277,4 @@ with gr.Blocks() as demo:
     download_button.click(fn=download_all_papers, inputs=None, outputs=[download_output, download_links, text_output])
 
     # 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])
-
-# Launch the Gradio interface with a public link
-demo.launch(share=True)
+    demo.load(fn=load_all_data, outputs=[