Update app.py

app.py

@@ -3,20 +3,23 @@ import requests
 from bs4 import BeautifulSoup
 from transformers import pipeline
 
-# Load summarization pipeline
+# Use a more lightweight model for Hugging Face Spaces
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
 def scrape_website(url):
     """Extracts text from a website with error handling"""
     try:
-        headers = {'User-Agent': 'Mozilla/5.0'}
+        headers = {'User-Agent': 'Mozilla/5.0'}  # Add headers to prevent 403 errors
         response = requests.get(url, headers=headers, timeout=10)
-        response.raise_for_status()
+        response.raise_for_status()  # Raise HTTP errors
         
         soup = BeautifulSoup(response.text, "html.parser")
+        
+        # Extract text from common content-containing tags
         text_elements = soup.find_all(['p', 'article', 'main', 'section'])
         text = " ".join([e.get_text(strip=True, separator=' ') for e in text_elements])
-        return text.strip() if text.strip() else "No content found"
+        
+        return text if text.strip() else "No content found"
         
     except Exception as e:
         return f"Scraping Error: {str(e)}"
@@ -24,97 +27,44 @@ def scrape_website(url):
 def summarize_website(url):
     """Handles the full summarization pipeline"""
     try:
-        with gr.Column(variant="panel"):
-            gr.Markdown("## ⚡ Processing...")
-            
-            extracted_text = scrape_website(url)
-            
-            if "Error" in extracted_text:
-                return f"❌ {extracted_text}"
-                
-            if len(extracted_text.split()) < 50:
-                return "⚠️ Error: Insufficient content for summarization (minimum 50 words required)"
-                
-            max_input_length = 1000
-            truncated_text = extracted_text[:max_input_length]
-            
-            summary = summarizer(
-                truncated_text,
-                max_length=200,
-                min_length=50,
-                do_sample=False,
-                truncation=True
-            )
+        extracted_text = scrape_website(url)
+        
+        if "Error" in extracted_text:
+            return extracted_text
             
-            return f"## 📝 Summary\n\n{summary[0]['summary_text']}"
+        # Check minimum text length
+        if len(extracted_text.split()) < 50:
+            return "Error: Insufficient content for summarization (minimum 50 words required)"
             
+        # Truncate text to model's max input length (1024 tokens for DistilBART)
+        max_input_length = 1000  # Conservative estimate for token count
+        truncated_text = extracted_text[:max_input_length]
+        
+        # Generate summary
+        summary = summarizer(
+            truncated_text,
+            max_length=200,
+            min_length=50,
+            do_sample=False,
+            truncation=True  # Ensure truncation is enabled
+        )
+        
+        return f"**Summary:**\n\n{summary[0]['summary_text']}"
+        
     except Exception as e:
-        return f"⛔ Summarization Error: {str(e)}"
-
-# Custom CSS for mobile optimization
-css = """
-@media screen and (max-width: 600px) {
-    .container {
-        padding: 10px !important;
-    }
-    .input-box textarea {
-        font-size: 16px !important;
-    }
-}
-"""
+        return f"Summarization Error: {str(e)}"
 
-# Mobile-optimized interface with Blocks API
-with gr.Blocks(theme=gr.themes.Soft(), css=css, title="Website Summarizer") as app:
-    gr.Markdown("# 🌐 AI Website Summarizer")
-    gr.Markdown("Paste any website URL below to get an instant AI-powered summary!")
-    
-    with gr.Row():
-        url_input = gr.Textbox(
-            label="Website URL",
-            placeholder="Enter full URL (https://...)",
-            lines=1,
-            max_lines=1,
-            elem_id="input-box"
-        )
-    
-    with gr.Row():
-        submit_btn = gr.Button("Generate Summary 🚀", variant="primary")
-        clear_btn = gr.Button("Clear 🔄")
-    
-    output = gr.Markdown()
-    
-    # Example section
-    gr.Examples(
-        examples=[
-            ["https://en.wikipedia.org/wiki/Large_language_model"],
-            ["https://www.bbc.com/news/technology-66510295"]
-        ],
-        inputs=url_input,
-        label="Try these examples:",
-        examples_per_page=2
-    )
-    
-    # Progress indicator
-    progress = gr.Textbox(visible=False)
-    
-    # Event handlers
-    submit_btn.click(
-        fn=summarize_website,
-        inputs=url_input,
-        outputs=output,
-        api_name="summarize"
-    )
-    
-    clear_btn.click(
-        fn=lambda: ("", ""),
-        inputs=None,
-        outputs=[url_input, output],
-        queue=False
-    )
+# Gradio interface with improved configuration
+iface = gr.Interface(
+    fn=summarize_website,
+    inputs=gr.Textbox(label="Website URL", placeholder="Enter full URL (including https://)..."),
+    outputs=gr.Markdown(),
+    title="AI-Powered Website Summarizer",
+    description="Enter a website URL to get an AI-generated summary of its content",
+    examples=[
+        ["https://en.wikipedia.org/wiki/Large_language_model"],
+        ["https://www.bbc.com/news/technology-66510295"]
+    ]
+)
 
-# Mobile-friendly configuration
-app.launch(
-    server_name="0.0.0.0",
-    server_port=7860,
-    favicon_path="https://www.svgrepo.com/show/355037/huggingface.svg"
-)
+iface.launch()