Update app.py

app.py

@@ -66,19 +66,19 @@ with open('label_encoder.pkl', 'rb') as file:
 def predict_phishing(url, html):
     cleaned_url = preprocess_url(url)
     cleaned_html = preprocess_html(html)
-    
+
     new_url_sequences = url_tokenizer.texts_to_sequences([cleaned_url])
     new_url_padded = pad_sequences(new_url_sequences, maxlen=max_url_length, padding='post', truncating='post')
-    
+
     new_html_sequences = html_tokenizer.texts_to_sequences([cleaned_html])
     new_html_padded = pad_sequences(new_html_sequences, maxlen=max_html_length, padding='post', truncating='post')
-    
+
     new_predictions_prob = model.predict([new_url_padded, new_html_padded])
     new_predictions = (new_predictions_prob > 0.6).astype(int)  # Adjust threshold if needed
-    
+
     predicted_category = label_encoder.inverse_transform(new_predictions)[0]
     predicted_probability = f"{new_predictions_prob[0][0]:.4f}"
-    
+
     return predicted_category.capitalize(), predicted_probability
 
 # Create Gradio Interface
@@ -86,14 +86,17 @@ interface = gr.Interface(
     fn=predict_phishing,
     inputs=[
         gr.components.Textbox(label="URL"),
-        gr.components.Textbox(label="HTML Snippet")
+        gr.components.Textbox(label="HTML Snippet", lines=10, placeholder="Paste HTML content here")
     ],
     outputs=[
         gr.components.Textbox(label="Predicted Category"),
         gr.components.Textbox(label="Predicted Probability")
     ],
     title="Phishing Detection Model",
-    description="Enter a URL and its HTML content to predict if it's spam or legitimate."
+    description="Enter a URL and its HTML content to predict if it's spam or legitimate. It's recommended to provide both for accurate results.",
+    theme="huggingface",
+    live=True,
+    css=".interface-container { border: 2px solid #4CAF50; border-radius: 10px; padding: 20px; }"
 )
 
 # Launch the Gradio interface