Update app.py

app.py

@@ -23,7 +23,7 @@ lemmatizer = WordNetLemmatizer()
 def preprocess_url(url):
     url = url.lower()  # Convert to lowercase
     url = re.sub(r'https?://', '', url)  # Remove http or https
-    url = re.sub(r'www.', '', url)  # Remove www
+    url = re.sub(r'www\.', '', url)  # Remove www
     url = re.sub(r'[^a-zA-Z0-9]', ' ', url)  # Remove special characters
     url = re.sub(r'\s+', ' ', url).strip()  # Remove extra spaces
     tokens = word_tokenize(url)  # Tokenize
@@ -86,23 +86,18 @@ interface = gr.Interface(
     fn=predict_phishing,
     inputs=[
         gr.inputs.Textbox(label="URL"),
-        gr.inputs.Textbox(label="HTML Snippet")
+        gr.inputs.Textbox(label="HTML Snippet", lines=10, placeholder="Paste HTML content here")
     ],
     outputs=[
         gr.outputs.Textbox(label="Predicted Category"),
         gr.outputs.Textbox(label="Predicted Probability")
     ],
     title="Phishing Detection Model",
-    description="Enter a URL and its HTML content to predict if it's spam or legitimate.",
-    theme="compact",  # Use a more modern theme
-    layout="vertical",  # Arrange inputs and outputs vertically
-    allow_flagging=True,  # Allow users to flag inappropriate content
-    allow_screenshot=True,  # Allow users to take a screenshot
-    allow_replay=True,  # Allow users to replay their inputs
-    allow_download=True,  # Allow users to download inputs/outputs
-    allow_share=True,  # Allow users to share the interface
-    show_comment=True,  # Show comment section
-    comment_text="Note: It's recommended to input both URL and HTML for better accuracy."  # Custom comment text
+    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; }",
+    footer="Made with ❤️ by Ramadhirra"
 )
 
 # Launch the Gradio interface