Create new_templates/website_monitor_function_v2

new_templates/website_monitor_function_v2

@@ -0,0 +1,123 @@
+def website_monitor_function_v2():
+    import requests
+    import threading
+    import time
+    from datetime import datetime
+    from difflib import SequenceMatcher
+    import re
+    
+    # Configuration
+    URL = "<add your target url here>"  # Replace with your target URL
+    CHECK_INTERVAL = 4  # in seconds
+    CHANGE_THRESHOLD = 0.01  # 1% difference threshold
+    
+    # Shared state variables
+    current_state = "Initializing..."
+    previous_html = None
+    last_check_time = None
+    monitor_thread = None
+    
+    def extract_text_content(html):
+        """Extract text content from HTML, removing tags and normalizing whitespace"""
+        # Remove HTML tags
+        text = re.sub(r'<[^>]+>', ' ', html)
+        # Normalize whitespace
+        text = ' '.join(text.split())
+        return text.lower().strip()
+    
+    def calculate_text_difference(text1, text2):
+        """Calculate percentage difference between two text strings"""
+        if not text1 and not text2:
+            return 0.0
+        if not text1 or not text2:
+            return 1.0
+        
+        similarity = SequenceMatcher(None, text1, text2).ratio()
+        sim_score = 1.0 - similarity
+        return sim_score
+    
+    def fetch_and_compare():
+        """Fetch URL content and compare with previous version"""
+        nonlocal current_state, previous_html, last_check_time
+        
+        try:
+            response = requests.get(URL, timeout=30)
+            response.raise_for_status()
+            current_html = response.text
+            current_time = datetime.now()
+            
+            if previous_html is None:
+                # First run
+                previous_html = current_html
+                last_check_time = current_time
+                current_state = f"Initial check completed at {current_time.strftime('%Y-%m-%d %H:%M:%S')}"
+                return
+            
+            # Extract and compare text content
+            previous_text = extract_text_content(previous_html)
+            current_text = extract_text_content(current_html)
+            
+            difference_ratio = calculate_text_difference(previous_text, current_text)
+            
+            if difference_ratio >= CHANGE_THRESHOLD:
+                current_state = f"Changes occurred between {last_check_time.strftime('%Y-%m-%d %H:%M:%S')} - {current_time.strftime('%Y-%m-%d %H:%M:%S')}"
+                previous_html = current_html
+            else:
+                current_state = f"No changes occurred since {last_check_time.strftime('%Y-%m-%d %H:%M:%S')}"
+            
+            last_check_time = current_time
+            
+        except requests.RequestException as e:
+            current_state = f"Error fetching URL at {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}: {str(e)}"
+        except Exception as e:
+            current_state = f"Unexpected error at {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}: {str(e)}"
+    
+    def monitor_loop():
+        """Continuous monitoring loop"""
+        while True:
+            fetch_and_compare()
+            time.sleep(CHECK_INTERVAL)
+    
+    def start_monitoring():
+        """Start the monitoring thread if not already running"""
+        nonlocal monitor_thread
+        if monitor_thread is None or not monitor_thread.is_alive():
+            monitor_thread = threading.Thread(target=monitor_loop, daemon=True)
+            monitor_thread.start()
+    
+    # Start monitoring when function is deployed
+    start_monitoring()
+    
+    def score(input_data):
+        """Score function that returns current monitoring state"""
+        try:
+            # Extract any parameters from input if needed (optional)
+            # For now, just return current state
+            
+            score_response = {
+                'predictions': [{
+                    'fields': ['monitoring_state', 'check_interval_seconds', 'target_url', 'last_updated'],
+                    'values': [[
+                        current_state,
+                        CHECK_INTERVAL,
+                        URL,
+                        datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+                    ]]
+                }]
+            }
+            
+            return score_response
+            
+        except Exception as e:
+            error_response = {
+                'predictions': [{
+                    'fields': ['error'],
+                    'values': [[f"Error in score function: {str(e)}"]]
+                }]
+            }
+            return error_response
+    
+    return score
+
+# Create the deployable score function
+score = website_monitor_function_v2()