extract individual vehicle info as well

app.py

@@ -72,22 +72,6 @@ def getRouteList():
 
             routes[rid] = text
 
-    for rid in range(500, 599): # all streetcar routes
-        tag = soup.find("p", {"id": str(rid)})
-        if tag and tag.text.strip():
-            # Clean text:
-            text = tag.get_text(strip=True)
-
-            # Remove leading symbols like "*" or "== $0"
-            text = re.sub(r"^[^A-Za-z0-9]+", "", text)   # strip non-alphanumeric at start
-            text = re.sub(r"\s*==.*$", "", text)        # strip trailing "== $0" or similar
-            text = re.sub(r"\s+", " ", text).strip()    # collapse spaces
-            
-            # Replace dash between number and name with space (e.g., "26-Dupont" -> "26 Dupont")
-            text = re.sub(r'(\d+)-([A-Za-z])', r'\1 \2', text)
-
-            routes[rid] = text
-
     for rid in range(900, 999): # all express routes
         tag = soup.find("p", {"id": str(rid)})
         if tag and tag.text.strip():
@@ -174,7 +158,6 @@ def listVehiclesByRoute():
                     pass
             # If it's mm:ss format, keep as is
         
-        if delay is None: continue
         delay = ("-" if late else "+") + delay_value
 
         # Extract coordinates from JavaScript AddMarker calls
@@ -248,6 +231,76 @@ def serviceAlerts():
 
     return jsonify(alerts)
 
+
+def getVehicleInfo(vehicle_id):
+    url = f'https://www.transsee.ca/fleetfind?a=ttc&findtrack=1&q={vehicle_id}&Go=Go'
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36',
+        'Referer': 'https://www.transsee.ca/',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+        'Accept-Language': 'en-US,en;q=0.9',
+        'DNT': '1',  # Do Not Track
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1'
+    }
+    try:
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+    except Exception as e:
+        return jsonify({"error": f"Failed to fetch vehicle info: {e}"}), 500
+    
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # Find the specific paragraph with id=vehicle_id
+    p = soup.find("p", id=vehicle_id)
+    if not p:
+        return jsonify({"error": f"Vehicle {vehicle_id} not found"}), 404
+    
+    # Get the HTML content to properly parse the structure
+    html_content = str(p)
+    
+    # Extract direction (like "going D")
+    direction = None
+    direction_match = re.search(r'going\s+([A-Za-z0-9]+)', html_content)
+    if direction_match:
+        direction = direction_match.group(1)
+    
+    # Extract destination - only the text before <br>
+    destination = None
+    
+    # Debug: print the raw HTML
+    print(f"DEBUG - Raw HTML: {html_content}")
+    
+    # Split by <br> and get only the first part
+    before_br = html_content.split('<br/>')[0].split('<br>')[0]
+    print(f"DEBUG - Before BR: {before_br}")
+    
+    # Look for the quoted destination text that contains direction words
+    dest_match = re.search(r'"([^"]*(?:South|North|East|West)[^"]*)"', before_br)
+    if dest_match:
+        raw_dest = dest_match.group(1).strip()
+        print(f"DEBUG - Raw destination: {raw_dest}")
+        # Clean up - remove anything after "at " or "on " which indicates location details
+        clean_dest = re.sub(r'at\s+.*$', '', raw_dest)
+        destination = clean_dest.strip()
+        print(f"DEBUG - Clean destination: {destination}")
+    else:
+        print("DEBUG - No direction-containing quoted text found, using fallback")
+        # Fallback: extract text content and look for direction patterns
+        temp_soup = BeautifulSoup(before_br, 'html.parser')
+        text_content = temp_soup.get_text()
+        dest_match = re.search(r'((?:South|North|East|West) to [^=]*?)(?=\s*==|\s*$)', text_content)
+        if dest_match:
+            raw_dest = dest_match.group(1).strip()
+            clean_dest = re.sub(r'at\s+.*$', '', raw_dest)
+            destination = clean_dest.strip()
+    
+    return jsonify({
+        "direction": direction,
+        "destination": destination
+    })
+
+
 @app.route('/seek', methods=['POST'])
 def seek():
     if not request.is_json:
@@ -430,6 +483,10 @@ def seek():
             else:
                 vehicle_data['vehicle_number'] = None
 
+        if vehicle_data['vehicle_number'] is None: continue
+        vehicle_info = getVehicleInfo(vehicle_data['vehicle_number'])
+        vehicle_data['direction'] = vehicle_info['direction']
+        vehicle_data['destination'] = vehicle_info['destination']
         vehicles.append(vehicle_data)
     
     return jsonify({