Update app.py

app.py

@@ -5,6 +5,13 @@ import requests
 from bs4 import BeautifulSoup
 import tempfile
 import os
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from datetime import datetime
+import pytz
 
 
 
@@ -228,9 +235,161 @@ def serviceAlerts():
 
     return jsonify(alerts)
 
+@app.route('/seek', methods=['POST'])
+def seek():
+    if not request.is_json:
+        return jsonify({'error': 'Request must be JSON'}), 400
+    
+    data = request.get_json()
+    stop_id = data.get('stop')
+    
+    if not stop_id:
+        return jsonify({'error': 'Stop ID is required'}), 404
+        
+    url = url = f"https://www.transsee.ca/smsstop?a=ttc&id={stop_id}"
+    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'
+    }
+    # Use Selenium to handle redirects and wait for page to load
+    options = Options()
+    options.add_argument("--headless=new")
+    options.add_argument("--disable-gpu")
+    options.add_argument("--no-sandbox")
+    
+    driver = webdriver.Chrome(options=options)
+    driver.get(url)
+    
+    # Wait for the page to load and look for divp elements
+    try:
+        WebDriverWait(driver, 15).until(
+            EC.presence_of_element_located((By.CLASS_NAME, "divp"))
+        )
+    except:
+        pass
+    
+    html = driver.page_source
+    driver.quit()
+    
+    soup = BeautifulSoup(html, 'html.parser')
+
+    # Extract routes from the <p> tags that contain <b> tags
+    routes = []
+    for p_tag in soup.find_all('p', id=re.compile(r'^\d+_\d+$')):
+        b_tag = p_tag.find('b')
+        if b_tag:
+            route_link = b_tag.find('a', href=re.compile(r'stoplist\?a=ttc&r=\d+'))
+            if route_link:
+                route_text = route_link.get_text(strip=True)
+                # Remove dash between number and name (e.g., "133-Neilson" -> "133 Neilson")
+                route_text = re.sub(r'(\d+)-([A-Za-z])', r'\1 \2', route_text)
+                
+                # Get the full text content of the p tag for branch and destination
+                full_text = p_tag.get_text()
+                
+                # Extract branch (letter/number after "going" if it exists)
+                branch = None
+                branch_match = re.search(r'going\s+([A-Za-z0-9]+)', full_text)
+                if branch_match:
+                    branch_text = branch_match.group(1)
+                    # Only treat single characters/numbers as branches (A, B, 1, 2, etc.)
+                    if len(branch_text) == 1 and branch_text.isalnum():
+                        branch = branch_text
+                
+                # Extract destination (everything after "to" until the end or next punctuation)
+                destination = None
+                destination_match = re.search(r'to\s+([^.]+)', full_text)
+                if destination_match:
+                    destination = destination_match.group(1).strip()
+                
+                routes.append({
+                    'name': route_text,
+                    'branch': branch,
+                    'destination': destination
+                })
+
+    pattern = re.compile(r'^\d{1,3}_\d{3,5}_[1-4]$')
+
+    vehicles = []
+
+    for div_tag in soup.find_all('div', class_='divp', id=pattern):
+        vehicle_id = div_tag.get('id')
+        id_parts = vehicle_id.split('_')
+        route = id_parts[0]  # Extract first 1-3 digits as route
+
+        vehicle_data = {
+            'route': route,
+        }
+
+        # Get both timedisp times
+        timedisp_elements = div_tag.find_all('time', class_='timedisp')
+        if len(timedisp_elements) >= 2:
+            vehicle_data['actual'] = timedisp_elements[0].get_text(strip=True)
+            vehicle_data['scheduled'] = timedisp_elements[1].get_text(strip=True)
+        elif len(timedisp_elements) == 1:
+            vehicle_data['actual'] = timedisp_elements[0].get_text(strip=True)
+            vehicle_data['scheduled'] = None
+        else:
+            vehicle_data['actual'] = None
+            vehicle_data['scheduled'] = None
+
+        # If actual is null, replace with current time (bus is at stop)
+        if vehicle_data['actual'] is None:
+            # Get current time in EST/EDT timezone
+            est_tz = pytz.timezone('America/New_York')
+            current_time = datetime.now(est_tz)
+            vehicle_data['actual'] = current_time.strftime("%I:%M:%S%p")
+
+        # Get delay/ahead status (like "1:10 ahead")
+        delay_span = None
+        for span in div_tag.find_all('span', style=True):
+            if 'color: light-dark' in span['style']:
+                span_text = span.get_text(strip=True)
+                if 'ahead' in span_text or 'behind' in span_text:
+                    delay_span = span
+                    break
+
+        if delay_span:
+            delay_text = delay_span.get_text(strip=True)
+            if 'ahead' in delay_text:
+                vehicle_data['delay'] = "+" + delay_text.replace(' ahead', '')
+            elif 'behind' in delay_text:
+                vehicle_data['delay'] = "-" + delay_text.replace(' behind', '')
+            else:
+                vehicle_data['delay'] = delay_text
+        else:
+            vehicle_data['delay'] = "0"
+
+        # Get vehicle number from #MapMain link or plain text
+        vehicle_link = div_tag.find('a', href="#MapMain")
+        if vehicle_link:
+            vehicle_data['vehicle_number'] = vehicle_link.get_text(strip=True)
+        else:
+            # Look for vehicle number in plain text like "Vehicle 1243 Load"
+            text = div_tag.get_text()
+            match = re.search(r'Vehicle\s+(\d+)', text)
+            if match:
+                vehicle_data['vehicle_number'] = match.group(1)
+            else:
+                vehicle_data['vehicle_number'] = None
+
+        vehicles.append(vehicle_data)
+    
+    return jsonify({
+        'stop': stop_id,
+        'routes': routes,
+        'vehicles': vehicles
+    })
+
 @app.route('/', methods=['GET'])
 def health_check():
     return 'Backend is running!', 200
 
 if __name__ == '__main__':
+    #app.run(debug=True, port=4999)
     app.run(debug=True, port=5000)