diff --git a/.env.example b/.env.example
index ef1682b07..72b3237cd 100644
--- a/.env.example
+++ b/.env.example
@@ -3,5 +3,8 @@ DB_NAME=
 DB_USER=
 DB_PASS=
 
-TRANSLOC_API_KEY=
-TRAFFIC_API_KEY=
\ No newline at end of file
+BUS_API_URL=
+BUS_API_KEY=
+
+TRAFFIC_API_KEY=
+GOOGLE_MAPS_API_KEY=
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index f21726c76..dd6f40689 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,6 +19,7 @@
 .env.production.local
 .env
 
+__pycache__
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
diff --git a/Platform/pipeline/extractors/BusExtractor.py b/Platform/pipeline/extractors/BusExtractor.py
index db7967fc5..d9ae73c3a 100644
--- a/Platform/pipeline/extractors/BusExtractor.py
+++ b/Platform/pipeline/extractors/BusExtractor.py
@@ -1,7 +1,101 @@
 from BaseExtractor import ABCBaseExtractor as BaseExtractor
 import pandas as pd
+from datetime import datetime, timedelta
+import pytz
+import re
 
+"""
+Route Ids
+Red: 20
+Blue: 21
+Green: 17
+Emory: 18
+Gold: 29
+Clough: 28
+Night Gold/Clough: 30
+Northside Dr. - Atlantic Station: 26
+Nara/Science SQ: 22
+"""
 class BusExtractor(BaseExtractor):
+    def get_bus_data(self):
+        endpoint = "Services/JSONPRelay.svc/GetMapVehiclePoints"
+        params = {
+            "apiKey": self.api_key,
+            "isPublicMap": "true"
+        }
+        
+        vehicles = self._get(endpoint, params=params)
+        
+        bus_data = []
+        
+        for vehicle in vehicles:
+            raw_timestamp = vehicle["TimeStamp"]
+            match = re.search(r'/Date\((\d+)([+-]\d{4})\)/', raw_timestamp)
+            
+            if not match:
+                continue
+            
+            timestamp_ms = int(match.group(1))
+            utc_offset = match.group(2)
+            offset_hours = int(utc_offset[:3])
+            offset_minutes = int(utc_offset[0] + utc_offset[3:])
+            
+            utc_time = datetime.fromtimestamp(timestamp_ms / 1000, tz=pytz.utc)
+            offset = timedelta(hours=offset_hours, minutes=offset_minutes)
+            adjusted_time = utc_time + offset
+            timestamp = adjusted_time.astimezone(pytz.timezone('America/New_York'))
+            
+            bus_id = vehicle["VehicleID"]
+            route_id = vehicle["RouteID"]
+            latitude = vehicle["Latitude"]
+            longitude = vehicle["Longitude"]
+            day_of_week = timestamp.strftime('%A')
+            month = timestamp.strftime('%m')
+            time_of_day = timestamp.strftime('%H:%M:%S')
+            bus_speed = vehicle["GroundSpeed"]
+            
+            stop_id, eta_to_stop = self.get_stop_info(bus_id)
+            #api call may return an eta where eta < t_o_d, in which we symbol with 0 to show bus already arrived or passed stop
+            if eta_to_stop < time_of_day:
+                eta_to_stop = 0
+            
+            bus_data.append({
+                "busid": bus_id,
+                "routeid": route_id,
+                "latitude": latitude,
+                "longitude": longitude,
+                "day_of_week": day_of_week,
+                "month": month,
+                "time_of_day": time_of_day,
+                "bus_speed": bus_speed,
+                "stop_id": stop_id,
+                "eta_to_stop": eta_to_stop
+            })
+        
+        return bus_data
+    
+    def get_stop_info(self, vehicle_id):
+        endpoint = "Services/JSONPRelay.svc/GetVehicleRouteStopEstimates"
+        params = {
+            "vehicleIdStrings": vehicle_id,
+        }
+
+        response = self._get(endpoint, params=params)
+        estimates = response[0].get("Estimates")
+
+        if estimates:
+            est = estimates[0]
+            stop_id = est.get("RouteStopID")
+            estimate_time = est.get("EstimateTime")
+            match = re.search(r'\\?/Date\((\d+)\)\\?/', estimate_time)
+            if match:
+                timestamp_ms = int(match.group(1))
+                utc_time = datetime.fromtimestamp(timestamp_ms / 1000, tz=pytz.utc)
+                timestamp = utc_time.astimezone(pytz.timezone('America/New_York'))
+                eta_time_of_day = timestamp.strftime('%H:%M:%S')
+                return stop_id, eta_time_of_day
+        return None, None
+    
     def extract(self) -> pd.DataFrame:
-        #implement here
-        return
\ No newline at end of file
+        bus_data = self.get_bus_data()
+        return pd.DataFrame(bus_data)