Update app.py

app.py

@@ -1,70 +1,79 @@
 import gradio as gr
 import requests
+from bs4 import BeautifulSoup
 
-# Assumed API endpoint based on the official journey planner.
-API_ENDPOINT = "https://jp.algoabus.co.za/api/journey"
+# URL for the schedule page (old schedule link provided)
+SCHEDULE_URL = "http://www.algoabus.co.za/port-elizabeth-bus-routes/route_list/schedule.aspx"
 
-def get_journey_schedule(origin, destination, date, time):
+def fetch_schedule():
     """
-    Retrieve journey schedule from Algoa Bus Company's API.
-    Expects:
-      - origin: starting location as a string.
-      - destination: ending location as a string.
-      - date: journey date in YYYY-MM-DD format.
-      - time: journey time in HH:MM 24-hour format.
+    Scrapes the schedule page and extracts bus routes and their schedules.
     
-    Returns a formatted string with the journey details.
+    This function assumes the schedule is contained in a table with a certain structure.
+    Adjust the selectors if Algoa updates their page design.
     """
-    payload = {
-        "origin": origin,
-        "destination": destination,
-        "date": date,
-        "time": time
-    }
-    headers = {
-        "Content-Type": "application/json",
-        "User-Agent": "Mozilla/5.0"
-    }
-    
     try:
-        response = requests.post(API_ENDPOINT, json=payload, headers=headers, timeout=10)
+        response = requests.get(SCHEDULE_URL, timeout=10)
         response.raise_for_status()
-        data = response.json()
+        html = response.text
+        
+        soup = BeautifulSoup(html, "html.parser")
+        schedule_data = {}
+        
+        # Assume the schedule is in a table with class "scheduleTable".
+        # (This is based on a guess—inspect the page source to confirm the actual class or id.)
+        table = soup.find("table", {"class": "scheduleTable"})
+        if not table:
+            return None, "Could not locate the schedule table on the page."
         
-        journeys = data.get("journeys", [])
-        if not journeys:
-            return "No journeys found for the given parameters."
+        rows = table.find_all("tr")
+        if not rows or len(rows) < 2:
+            return None, "No schedule rows found in the table."
         
-        result_str = ""
-        for journey in journeys:
-            dep_time = journey.get("departure_time", "N/A")
-            arr_time = journey.get("arrival_time", "N/A")
-            route = journey.get("route", "N/A")
-            stops = journey.get("stops", [])
-            stops_str = ", ".join(stops)
-            
-            result_str += f"**Route:** {route}\n"
-            result_str += f"**Departure:** {dep_time}\n"
-            result_str += f"**Arrival:** {arr_time}\n"
-            result_str += f"**Stops:** {stops_str}\n"
-            result_str += "--------------------------\n"
+        # Assuming the first row is header, start parsing from the second row.
+        for row in rows[1:]:
+            cols = row.find_all("td")
+            # We assume that at least two columns exist:
+            # Column 0: Bus route name; Column 1: Schedule details.
+            if len(cols) >= 2:
+                route_name = cols[0].get_text(strip=True)
+                # The schedule details might include multiple departure times separated by newlines.
+                schedule_info = cols[1].get_text(separator="\n", strip=True)
+                schedule_data[route_name] = schedule_info
         
-        return result_str
+        if not schedule_data:
+            return None, "No schedule data could be extracted from the table."
+        return schedule_data, None
     except Exception as e:
-        return f"Error retrieving schedule: {str(e)}"
+        return None, f"Error fetching schedule: {str(e)}"
+
+# Fetch schedule data at startup.
+schedule_data, error = fetch_schedule()
+
+# If scraping failed, we fallback to an empty dictionary.
+if error:
+    print("Scraping error:", error)
+    schedule_data = {}
+
+def get_route_schedule(route):
+    """
+    Returns the schedule details for a selected bus route.
+    """
+    if not schedule_data:
+        return "Schedule data is not available at the moment."
+    if route not in schedule_data:
+        return "Selected route not found in the schedule data."
+    return f"**Route:** {route}\n\n**Schedule:**\n{schedule_data[route]}"
+
+# Create a dropdown list from the scraped routes (or a placeholder if no data was retrieved).
+route_choices = list(schedule_data.keys()) if schedule_data else ["No Data Available"]
 
-# Define the Gradio interface.
 iface = gr.Interface(
-    fn=get_journey_schedule,
-    inputs=[
-        gr.Textbox(label="Origin (e.g., Port Elizabeth Central)"),
-        gr.Textbox(label="Destination (e.g., Algoa Park)"),
-        gr.Textbox(label="Date (YYYY-MM-DD)"),
-        gr.Textbox(label="Time (HH:MM, 24-hour format)")
-    ],
-    outputs=gr.Textbox(label="Journey Schedule"),
-    title="Algoa Bus Journey Planner",
-    description="Enter your journey details to retrieve the latest bus schedule for Algoa Bus Company in Port Elizabeth."
+    fn=get_route_schedule,
+    inputs=gr.Dropdown(choices=route_choices, label="Select Bus Route"),
+    outputs=gr.Textbox(label="Bus Schedule"),
+    title="Algoa Bus Schedule",
+    description="Select a bus route to view its schedule for Algoa Bus Company in Port Elizabeth."
 )
 
 if __name__ == "__main__":