Spaces:
Sleeping
Sleeping
import gradio as gr | |
import requests | |
from bs4 import BeautifulSoup | |
# 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 fetch_schedule(): | |
""" | |
Scrapes the schedule page and extracts bus routes and their schedules. | |
This function assumes the schedule is contained in a table with a certain structure. | |
Adjust the selectors if Algoa updates their page design. | |
""" | |
try: | |
response = requests.get(SCHEDULE_URL, timeout=10) | |
response.raise_for_status() | |
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." | |
rows = table.find_all("tr") | |
if not rows or len(rows) < 2: | |
return None, "No schedule rows found in the table." | |
# 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 | |
if not schedule_data: | |
return None, "No schedule data could be extracted from the table." | |
return schedule_data, None | |
except Exception as 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"] | |
iface = gr.Interface( | |
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__": | |
iface.launch() | |