app.py

import requests
import pandas as pd
from bs4 import BeautifulSoup
from datetime import datetime
import gradio as gr
import os
import schedule
import time
import threading

def scrape_exchange_rates():
    url = "https://www.mcb.com.lk/exchange-rates/"
    try:
        r = requests.get(url, timeout=10)
        print(f"Status code: {r.status_code}")
        if r.status_code != 200:
            print(f"Failed to fetch URL: Status code {r.status_code}")
            return None
        
        soup = BeautifulSoup(r.text, "lxml")
        table = soup.find("table", class_="uael-text-break uael-column-rules uael-table")
        if not table:
            print("Table not found in webpage")
            return None
        
        headers = ["Currency Type", "Buying Rate", "Selling Rate"]
        rows = []
        for tr in table.find_all("tr")[2:]:
            cells = tr.find_all("td")
            if len(cells) >= 3:
                row = [
                    cells[0].text.strip(),
                    cells[1].text.strip(),
                    cells[2].text.strip()
                ]
                rows.append(row)
        
        if not rows:
            print("No data rows found in table")
            return None
            
        df = pd.DataFrame(rows, columns=headers)
        df['extracted_date'] = datetime.now().strftime('%Y-%m-%d')
        print("Scraping successful")
        return df
    except Exception as e:
        print(f"Scraping error: {str(e)}")
        return None

def update_csv():
    csv_file = "data.csv"
    today = datetime.now().strftime('%Y-%m-%d')
    
    if not os.path.exists(csv_file):
        print("CSV file not found, creating new one")
        df = scrape_exchange_rates()
        if df is not None:
            df.to_csv(csv_file, index=False)
            print(f"Initial CSV created with data for {today}")
        else:
            print("Failed to create initial CSV - scraping returned no data")
        return
    
    try:
        existing_df = pd.read_csv(csv_file)
    except Exception as e:
        print(f"Error reading CSV: {e}")
        existing_df = pd.DataFrame(columns=["Currency Type", "Buying Rate", "Selling Rate", "extracted_date"])
    
    if 'extracted_date' not in existing_df.columns or today not in existing_df['extracted_date'].values:
        print(f"Updating data for {today}")
        new_df = scrape_exchange_rates()
        if new_df is not None:
            updated_df = pd.concat([existing_df, new_df], ignore_index=True)
            updated_df.to_csv(csv_file, index=False)
            print(f"Data updated successfully for {today}")
        else:
            print("Failed to update data - scraping returned no data")

def run_schedule():
    schedule.every().day.at("14:00").do(update_csv)
    while True:
        schedule.run_pending()
        time.sleep(60)

def start_scheduler():
    update_csv()
    scheduler_thread = threading.Thread(target=run_schedule, daemon=True)
    scheduler_thread.start()

def get_display_data():
    csv_file = "data.csv"
    if os.path.exists(csv_file):
        try:
            df = pd.read_csv(csv_file)
            if 'extracted_date' in df.columns and not df.empty:
                last_date = df['extracted_date'].iloc[-1]
                return last_date, df
        except Exception as e:
            print(f"Error in get_display_data: {e}")
    return "No data available yet", pd.DataFrame(columns=["Currency Type", "Buying Rate", "Selling Rate", "extracted_date"])

# Gradio interface
with gr.Blocks(title="Exchange Rate Monitor") as demo:
    gr.Markdown("# Exchange Rate Monitoring System")
    
    with gr.Row():
        last_update = gr.Textbox(label="Last Data Scraping Date", value="Loading...")
    
    with gr.Row():
        data_table = gr.Dataframe(
            label="Exchange Rates History",
            headers=["Currency Type", "Buying Rate", "Selling Rate", "extracted_date"],
            datatype=["str", "str", "str", "str"],
            interactive=False
        )
    
    refresh_btn = gr.Button("Refresh Data")
    
    def update_display():
        last_date, df = get_display_data()
        return last_date, df
    
    demo.load(
        fn=update_display,
        inputs=None,
        outputs=[last_update, data_table]
    )
    
    refresh_btn.click(
        fn=update_display,
        inputs=None,
        outputs=[last_update, data_table]
    )
    
    demo.load(fn=start_scheduler, inputs=None, outputs=None)

demo.launch(debug=True)