fetch_data()

import requests
import pandas as pd
import streamlit as st
from io import BytesIO
from bs4 import BeautifulSoup

@st.cache_data(ttl=3600)
def fetch_data():
    url = "https://www.ireland.ie/en/india/newdelhi/services/visas/processing-times-and-decisions/"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"
    }

    st.write("🔄 Fetching webpage...")
    try:
        response = requests.get(url, headers=headers, timeout=10)  # Timeout added
        response.raise_for_status()  # Raise an error if request fails
    except requests.exceptions.RequestException as e:
        st.error(f"❌ Failed to fetch webpage: {e}")
        return None, None

    # Parse the HTML
    st.write("🔄 Parsing webpage...")
    soup = BeautifulSoup(response.content, "html.parser")

    file_url = None
    for link in soup.find_all("a"):
        if "Visa decisions made from 1 January 2025" in link.get_text():
            file_url = link.get("href")
            if not file_url.startswith("http"):
                file_url = requests.compat.urljoin(url, file_url)
            break

    if not file_url:
        st.error("❌ Could not find the visa decisions file link.")
        return None, None

    st.write(f"📥 Found file link: {file_url}")

    # Download the .ods file
    try:
        st.write("🔄 Downloading file...")
        ods_response = requests.get(file_url, headers=headers, timeout=15)  # Timeout added
        ods_response.raise_for_status()
    except requests.exceptions.RequestException as e:
        st.error(f"❌ Failed to download the file: {e}")
        return None, None

    st.write("📂 Processing file...")
    ods_file = BytesIO(ods_response.content)

    # Read Excel file
    try:
        df = pd.read_excel(ods_file, engine="odf")
    except Exception as e:
        st.error(f"❌ Error reading ODS file: {e}")
        return None, None

    # Drop empty rows
    df.dropna(how="all", inplace=True)
    df.reset_index(drop=True, inplace=True)

    # Find header row
    header_rows = df[df.iloc[:, 0].astype(str).str.contains("Application Number", na=False)].index
    if len(header_rows) == 0:
        st.error("❌ Could not find the header row. Check the file format.")
        return None, None

    header_index = header_rows[0]
    df = df.iloc[header_index + 1:].reset_index(drop=True)

    # Rename columns
    df.columns = ["Application Number", "Decision"]
    df.dropna(inplace=True)
    df["Application Number"] = df["Application Number"].astype(str).str.strip()

    st.write("✅ Data loaded successfully!")
    return df, "Visa Decisions Report"

precomputed_df, file_name = fetch_data()