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

# URL and headers for the file source
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.cache_data(ttl=3600, max_entries=1)
def load_data_file():
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        soup = BeautifulSoup(response.content, 'html.parser')
        links = soup.find_all('a')

        file_url = None
        for link in links:
            link_text = link.get_text(strip=True)
            if "Visa decisions made from 1 January 2024 to" in link_text:
                file_url = link.get('href')
                break

        if file_url:
            if not file_url.startswith('http'):
                file_url = requests.compat.urljoin(url, file_url)

            file_response = requests.get(file_url, headers=headers)
            if file_response.status_code == 200:
                return BytesIO(file_response.content), link_text
            else:
                st.error(f"Failed to download the file. Status code: {file_response.status_code}")
        else:
            st.error("The specified link was not found.")
    else:
        st.error(f"Failed to retrieve the webpage. Status code: {response.status_code}")
    return None, None