lit1.py

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

# Streamlit app title
st.title("Visa Application Status Checker")

# URL of the website to scrape
url = "https://www.ireland.ie/en/india/newdelhi/services/visas/processing-times-and-decisions/"

# Headers to mimic a browser request
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"
    )
}

# Step 1: Function to fetch and cache the .ods file
@st.cache_data(ttl=3600, max_entries=1)
def fetch_ods_file():
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        soup = BeautifulSoup(response.content, 'html.parser')

        # Find all anchor tags
        links = soup.find_all('a')

        # Search for the link containing the specific text
        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')
                file_name = link_text
                break
        
        if file_url:
            # Make the link absolute if it is relative
            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), file_name
            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

# Step 2: Fetch the cached .ods file
ods_file, cached_file_name = fetch_ods_file()

if ods_file:
    try:
        # Step 3: Read the .ods file into a DataFrame
        df = pd.read_excel(ods_file, engine='odf')
        
        # Clean up the DataFrame by dropping unnecessary columns
        df.drop(columns=["Unnamed: 0", "Unnamed: 1"], inplace=True, errors='ignore')
        
        # Drop empty rows and reset index
        df.dropna(how='all', inplace=True)
        df.reset_index(drop=True, inplace=True)
        
        # Identify the header row and reformat DataFrame
        for idx, row in df.iterrows():
            if row['Unnamed: 2'] == 'Application Number' and row['Unnamed: 3'] == 'Decision':
                df.columns = ['Application Number', 'Decision']
                df = df.iloc[idx + 1:]  # Skip the header row
                break
        
        # Reset index after cleaning
        df.reset_index(drop=True, inplace=True)
        
        # Convert "Application Number" to string for consistency
        df['Application Number'] = df['Application Number'].astype(str)

        # Step 4: Get user input for application number using Streamlit
        user_input = st.text_input("Enter your Application Number (including IRL if applicable):")
        
        if user_input:
            # Input validation logic
            if "irl" in user_input.lower():
                try:
                    application_number = int("".join(filter(str.isdigit, user_input.lower().split("irl")[-1])))
                    if len(str(application_number)) < 8:
                        st.warning("Please enter a valid application number with at least 8 digits after IRL.")
                        st.stop()
                except ValueError:
                    st.error("Invalid input after IRL. Please enter only digits.")
                    st.stop()
            else:
                if not user_input.isdigit() or len(user_input) < 8:
                    st.warning("Please enter at least 8 digits for your VISA application number.")
                    st.stop()
                application_number = int(user_input)
            
            # Check if the application number exists in the DataFrame
            result = df[df['Application Number'] == str(application_number)]
            
            if not result.empty:
                decision = result.iloc[0]['Decision']
                st.success(f"Application Number: **{application_number}**\n\nDecision: **{decision}**")
            else:
                st.warning(f"No record found for Application Number: {application_number}.")
                
                # Find the nearest application numbers
                df['Application Number'] = df['Application Number'].astype(int)
                df['Difference'] = abs(df['Application Number'] - application_number)
                nearest_records = df.nsmallest(2, 'Difference')

                if not nearest_records.empty:
                    st.subheader("Nearest Application Numbers")
                    st.table(nearest_records[['Application Number', 'Decision', 'Difference']])
                else:
                    st.info("No nearest application numbers found.")

    except Exception as e:
        st.error(f"Error reading the .ods file: {e}")
else:
    st.error("No file data available.")