Untitled3.py

#!/usr/bin/env python
# coding: utf-8

# In[10]:


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

# 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"
    )
}

# Send an HTTP GET request to the website
response = requests.get(url, headers=headers)

# Check if the request was successful
if response.status_code == 200:
    # Parse the HTML content of the page
    soup = BeautifulSoup(response.content, 'html.parser')
    
    # Find all anchor tags
    links = soup.find_all('a')
    
    # Search for the link that contains 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')
            break
    
    # Check if the link was found
    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)
        
        print(f"Found link: {file_url}")
        
        # Download the file into memory
        file_response = requests.get(file_url, headers=headers)
        
        if file_response.status_code == 200:
            # Load the file into a BytesIO object
            ods_file = BytesIO(file_response.content)
            
            # Read the .ods file using pandas
            try:
                # Load the .ods file into a DataFrame
                df = pd.read_excel(ods_file, engine='odf')
                
                # Step 1: Clean the DataFrame
                # Drop the first two columns
                df.drop(columns=["Unnamed: 0", "Unnamed: 1"], inplace=True)
                
                # Step 2: Drop NaN rows until we find the actual header row
                df.dropna(how='all', inplace=True)
                
                # Step 3: Reset index and rename the header row
                df.reset_index(drop=True, inplace=True)
                
                # Step 4: Find the row where "Application Number" starts
                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
                
                # Step 5: Reset the 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)

                # Display the cleaned DataFrame
                #print("Cleaned Data:")
                #print(df.to_string(index=False))
                
                # Step 6: Ask the user for their application number
                user_application_number = input("\nEnter your Application Number: ").strip()
                
                # Step 7: Check if the application number exists in the DataFrame
                result = df[df['Application Number'] == user_application_number]
                
                if not result.empty:
                    print(f"\nCongratulations! Your visa application ({user_application_number}) has been {result.iloc[0]['Decision']}.")
                else:
                    print(f"\nSorry, no record found for Application Number: {user_application_number}.")
                    
            except Exception as e:
                print("Error reading the .ods file:", e)
        else:
            print("Failed to download the file. Status code:", file_response.status_code)
    else:
        print("The specified link was not found.")
else:
    print(f"Failed to retrieve the webpage. Status code: {response.status_code}")