File size: 1,578 Bytes
21a5451 49602b8 21a5451 49602b8 21a5451 49602b8 21a5451 49602b8 21a5451 49602b8 21a5451 49602b8 21a5451 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import requests
from bs4 import BeautifulSoup
from io import BytesIO
import streamlit as st
# URL of the website to scrape
url = "https://www.ireland.ie/en/india/newdelhi/services/visas/processing-times-and-decisions/"
# Headers for the HTTP 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"
)
}
@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')
# Look for the link to the .ods file
file_url = None
file_name = 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:
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(f"Failed to retrieve the webpage. Status code: {response.status_code}")
return None, None
|