Create loading_file.py
Browse files- loading_file.py +42 -0
loading_file.py
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
from bs4 import BeautifulSoup
|
3 |
+
from io import BytesIO
|
4 |
+
import streamlit as st
|
5 |
+
|
6 |
+
# URL and headers for the file source
|
7 |
+
url = "https://www.ireland.ie/en/india/newdelhi/services/visas/processing-times-and-decisions/"
|
8 |
+
headers = {
|
9 |
+
"User-Agent": (
|
10 |
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
|
11 |
+
"(KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"
|
12 |
+
)
|
13 |
+
}
|
14 |
+
|
15 |
+
@st.cache_data(ttl=3600, max_entries=1)
|
16 |
+
def load_data_file():
|
17 |
+
response = requests.get(url, headers=headers)
|
18 |
+
if response.status_code == 200:
|
19 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
20 |
+
links = soup.find_all('a')
|
21 |
+
|
22 |
+
file_url = None
|
23 |
+
for link in links:
|
24 |
+
link_text = link.get_text(strip=True)
|
25 |
+
if "Visa decisions made from 1 January 2024 to" in link_text:
|
26 |
+
file_url = link.get('href')
|
27 |
+
break
|
28 |
+
|
29 |
+
if file_url:
|
30 |
+
if not file_url.startswith('http'):
|
31 |
+
file_url = requests.compat.urljoin(url, file_url)
|
32 |
+
|
33 |
+
file_response = requests.get(file_url, headers=headers)
|
34 |
+
if file_response.status_code == 200:
|
35 |
+
return BytesIO(file_response.content), link_text
|
36 |
+
else:
|
37 |
+
st.error(f"Failed to download the file. Status code: {file_response.status_code}")
|
38 |
+
else:
|
39 |
+
st.error("The specified link was not found.")
|
40 |
+
else:
|
41 |
+
st.error(f"Failed to retrieve the webpage. Status code: {response.status_code}")
|
42 |
+
return None, None
|