Test.py

####
'''  A simple web scraping script using requests and BeautifulSoup libraries. I am trying to achive the following:
1. Send an HTTP GET request to a website.
2. Parse the HTML content of the page.
3. Extract relevant data (e.g., tables, headings, paragraphs).
4. Save the extracted data to a file or display it in the terminal.'''


import requests
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 with headers
response = requests.get(url, headers=headers)

# Check if the request was successful (status code 200)
if response.status_code == 200:
    # Parse the HTML content of the page
    soup = BeautifulSoup(response.content, 'html.parser')
    
    # Extract relevant data (e.g., tables, headings, paragraphs)
    paragraphs = soup.find_all('p')
    for i, paragraph in enumerate(paragraphs, start=1):
        print(f"Paragraph {i}: {paragraph.get_text(strip=True)}")
        print("-" * 80)
    
    # Example: Scraping tables (if there are any)
    tables = soup.find_all('table')
    for table in tables:
        print("\nTable found:")
        rows = table.find_all('tr')
        for row in rows:
            cells = row.find_all(['th', 'td'])
            cell_data = [cell.get_text(strip=True) for cell in cells]
            print("\t".join(cell_data))
else:
    print(f"Failed to retrieve the webpage. Status code: {response.status_code}")