Pasted

import requests
from bs4 import BeautifulSoup
import re
 
def get_css_classes_ids(url):
    # Send a GET request to the URL
    response = requests.get(url)
    # Check if the request was successful
    if response.status_code == 200:
        # Parse the HTML content
        soup = BeautifulSoup(response.text, 'html.parser')
        # Use regex to find all classes and IDs
        classes = set(re.findall(r'class="([^"]+)"', soup.decode()))
        ids = set(re.findall(r'id="([^"]+)"', soup.decode()))
        # Return a tuple of sets containing classes and IDs
        return classes, ids
    else:
        print(f"Failed to retrieve content from {url}, status code: {response.status_code}")
        return set(), set()
 
# Replace 'http://example.com' with the URL you want to scrape
classes, ids = get_css_classes_ids('http://example.com')
 
print("CSS Classes found:")
for c in classes:
    print(c)
 
print("\nCSS IDs found:")
for i in ids:
    print(i)