def get_url_info(url, guess_and_check, max_depth):
# Create a new Link instance
link = Link()
# Save the extracted URL
link.url = url
# Remove markdown and other artifacts from the URL
link.url_clean = remove_markdown(url)
# Check if the clean URL is valid, if so continue with the next steps
link.url_clean_is_valid = check_if_valid_url(link.url_clean)
if link.url_clean_is_valid:
link.is_amp = check_if_amp(link.url_clean)
if link.is_amp:
link.is_cached = check_if_cached(link.url_clean)
link.domain = tldextract.extract(link.url_clean).domain
link = get_canonical(link, guess_and_check, max_depth)
return link
