Transform any URL to a standard form (useful for joining tables)

prettify_url.py

# Want to join your data based on URLs (links)? 
# You need to convert all urls to one format.
# E.g. remove www., remove https://, remove url params
# This is how I do it:

def prettify(url):
    if not url or not isinstance(url, str):
        return None  # not sure that this is the best approach
    
    url = url.lower().strip()
    
    # remove garbage
    url = url.replace("www.", "")
    url = url.replace("http://", "")
    url = url.replace("https://", "")
    
    # remove url params
    __q = url.find("?")
    if __q != -1:
        url = url[:__q]
        
    # remove backslash
    url = url.rstrip("/")
    
    return url


# Sometimes a Linkedin link has useless subdomain
def prettify_linkedin(url):
    url = prettify(url)
    
    if not url:
        return None
    
    # cut & everything before domain
    __l = url.rfind("linkedin.com")
    if __l != -1:
        url = url[__l:]
        
    return url