convert_to_relative.py

#convert absolute URLs to relative

from urllib.parse import urlsplit, urlunsplit 

#Absolute source URLs linking to 404s from Search Console API: webmasters.urlcrawlerrorssamples.list 

linkedFromUrls= [
     "http://www.example.com/brand/swirly/shopby?sizecode=99",
     "https://www.example.com/brand/swirly"
    ]

#first break url into parts
u = urlsplit(linkedFromUrls[0])

# u -> SplitResult(scheme='http', netloc='www.example.com', path='/brand/swirly/shopby', query='sizecode=99', fragment='')

#then rebuild it back with empty scheme, netloc and fragment
relative_url = urlunsplit(("", "", o.path, o.query, ""))

print(relative_url)
#Output -> /brand/swirly/shopby?sizecode=99