handling_url_parameters.py

#Handling URL parameters

from urllib.parse import urlsplit, urlunsplit 

def clean_url_params(url):
  
  print(url)
  
  u = urlsplit(url)

  print(u.query)

  #example output -> 'sizecode=99&sort='

  url_params = parse_qsl(u.query)
  
  print(url_params)

  #example output -> [('sizecode', '99')]

  #next let's sort the parameters so they are always in the same order
  url_params.sort(key=lambda tup: tup[0])  # sorts in place by parameter name


  #now we need to rebuild the URL
  new_query = urlencode(url_params)
  
  print(new_query)

  #example output -> 'sizecode=99'

  new_url = urlunsplit((u.scheme, u.netloc, u.path, new_query, ""))

  print(new_url)

  #example output -> 'http://www.example.com/brand/swirly/shopby?sizecode=99'

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

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

#You might have parameters with no values. For example, sort=
clean_url_params(linkedFromUrls[0])

#Output: http://www.example.com/brand/swirly/shopby?sizecode=99&sort= -> http://www.example.com/brand/swirly/shopby?sizecode=99

#You might have parameters ordered differently 
clean_url_params(linkedFromUrls[1])

clean_url_params(linkedFromUrls[2])

#Output:
# https://www.example.com/brand/swirly?sort=asc&sizecode=99 -> https://www.example.com/brand/swirly?sizecode=99&sort=asc
# https://www.example.com/brand/swirly?sizecode=99&sort=asc -> https://www.example.com/brand/swirly?sizecode=99&sort=asc