Skip to content

Add parameter without removing duplicated value in query string #126

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions tests/test_url.py
Original file line number Diff line number Diff line change
Expand Up @@ -283,6 +283,12 @@ def test_add_or_replace_parameter(self):
self.assertEqual(add_or_replace_parameter(url, 'pageurl', 'test'),
'http://example.com/?version=1&pageurl=test&param2=value2')

url = 'http://domain/test?arg1=v1&arg2=v2&arg1=v3'
self.assertEqual(add_or_replace_parameter(url, 'arg4', 'v4'),
'http://domain/test?arg1=v1&arg2=v2&arg1=v3&arg4=v4')
self.assertEqual(add_or_replace_parameter(url, 'arg1', 'v3'),
'http://domain/test?arg1=v3&arg2=v2')

def test_add_or_replace_parameters(self):
url = 'http://domain/test'
self.assertEqual(add_or_replace_parameters(url, {'arg': 'v'}),
Expand All @@ -292,6 +298,17 @@ def test_add_or_replace_parameters(self):
'http://domain/test?arg1=v1&arg2=v2&arg3=v3&arg4=v4')
self.assertEqual(add_or_replace_parameters(url, {'arg4': 'v4', 'arg3': 'v3new'}),
'http://domain/test?arg1=v1&arg2=v2&arg3=v3new&arg4=v4')
url = 'http://domain/test?arg1=v1&arg2=v2&arg1=v3'
self.assertEqual(add_or_replace_parameters(url, {'arg4': 'v4'}),
'http://domain/test?arg1=v1&arg2=v2&arg1=v3&arg4=v4')
self.assertEqual(add_or_replace_parameters(url, {'arg1': 'v3'}),
'http://domain/test?arg1=v3&arg2=v2')

def test_add_or_replace_parameters_does_not_change_input_param(self):
url = 'http://domain/test?arg=original'
input_param = {'arg': 'value'}
new_url = add_or_replace_parameters(url, input_param) # noqa
self.assertEqual(input_param, {'arg': 'value'})

def test_url_query_cleaner(self):
self.assertEqual('product.html',
Expand Down
20 changes: 14 additions & 6 deletions w3lib/url.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
import posixpath
import warnings
import string
from collections import namedtuple, OrderedDict
from collections import namedtuple
import six
from six.moves.urllib.parse import (urljoin, urlsplit, urlunsplit,
urldefrag, urlencode, urlparse,
Expand Down Expand Up @@ -199,13 +199,21 @@ def url_query_cleaner(url, parameterlist=(), sep='&', kvsep='=', remove=False, u
url += '#' + fragment
return url


def _add_or_replace_parameters(url, params):
parsed = urlsplit(url)
args = parse_qsl(parsed.query, keep_blank_values=True)

new_args = OrderedDict(args)
new_args.update(params)
current_args = parse_qsl(parsed.query, keep_blank_values=True)

new_args = []
seen_params = set()
for name, value in current_args:
if name not in params:
new_args.append((name, value))
elif name not in seen_params:
new_args.append((name, params[name]))
seen_params.add(name)

not_modified_args = [(name, value) for name, value in params.items() if name not in seen_params]
new_args += not_modified_args

query = urlencode(new_args)
return urlunsplit(parsed._replace(query=query))
Expand Down