mirror of
https://github.com/searxng/searxng.git
synced 2024-11-25 12:21:00 +00:00
542f7d0d7b
In the past, some files were tested with the standard profile, others with a profile in which most of the messages were switched off ... some files were not checked at all. - ``PYLINT_SEARXNG_DISABLE_OPTION`` has been abolished - the distinction ``# lint: pylint`` is no longer necessary - the pylint tasks have been reduced from three to two 1. ./searx/engines -> lint engines with additional builtins 2. ./searx ./searxng_extra ./tests -> lint all other python files Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# pylint: disable=missing-module-docstring
|
|
|
|
import re
|
|
from urllib.parse import urlunparse, parse_qsl, urlencode
|
|
|
|
from flask_babel import gettext
|
|
|
|
regexes = {
|
|
re.compile(r'utm_[^&]+'),
|
|
re.compile(r'(wkey|wemail)[^&]*'),
|
|
re.compile(r'(_hsenc|_hsmi|hsCtaTracking|__hssc|__hstc|__hsfp)[^&]*'),
|
|
re.compile(r'&$'),
|
|
}
|
|
|
|
name = gettext('Tracker URL remover')
|
|
description = gettext('Remove trackers arguments from the returned URL')
|
|
default_on = True
|
|
preference_section = 'privacy'
|
|
|
|
|
|
def on_result(_request, _search, result):
|
|
if 'parsed_url' not in result:
|
|
return True
|
|
|
|
query = result['parsed_url'].query
|
|
|
|
if query == "":
|
|
return True
|
|
parsed_query = parse_qsl(query)
|
|
|
|
changes = 0
|
|
for i, (param_name, _) in enumerate(list(parsed_query)):
|
|
for reg in regexes:
|
|
if reg.match(param_name):
|
|
parsed_query.pop(i - changes)
|
|
changes += 1
|
|
result['parsed_url'] = result['parsed_url']._replace(query=urlencode(parsed_query))
|
|
result['url'] = urlunparse(result['parsed_url'])
|
|
break
|
|
|
|
return True
|