searxng/searx/plugins/hostname_replace.py
Markus Heiser 542f7d0d7b [mod] pylint all files with one profile / drop PYLINT_SEARXNG_DISABLE_OPTION
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>
2024-03-11 14:55:38 +01:00

49 lines
1.6 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=missing-module-docstring
import re
from urllib.parse import urlunparse, urlparse
from flask_babel import gettext
from searx import settings
from searx.plugins import logger
name = gettext('Hostname replace')
description = gettext('Rewrite result hostnames or remove results based on the hostname')
default_on = False
preference_section = 'general'
plugin_id = 'hostname_replace'
replacements = {re.compile(p): r for (p, r) in settings[plugin_id].items()} if plugin_id in settings else {}
logger = logger.getChild(plugin_id)
parsed = 'parsed_url'
_url_fields = ['iframe_src', 'audio_src']
def on_result(_request, _search, result):
for pattern, replacement in replacements.items():
if parsed in result:
if pattern.search(result[parsed].netloc):
# to keep or remove this result from the result list depends
# (only) on the 'parsed_url'
if not replacement:
return False
result[parsed] = result[parsed]._replace(netloc=pattern.sub(replacement, result[parsed].netloc))
result['url'] = urlunparse(result[parsed])
for url_field in _url_fields:
if result.get(url_field):
url_src = urlparse(result[url_field])
if pattern.search(url_src.netloc):
if not replacement:
del result[url_field]
else:
url_src = url_src._replace(netloc=pattern.sub(replacement, url_src.netloc))
result[url_field] = urlunparse(url_src)
return True