mirror of
https://github.com/searxng/searxng.git
synced 2024-11-19 19:00:10 +01:00
795e8af61d
This is a rewrite of the hostname_replace.py that:
- don't stop to replace URL in fields ('data_src', 'audio_src') if there isn't a
'parsed_url',
- adds a comment about keep or remove a result from the result list
- adds a loop over ['data_src', 'audio_src'] instead of doubling code lines
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
import re
|
|
from urllib.parse import urlunparse, urlparse
|
|
from searx import settings
|
|
from searx.plugins import logger
|
|
from flask_babel import gettext
|
|
|
|
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 = ['data_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
|