searxng/searx/botdetection/ip_lists.py
Ivan Gabaldon eb9f20a823
[mod] botdetection: trusted proxies
Replaces `x_for` functionality with `trusted_proxies`. This allows defining which IP / ranges to trust extracting the client IP address from X-Forwarded-For and X-Real-IP headers.

We don't know if the proxy chain will give us the proper client address, so we rely on reading the headers of the proxy before SearXNG (if there is one, in that case it must be added to trusted_proxies) hoping it has done the proper checks. In case a proxy in the chain does not check the client address correctly, integrity is compromised and this should be fixed by whoever manages the proxy, not us.

I had to move the get_cnf func to another file (config.py) to prevent cyclic imports since we need to read the list inside _helpers.py

Closes https://github.com/searxng/searxng/issues/4907
Closes https://github.com/searxng/searxng/issues/3632
Closes https://github.com/searxng/searxng/issues/3191
Closes https://github.com/searxng/searxng/issues/1237

Related https://github.com/searxng/searxng-docker/issues/386
Related https://github.com/inetol-infrastructure/searxng-container/issues/81
2025-07-10 20:40:56 +02:00

103 lines
3.3 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
""".. _botdetection.ip_lists:
Method ``ip_lists``
-------------------
The ``ip_lists`` method implements IP
:py:obj:`trusted_proxies <trusted_proxies>`, :py:obj:`block-list <block_ip>`
and :py:obj:`pass-list <pass_ip>`.
.. code:: toml
[botdetection.ip_lists]
trusted_proxies = [
'127.0.0.1/32', # IPv4 localhost
'::1', # IPv6 localhost
'192.168.0.0/16', # IPv4 private network
]
pass_ip = [
'167.235.158.251', # IPv4 of check.searx.space
'192.168.0.0/16', # IPv4 private network
'fe80::/10' # IPv6 linklocal
]
block_ip = [
'93.184.216.34', # IPv4 of example.org
'257.1.1.1', # invalid IP --> will be ignored, logged in ERROR class
]
"""
# pylint: disable=unused-argument
from __future__ import annotations
from typing import Tuple
from ipaddress import (
ip_network,
IPv4Address,
IPv6Address,
)
from . import config
from ._helpers import logger
logger = logger.getChild('ip_limit')
SEARXNG_ORG = [
# https://github.com/searxng/searxng/pull/2484#issuecomment-1576639195
'167.235.158.251', # IPv4 check.searx.space
'2a01:04f8:1c1c:8fc2::/64', # IPv6 check.searx.space
]
"""Passlist of IPs from the SearXNG organization, e.g. `check.searx.space`."""
def trusted_proxies(remote_addr: IPv4Address | IPv6Address, cfg: config.Config) -> bool:
"""Checks if the remote IP is in one of the members of the
``botdetection.ip_lists.trusted_proxies`` list.
"""
for net in cfg.get("botdetection.ip_lists.trusted_proxies", default=["127.0.0.1/32", "::1"]):
net = ip_network(net, strict=False)
if remote_addr.version == net.version and remote_addr in net:
return True
return False
def pass_ip(real_ip: IPv4Address | IPv6Address, cfg: config.Config) -> Tuple[bool, str]:
"""Checks if the IP on the subnet is in one of the members of the
``botdetection.ip_lists.pass_ip`` list.
"""
if cfg.get('botdetection.ip_lists.pass_searxng_org', default=True):
for net in SEARXNG_ORG:
net = ip_network(net, strict=False)
if real_ip.version == net.version and real_ip in net:
return True, f"IP matches {net.compressed} in SEARXNG_ORG list."
return ip_is_subnet_of_member_in_list(real_ip, 'botdetection.ip_lists.pass_ip', cfg)
def block_ip(real_ip: IPv4Address | IPv6Address, cfg: config.Config) -> Tuple[bool, str]:
"""Checks if the IP on the subnet is in one of the members of the
``botdetection.ip_lists.block_ip`` list.
"""
block, msg = ip_is_subnet_of_member_in_list(real_ip, 'botdetection.ip_lists.block_ip', cfg)
if block:
msg += " To remove IP from list, please contact the maintainer of the service."
return block, msg
def ip_is_subnet_of_member_in_list(
real_ip: IPv4Address | IPv6Address, list_name: str, cfg: config.Config
) -> Tuple[bool, str]:
for net in cfg.get(list_name, default=[]):
try:
net = ip_network(net, strict=False)
except ValueError:
logger.error("invalid IP %s in %s", net, list_name)
continue
if real_ip.version == net.version and real_ip in net:
return True, f"IP matches {net.compressed} in {list_name}."
return False, f"IP is not a member of an item in the f{list_name} list"