mirror of
https://github.com/searxng/searxng.git
synced 2025-10-31 10:37:06 -04:00
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>
78 lines
2.8 KiB
Python
78 lines
2.8 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""Raise exception for an HTTP response is an error.
|
|
|
|
"""
|
|
|
|
from searx.exceptions import (
|
|
SearxEngineCaptchaException,
|
|
SearxEngineTooManyRequestsException,
|
|
SearxEngineAccessDeniedException,
|
|
)
|
|
from searx import get_setting
|
|
|
|
|
|
def is_cloudflare_challenge(resp):
|
|
if resp.status_code in [429, 503]:
|
|
if ('__cf_chl_jschl_tk__=' in resp.text) or (
|
|
'/cdn-cgi/challenge-platform/' in resp.text
|
|
and 'orchestrate/jsch/v1' in resp.text
|
|
and 'window._cf_chl_enter(' in resp.text
|
|
):
|
|
return True
|
|
if resp.status_code == 403 and '__cf_chl_captcha_tk__=' in resp.text:
|
|
return True
|
|
return False
|
|
|
|
|
|
def is_cloudflare_firewall(resp):
|
|
return resp.status_code == 403 and '<span class="cf-error-code">1020</span>' in resp.text
|
|
|
|
|
|
def raise_for_cloudflare_captcha(resp):
|
|
if resp.headers.get('Server', '').startswith('cloudflare'):
|
|
if is_cloudflare_challenge(resp):
|
|
# https://support.cloudflare.com/hc/en-us/articles/200170136-Understanding-Cloudflare-Challenge-Passage-Captcha-
|
|
# suspend for 2 weeks
|
|
raise SearxEngineCaptchaException(
|
|
message='Cloudflare CAPTCHA', suspended_time=get_setting('search.suspended_times.cf_SearxEngineCaptcha')
|
|
)
|
|
|
|
if is_cloudflare_firewall(resp):
|
|
raise SearxEngineAccessDeniedException(
|
|
message='Cloudflare Firewall',
|
|
suspended_time=get_setting('search.suspended_times.cf_SearxEngineAccessDenied'),
|
|
)
|
|
|
|
|
|
def raise_for_recaptcha(resp):
|
|
if resp.status_code == 503 and '"https://www.google.com/recaptcha/' in resp.text:
|
|
raise SearxEngineCaptchaException(
|
|
message='ReCAPTCHA', suspended_time=get_setting('search.suspended_times.recaptcha_SearxEngineCaptcha')
|
|
)
|
|
|
|
|
|
def raise_for_captcha(resp):
|
|
raise_for_cloudflare_captcha(resp)
|
|
raise_for_recaptcha(resp)
|
|
|
|
|
|
def raise_for_httperror(resp):
|
|
"""Raise exception for an HTTP response is an error.
|
|
|
|
Args:
|
|
resp (requests.Response): Response to check
|
|
|
|
Raises:
|
|
requests.HTTPError: raise by resp.raise_for_status()
|
|
searx.exceptions.SearxEngineAccessDeniedException: raise when the HTTP status code is 402 or 403.
|
|
searx.exceptions.SearxEngineTooManyRequestsException: raise when the HTTP status code is 429.
|
|
searx.exceptions.SearxEngineCaptchaException: raise when if CATPCHA challenge is detected.
|
|
"""
|
|
if resp.status_code and resp.status_code >= 400:
|
|
raise_for_captcha(resp)
|
|
if resp.status_code in (402, 403):
|
|
raise SearxEngineAccessDeniedException(message='HTTP error ' + str(resp.status_code))
|
|
if resp.status_code == 429:
|
|
raise SearxEngineTooManyRequestsException()
|
|
resp.raise_for_status()
|