diff options
author | Alexandre Flament <alex@al-f.net> | 2021-04-05 10:43:33 +0200 |
---|---|---|
committer | Alexandre Flament <alex@al-f.net> | 2021-04-12 17:25:56 +0200 |
commit | d14994dc73ba5c95382812581dac146d9eceaafa (patch) | |
tree | 2f7720dbae8f1064fe479f986f0b198aff2beb99 /searx/network/raise_for_httperror.py | |
parent | eaa694fb7d0e47b943bc6d6edb6cb6a40ab2d85e (diff) |
[httpx] replace searx.poolrequests by searx.network
settings.yml:
* outgoing.networks:
* can contains network definition
* propertiers: enable_http, verify, http2, max_connections, max_keepalive_connections,
keepalive_expiry, local_addresses, support_ipv4, support_ipv6, proxies, max_redirects, retries
* retries: 0 by default, number of times searx retries to send the HTTP request (using different IP & proxy each time)
* local_addresses can be "192.168.0.1/24" (it supports IPv6)
* support_ipv4 & support_ipv6: both True by default
see https://github.com/searx/searx/pull/1034
* each engine can define a "network" section:
* either a full network description
* either reference an existing network
* all HTTP requests of engine use the same HTTP configuration (it was not the case before, see proxy configuration in master)
Diffstat (limited to 'searx/network/raise_for_httperror.py')
-rw-r--r-- | searx/network/raise_for_httperror.py | 66 |
1 files changed, 66 insertions, 0 deletions
diff --git a/searx/network/raise_for_httperror.py b/searx/network/raise_for_httperror.py new file mode 100644 index 00000000..bd12df9a --- /dev/null +++ b/searx/network/raise_for_httperror.py @@ -0,0 +1,66 @@ +# SPDX-License-Identifier: AGPL-3.0-or-later +""" +Raise exception for an HTTP response is an error. +""" +from searx.exceptions import (SearxEngineCaptchaException, SearxEngineTooManyRequestsException, + SearxEngineAccessDeniedException) + + +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=3600 * 24 * 15) + + if is_cloudflare_firewall(resp): + raise SearxEngineAccessDeniedException(message='Cloudflare Firewall', suspended_time=3600 * 24) + + +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=3600 * 24 * 7) + + +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), + suspended_time=3600 * 24) + if resp.status_code == 429: + raise SearxEngineTooManyRequestsException() + resp.raise_for_status() |