zaclys/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng synced 2024-01-01 19:24:07 +01:00
Code Issues Projects Releases Packages Wiki Activity

add log info

Browse source
This commit is contained in:
capric98 2022-04-07 00:36:01 +08:00
parent 0eeb22bf82
commit 9f395dc57d
1 changed files with 15 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
searx/plugins/limiter.py
View file

@ -25,6 +25,10 @@ default_on = False
preference_section = 'service' preference_section = 'service'
c_burst_limit = 15
c_10min_limit = 150
re_bot = re.compile( re_bot = re.compile(
r'(' r'('
+ r'[Cc][Uu][Rr][Ll]|[wW]get|Scrapy|splash|JavaFX|FeedFetcher|python-requests|Go-http-client|Java|Jakarta|okhttp' + r'[Cc][Uu][Rr][Ll]|[wW]get|Scrapy|splash|JavaFX|FeedFetcher|python-requests|Go-http-client|Java|Jakarta|okhttp'
@ -36,6 +40,11 @@ re_bot = re.compile(
) )
if "logger" not in locals():
import logging
logger = logging.getLogger("searx.plugins.limiter")
def cdn_reported_ip(headers: dict) -> str: def cdn_reported_ip(headers: dict) -> str:
# some commonly used CDNs: # some commonly used CDNs:
cdn_keys = [ cdn_keys = [
@ -62,6 +71,7 @@ def is_accepted_request(inc_get_counter) -> bool:
if request.path == '/image_proxy': if request.path == '/image_proxy':
if re_bot.match(user_agent): if re_bot.match(user_agent):
logger.info(f"reject [{client_ip}]: client may be a bot described by UA=\"{user_agent}\"")
return False return False
return True return True
@ -69,13 +79,16 @@ def is_accepted_request(inc_get_counter) -> bool:
c_burst = inc_get_counter(interval=20, keys=[b'IP limit, burst', client_ip]) c_burst = inc_get_counter(interval=20, keys=[b'IP limit, burst', client_ip])
c_10min = inc_get_counter(interval=600, keys=[b'IP limit, 10 minutes', client_ip]) c_10min = inc_get_counter(interval=600, keys=[b'IP limit, 10 minutes', client_ip])
if c_burst > 15 or c_10min > 150: if c_burst > c_burst_limit or c_10min > c_10min_limit:
logger.info(f"reject [{client_ip}]: c_burst({c_burst})>{c_burst_limit} or c_10min({c_10min})>{c_10min_limit}")
return False return False
if re_bot.match(user_agent): if re_bot.match(user_agent):
logger.info(f"reject [{client_ip}]: client may be a bot described by UA=\"{user_agent}\"")
return False return False
if request.headers.get('Accept-Language', '').strip(): if request.headers.get('Accept-Language', '').strip():
logger.info(f"reject [{client_ip}]: empty Accept-Language")
return False return False
# If SearXNG is behind Cloudflare, all requests will get 429 because # If SearXNG is behind Cloudflare, all requests will get 429 because
@ -89,6 +102,7 @@ def is_accepted_request(inc_get_counter) -> bool:
# return False # return False
if 'text/html' not in request.accept_mimetypes: if 'text/html' not in request.accept_mimetypes:
logger.info(f"reject [{client_ip}]: non-html request to /search")
return False return False
# IDK but maybe api limit should based on path not format? # IDK but maybe api limit should based on path not format?