kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-09-29 16:10:16 +02:00
Code

[mod] limiter: minor improvements

Browse Source 
- requests without HTTP header 'Connection' or missing 'User-Agent' will be
  blocked by the limiter

- re_bot is related to 'User-Agent' and has been renamed to block_user_agent

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2023-04-01 12:34:58 +02:00
parent 7592d85982
commit 66810ce711
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
searx/plugins/limiter.py
View File

@ -26,13 +26,17 @@ default_on = False
preference_section = 'service'
logger = logger.getChild('limiter')
re_bot = re.compile(
block_user_agent = re.compile(
r'('
+ r'[Cc][Uu][Rr][Ll]|[wW]get|Scrapy|splash|JavaFX|FeedFetcher|python-requests|Go-http-client|Java|Jakarta|okhttp'
+ r'unknown'
+ r'|[Cc][Uu][Rr][Ll]|[wW]get|Scrapy|splash|JavaFX|FeedFetcher|python-requests|Go-http-client|Java|Jakarta|okhttp'
+ r'|HttpClient|Jersey|Python|libwww-perl|Ruby|SynHttpClient|UniversalFeedParser|Googlebot|GoogleImageProxy'
+ r'|bingbot|Baiduspider|yacybot|YandexMobileBot|YandexBot|Yahoo! Slurp|MJ12bot|AhrefsBot|archive.org_bot|msnbot'
+ r'|MJ12bot|SeznamBot|linkdexbot|Netvibes|SMTBot|zgrab|James BOT|Sogou|Abonti|Pixray|Spinn3r|SemrushBot|Exabot'
+ r'|ZmEu|BLEXBot|bitlybot'
# when you block requests from Farside instances, your instance will
# disappear from https://farside.link/
# + r'|Farside'
+ r')'
)
@ -40,14 +44,15 @@ re_bot = re.compile(
def is_accepted_request() -> bool:
# pylint: disable=too-many-return-statements
redis_client = redisdb.client()
user_agent = request.headers.get('User-Agent', '')
user_agent = request.headers.get('User-Agent', 'unknown')
x_forwarded_for = request.headers.get('X-Forwarded-For', '')
if re_bot.match(user_agent):
logger.debug("BLOCK %s: detected bot", x_forwarded_for)
if block_user_agent.match(user_agent):
logger.debug("BLOCK %s: %s --> detected User-Agent: %s" % (x_forwarded_for, request.path, user_agent))
return False
if request.path == '/search':
c_burst = incr_sliding_window(redis_client, 'IP limit, burst' + x_forwarded_for, 20)
c_10min = incr_sliding_window(redis_client, 'IP limit, 10 minutes' + x_forwarded_for, 600)
if c_burst > 15 or c_10min > 150: