Files

62 lines
1.7 KiB
YAML

bots:
# Pathological bots to deny
- # This correlates to data/bots/deny-pathological.yaml in the source tree
# https://github.com/TecharoHQ/anubis/blob/main/data/bots/deny-pathological.yaml
import: (data)/bots/_deny-pathological.yaml
- import: (data)/bots/aggressive-brazilian-scrapers.yaml
- import: /amazonips.yaml # deny aws ips due to frequent scraper usage
- import: /oracleips.yaml # despite the name oraclenhuawei, this is a list ive compiled of datacenter ip ranges used by scrapers
# Aggressively block AI/LLM related bots/agents by default
- import: (data)/meta/ai-block-aggressive.yaml
# Challenge Firefox AI previews
- import: (data)/clients/x-firefox-ai.yaml
# Allow common "keeping the internet working" routes (well-known, favicon, robots.txt)
- import: (data)/common/keep-internet-working.yaml
- name: whitelist-home-ip
action: ALLOW
expression:
remoteAddress == "REDACTED" # nice try
- name: fastside
action: ALLOW
expression:
remoteAddress == "194.62.248.14"
- name: donottrack_strict
action: CHALLENGE
expression:
all:
- '"Dnt" in headers'
- 'headers["Dnt"] == "1"'
- '"Sec-Gpc" in headers'
- 'headers["Sec-Gpc"] == "1"'
- '"Te" in headers'
- 'headers["Te"] == "trailers"'
- '"Priority" in headers'
challenge:
algorithm: fast
difficulty: 5
report_as: 1
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 3
report_as: 1
dnsbl: true
status_codes:
CHALLENGE: 200
DENY: 429
# ^ | tricks bots into making less requests