nuke/data/botPolicies.yaml

## Anubis has the ability to let you import snippets of configuration into the main
## configuration file. This allows you to break up your config into smaller parts
## that get logically assembled into one big file.
##
## Of note, a bot rule can either have inline bot configuration or import a
## bot config snippet. You cannot do both in a single bot rule.
##
## Import paths can either be prefixed with (data) to import from the common/shared
## rules in the data folder in the Anubis source tree or will point to absolute/relative
## paths in your filesystem. If you don't have access to the Anubis source tree, check
## /usr/share/docs/anubis/data or in the tarball you extracted Anubis from.

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

  # Aggressively block AI/LLM related bots/agents by default
  - import: (data)/meta/ai-block-aggressive.yaml

  # Consider replacing the aggressive AI policy with more selective policies:
  # - import: (data)/meta/ai-block-moderate.yaml
  # - import: (data)/meta/ai-block-permissive.yaml

  # Search engine crawlers to allow, defaults to:
  #   - Google (so they don't try to bypass Anubis)
  #   - Apple
  #   - Bing
  #   - DuckDuckGo
  #   - Qwant
  #   - The Internet Archive
  #   - Kagi
  #   - Marginalia
  #   - Mojeek
  - import: (data)/crawlers/_allow-good.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

  # # Punish any bot with "bot" in the user-agent string
  # # This is known to have a high false-positive rate, use at your own risk
  # - name: generic-bot-catchall
  #   user_agent_regex: (?i:bot|crawler)
  #   action: CHALLENGE
  #   challenge:
  #     difficulty: 16  # impossible
  #     report_as: 4    # lie to the operator
  #     algorithm: slow # intentionally waste CPU cycles and time

  # Requires a subscription to Thoth to use, see
  # https://anubis.techaro.lol/docs/admin/thoth#geoip-based-filtering
  - name: countries-with-aggressive-scrapers
    action: WEIGH
    geoip:
      countries:
        - BR
        - CN
    weight:
      adjust: 10

  # Requires a subscription to Thoth to use, see
  # https://anubis.techaro.lol/docs/admin/thoth#asn-based-filtering
  - name: aggressive-asns-without-functional-abuse-contact
    action: WEIGH
    asns:
      match:
        - 13335 # Cloudflare
        - 136907 # Huawei Cloud
        - 45102 # Alibaba Cloud
    weight:
      adjust: 10

  # Generic catchall rule
  - name: generic-browser
    user_agent_regex: >-
      Mozilla|Opera
    action: WEIGH
    weight:
      adjust: 10

dnsbl: false

# Open Graph passthrough configuration, see here for more information:
# https://anubis.techaro.lol/docs/admin/configuration/open-graph/
openGraph:
  # Enables Open Graph passthrough
  enabled: false
  # Enables the use of the HTTP host in the cache key, this enables
  # caching metadata for multiple http hosts at once.
  considerHost: false
  # How long cached OpenGraph metadata should last in memory
  ttl: 24h
  # # If set, return these opengraph values instead of looking them up with
  # # the target service.
  # #
  # # Correlates to properties in https://ogp.me/
  # override:
  #   # og:title is required, it is the title of the website
  #   "og:title": "Techaro Anubis"
  #   "og:description": >-
  #     Anubis is a Web AI Firewall Utility that helps you fight the bots
  #     away so that you can maintain uptime at work!
  #   "description": >-
  #     Anubis is a Web AI Firewall Utility that helps you fight the bots
  #     away so that you can maintain uptime at work!

# By default, send HTTP 200 back to clients that either get issued a challenge
# or a denial. This seems weird, but this is load-bearing due to the fact that
# the most aggressive scraper bots seem to really, really, want an HTTP 200 and
# will stop sending requests once they get it.
status_codes:
  CHALLENGE: 200
  DENY: 200

# The weight thresholds for when to trigger individual challenges. Any
# CHALLENGE will take precedence over this.
#
# A threshold has four configuration options:
#
#   - name: the name that is reported down the stack and used for metrics
#   - expression: A CEL expression with the request weight in the variable
#     weight
#   - action: the Anubis action to apply, similar to in a bot policy
#   - challenge: which challenge to send to the user, similar to in a bot policy
#
# See https://anubis.techaro.lol/docs/admin/configuration/thresholds for more
# information.
thresholds:
  # By default Anubis ships with the following thresholds:
  - name: minimal-suspicion # This client is likely fine, its soul is lighter than a feather
    expression: weight < 0 # a feather weighs zero units
    action: ALLOW # Allow the traffic through
  # For clients that had some weight reduced through custom rules, give them a
  # lightweight challenge.
  - name: mild-suspicion
    expression:
      all:
        - weight >= 0
        - weight < 10
    action: CHALLENGE
    challenge:
      # https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
      algorithm: metarefresh
      difficulty: 1
      report_as: 1
  # For clients that are browser-like but have either gained points from custom rules or
  # report as a standard browser.
  - name: moderate-suspicion
    expression:
      all:
        - weight >= 10
        - weight < 20
    action: CHALLENGE
    challenge:
      # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
      algorithm: fast
      difficulty: 2 # two leading zeros, very fast for most clients
      report_as: 2
  # For clients that are browser like and have gained many points from custom rules
  - name: extreme-suspicion
    expression: weight >= 20
    action: CHALLENGE
    challenge:
      # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
      algorithm: fast
      difficulty: 4
      report_as: 4