Compare commits

..

1 Commits

Author SHA1 Message Date
Jason Cameron
b488220228 chore: remove duplicate CHANGELOG entry
Signed-off-by: Jason Cameron <git@jasoncameron.dev>
2025-06-17 18:45:07 -04:00
79 changed files with 569 additions and 1977 deletions

View File

@@ -83,9 +83,7 @@
^\Q.github/FUNDING.yml\E$
^\Q.github/workflows/spelling.yml\E$
^data/crawlers/
^docs/blog/tags\.yml$
^docs/manifest/.*$
^docs/static/\.nojekyll$
^lib/policy/config/testdata/bad/unparseable\.json$
ignore$
robots.txt

View File

@@ -44,6 +44,7 @@ chall
challengemozilla
checkpath
checkresult
chen
chibi
cidranger
ckie
@@ -60,6 +61,7 @@ DDOS
Debian
debrpm
decaymap
decompiling
Diffbot
discordapp
discordbot
@@ -129,7 +131,6 @@ iat
ifm
Imagesift
imgproxy
impressum
inp
IPTo
iptoasn
@@ -187,7 +188,6 @@ ogtags
omgili
omgilibot
openai
opengraph
openrc
pag
palemoon
@@ -218,7 +218,6 @@ rawler
rcvar
redir
redirectscheme
refactors
relayd
reputational
reqmeta
@@ -239,7 +238,6 @@ Seo
setsebool
shellcheck
Sidetrade
simprint
sitemap
sls
sni
@@ -263,7 +261,6 @@ techarohq
templ
templruntime
testarea
Thancred
thoth
thothmock
Tik
@@ -303,7 +300,6 @@ xess
xff
XForwarded
XNG
XOB
XReal
yae
YAMLTo

View File

@@ -273,6 +273,14 @@
# Most people only have two hands. Reword.
\b(?i)on the third hand\b
# Should be `Open Graph`
# unless talking about a specific Open Graph implementation:
# - Java
# - Node
# - Py
# - Ruby
\bOpenGraph\b
# Should be `OpenShift`
\bOpenshift\b

View File

@@ -22,7 +22,7 @@ jobs:
persist-credentials: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Log into registry
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
@@ -50,14 +50,14 @@ jobs:
push: true
- name: Apply k8s manifests to aeacus
uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
uses: actions-hub/kubectl@f632a31512a74cb35940627c49c20f67723cbaaf # v1.33.1
env:
KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
with:
args: apply -k docs/manifest
- name: Apply k8s manifests to aeacus
uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
uses: actions-hub/kubectl@f632a31512a74cb35940627c49c20f67723cbaaf # v1.33.1
env:
KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
with:

View File

@@ -18,7 +18,7 @@ jobs:
persist-credentials: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Docker meta
id: meta

View File

@@ -30,7 +30,7 @@ jobs:
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build and push
run: |
cd ./test/ssh-ci

View File

@@ -21,7 +21,7 @@ jobs:
persist-credentials: false
- name: Install the latest version of uv
uses: astral-sh/setup-uv@445689ea25e0de0a23313031f5fe577c74ae45a1 # v6.3.0
uses: astral-sh/setup-uv@f0ec1fc3b38f5e7cd731bb6ce540c5af426746bb # v6.1.0
- name: Run zizmor 🌈
run: uvx zizmor --format sarif . > results.sarif

View File

@@ -18,7 +18,6 @@ assets: deps
build: assets
$(GO) build -o ./var/anubis ./cmd/anubis
$(GO) build -o ./var/robots2policy ./cmd/robots2policy
@echo "Anubis is now built to ./var/anubis"
lint: assets
@@ -28,7 +27,6 @@ lint: assets
prebaked-build:
$(GO) build -o ./var/anubis -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/anubis
$(GO) build -o ./var/robots2policy -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/robots2policy
test: assets
$(GO) test ./...

View File

@@ -1 +1 @@
1.20.0-pre2
1.19.1

View File

@@ -331,28 +331,22 @@ func main() {
slog.Warn("REDIRECT_DOMAINS is not set, Anubis will only redirect to the same domain a request is coming from, see https://anubis.techaro.lol/docs/admin/configuration/redirect-domains")
}
// If OpenGraph configuration values are not set in the config file, use the
// values from flags / envvars.
if !policy.OpenGraph.Enabled {
policy.OpenGraph.Enabled = *ogPassthrough
policy.OpenGraph.ConsiderHost = *ogCacheConsiderHost
policy.OpenGraph.TimeToLive = *ogTimeToLive
policy.OpenGraph.Override = map[string]string{}
}
s, err := libanubis.New(libanubis.Options{
BasePrefix: *basePrefix,
StripBasePrefix: *stripBasePrefix,
Next: rp,
Policy: policy,
ServeRobotsTXT: *robotsTxt,
PrivateKey: priv,
CookieDomain: *cookieDomain,
CookieExpiration: *cookieExpiration,
CookiePartitioned: *cookiePartitioned,
RedirectDomains: redirectDomainsList,
Target: *target,
WebmasterEmail: *webmasterEmail,
BasePrefix: *basePrefix,
StripBasePrefix: *stripBasePrefix,
Next: rp,
Policy: policy,
ServeRobotsTXT: *robotsTxt,
PrivateKey: priv,
CookieDomain: *cookieDomain,
CookieExpiration: *cookieExpiration,
CookiePartitioned: *cookiePartitioned,
OGPassthrough: *ogPassthrough,
OGTimeToLive: *ogTimeToLive,
RedirectDomains: redirectDomainsList,
Target: *target,
WebmasterEmail: *webmasterEmail,
OGCacheConsidersHost: *ogCacheConsiderHost,
})
if err != nil {
log.Fatalf("can't construct libanubis.Server: %v", err)

View File

@@ -56,7 +56,7 @@ bots:
- name: countries-with-aggressive-scrapers
action: WEIGH
geoip:
countries:
counties:
- BR
- CN
weight:
@@ -84,59 +84,6 @@ bots:
dnsbl: false
# #
# impressum:
# # Displayed at the bottom of every page rendered by Anubis.
# footer: >-
# This website is hosted by Zonbocom. If you have any complaints or notes
# about the service, please contact
# <a href="mailto:contact@domainhere.example">contact@domainhere.example</a>
# and we will assist you as soon as possible.
# # The imprint page that will be linked to at the footer of every Anubis page.
# page:
# # The HTML <title> of the page
# title: Imprint and Privacy Policy
# # The HTML contents of the page. The exact contents of this page can
# # and will vary by locale. Please consult with a lawyer if you are not
# # sure what to put here
# body: >-
# <p>Last updated: June 2025</p>
# <h2>Information that is gathered from visitors</h2>
# <p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
# <p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
# <p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
# <!-- ... -->
# 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
@@ -144,57 +91,3 @@ openGraph:
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

View File

@@ -2,5 +2,5 @@
# Note: Blocks human-directed/non-training user agents
- name: "ai-robots-txt"
user_agent_regex: >-
AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|bedrockbot|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|MyCentralAIScraperBot|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|Poseidon Research Crawler|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot|SemrushBot-BA|SemrushBot-CT|SemrushBot-OCOB|SemrushBot-SI|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot
AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|bedrockbot|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot
action: DENY

View File

@@ -11,139 +11,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
## v1.20.0: Thancred Waters
The big ticket items are as follows:
- Implement a no-JS challenge method: [`metarefresh`](./admin/configuration/challenges/metarefresh.mdx) ([#95](https://github.com/TecharoHQ/anubis/issues/95))
- Implement request "weight", allowing administrators to customize the behaviour of Anubis based on specific criteria
- Implement GeoIP and ASN based checks via [Thoth](https://anubis.techaro.lol/docs/admin/thoth) ([#206](https://github.com/TecharoHQ/anubis/issues/206))
- Add [custom weight thresholds](./admin/configuration/thresholds.mdx) via CEL ([#688](https://github.com/TecharoHQ/anubis/pull/688))
- Move Open Graph configuration [to the policy file](./admin/configuration/open-graph.mdx)
- Enable support for Open Graph metadata to be returned by default instead of doing lookups against the target
- Add `robots2policy` CLI utility to convert robots.txt files to Anubis challenge policies using CEL expressions ([#409](https://github.com/TecharoHQ/anubis/issues/409))
- Refactor challenge presentation logic to use a challenge registry
- Allow challenge implementations to register HTTP routes
- [Imprint/Impressum support](./admin/configuration/impressum.mdx) ([#362](https://github.com/TecharoHQ/anubis/issues/362))
- Fix "invalid response" after "Success!" in Chromium ([#564](https://github.com/TecharoHQ/anubis/issues/564))
A lot of performance improvements have been made:
- Replace internal SHA256 hashing with xxhash for 4-6x performance improvement in policy evaluation and cache operations
- Optimized the OGTags subsystem with reduced allocations and runtime per request by up to 66%
- Replace cidranger with bart for IP range checking, improving IP matching performance by 3-20x with zero heap
- Replace cidranger with bart for IP range checking, improving IP matching performance by 3-20x with zero heap
allocations
And some cleanups/refactors were added:
- Remove the unused `/test-error` endpoint and update the testing endpoint `/make-challenge` to only be enabled in
development
- Add `--xff-strip-private` flag/envvar to toggle skipping X-Forwarded-For private addresses or not
- Bump AI-robots.txt to version 1.37
- Requests can have their weight be adjusted, if a request weighs zero or less than it is allowed through
- Refactor challenge presentation logic to use a challenge registry
- Allow challenge implementations to register HTTP routes
- Implement a no-JS challenge method: [`metarefresh`](./admin/configuration/challenges/metarefresh.mdx) ([#95](https://github.com/TecharoHQ/anubis/issues/95))
- Bump AI-robots.txt to version 1.34
- Make progress bar styling more compatible (UXP, etc)
- Optimized the OGTags subsystem with reduced allocations and runtime per request by up to 66%
- Add `--strip-base-prefix` flag/envvar to strip the base prefix from request paths when forwarding to target servers
- Fix an off-by-one in the default threshold config
Request weight is one of the biggest ticket features in Anubis. This enables Anubis to be much closer to a Web Application Firewall and when combined with custom thresholds allows administrators to have Anubis take advanced reactions. For more information about request weight, see [the request weight section](./admin/policies.mdx#request-weight) of the policy file documentation.
TL;DR when you have one or more WEIGHT rules like this:
```yaml
bots:
- name: gitea-session-token
action: WEIGH
expression:
all:
- '"Cookie" in headers'
- headers["Cookie"].contains("i_love_gitea=")
# Remove 5 weight points
weight:
adjust: -5
```
You can configure custom thresholds like this:
```yaml
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
```
These thresholds apply when no other `ALLOW`, `DENY`, or `CHALLENGE` rule matches the request. `WEIGHT` rules add and remove request weight as needed:
```yaml
bots:
- name: gitea-session-token
action: WEIGH
expression:
all:
- '"Cookie" in headers'
- headers["Cookie"].contains("i_love_gitea=")
# Remove 5 weight points
weight:
adjust: -5
- name: bot-like-user-agent
action: WEIGH
expression: '"Bot" in userAgent'
# Add 5 weight points
weight:
adjust: 5
```
Of note: the default "generic browser" rule assigns 10 weight points:
```yaml
# Generic catchall rule
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: WEIGH
weight:
adjust: 10
```
Adjust this as you see fit.
- Add `robots2policy` CLI utility to convert robots.txt files to Anubis challenge policies using CEL expressions ([#409](https://github.com/TecharoHQ/anubis/issues/409))
- Implement GeoIP and ASN based checks via [Thoth](https://anubis.techaro.lol/docs/admin/thoth) ([#206](https://github.com/TecharoHQ/anubis/issues/206))
- Replace internal SHA256 hashing with xxhash for 4-6x performance improvement in policy evaluation and cache operations
## v1.19.1: Jenomis cen Lexentale - Echo 1

View File

@@ -1,70 +0,0 @@
# Imprint / Impressum configuration
Some jurisdictions (such as the European Union and specifically Germany) [must have contact information freely available](https://www.privacycompany.eu/blog/the-imprint-requirement-a-must-have-for-companies-from-outside-germany) on an imprint/impressum page. Anubis supports creating an Anubis-specific imprint page for your organization with the `impressum` block in your bot policy file. For example:
```yaml
impressum:
# Displayed at the bottom of every page rendered by Anubis.
footer: >-
This website is hosted by Techaro. If you have any complaints or notes
about the service, please contact
<a href="mailto:contact@techaro.lol">contact@techaro.lol</a> and we
will assist you as soon as possible.
# The imprint page that will be linked to at the footer of every Anubis page.
page:
# The HTML <title> of the page
title: Imprint and Privacy Policy
# The HTML contents of the page. The exact contents of this page can
# and will vary by locale. Please consult with a lawyer if you are not
# sure what to put here
body: >-
<p>Last updated: June 2025</p>
<h2>Information that is gathered from visitors</h2>
<p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
<p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
<p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
<!-- ... -->
```
If you are subscribed to and using [advanced classification features](../thoth.mdx), be sure to disclose the following:
```html
<h2>Techaro Anubis</h2>
<p>
This website uses a service called
<a href="https://anubis.techaro.lol">Anubis</a> by
<a href="https://techaro.lol">Techaro</a> to filter malicious traffic. Anubis
requires the use of browser cookies to ensure that web clients are running
conformant software. Anubis also may report the following data to Techaro to
improve service quality:
</p>
<ul>
<li>
IP address (for purposes of matching against geo-location and BGP autonomous
systems numbers), which is stored in-memory and not persisted to disk.
</li>
<li>
Unique browser fingerprints (such as HTTP request fingerprints and
encryption system fingerprints), which may be stored on Techaro's side for a
period of up to one month.
</li>
<li>
HTTP request metadata that may include things such as the User-Agent header
and other identifiers.
</li>
</ul>
<p>
This data is processed and stored for the legitimate interest of combatting
abusive web clients. This data is encrypted at rest as much as possible and is
only decrypted in memory for the purposes of fulfilling requests.
</p>
```

View File

@@ -9,45 +9,12 @@ This page provides detailed information on how to configure [Open Graph tag](htt
## Configuration Options
Open Graph settings are configured in the `openGraph` section of the [Policy File](../policies.mdx).
```yaml
openGraph:
# Enables Open Graph passthrough
enabled: true
# Enables the use of the HTTP host in the cache key, this enables
# caching metadata for multiple http hosts at once.
considerHost: true
# 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!
```
<details>
<summary>Configuration flags / envvars (old)</summary>
Open Graph passthrough used to be configured with configuration flags / environment variables. Reference to these settings are maintained for backwards compatibility's sake.
| Name | Description | Type | Default | Example |
| ------------------------ | --------------------------------------------------------- | -------- | ------- | ----------------------------- |
| `OG_PASSTHROUGH` | Enables or disables the Open Graph tag passthrough system | Boolean | `true` | `OG_PASSTHROUGH=true` |
| `OG_EXPIRY_TIME` | Configurable cache expiration time for Open Graph tags | Duration | `24h` | `OG_EXPIRY_TIME=1h` |
| `OG_CACHE_CONSIDER_HOST` | Enables or disables the use of the host in the cache key | Boolean | `false` | `OG_CACHE_CONSIDER_HOST=true` |
</details>
## Usage
To configure Open Graph tags, you can set the following environment variables, environment file or as flags in your Anubis configuration:

View File

@@ -1,140 +0,0 @@
# Weight Threshold Configuration
Anubis offers the ability to assign "weight" to requests. This is a custom level of suspicion that rules can add to or remove from. For example, here's how you assign 10 weight points to anything that might be a browser:
```yaml
# botPolicies.yaml
bots:
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: WEIGH
weight:
adjust: 10
```
Thresholds let you take this per-request weight value and take actions in response to it. Thresholds are defined alongside your bot configuration in `botPolicies.yaml`.
:::note
Thresholds DO NOT apply when a request matches a bot rule with the CHALLENGE action. Thresholds only apply when requests don't match any terminal bot rules.
:::
```yaml
# botPolicies.yaml
bots: ...
thresholds:
- name: minimal-suspicion
expression: weight < 0
action: ALLOW
- name: mild-suspicion
expression:
all:
- weight >= 0
- weight < 10
action: CHALLENGE
challenge:
algorithm: metarefresh
difficulty: 1
report_as: 1
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 2
report_as: 2
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 4
report_as: 4
```
This defines a suite of 4 thresholds:
1. If the request weight is less than zero, allow it through.
2. If the request weight is greater than or equal to zero, but less than ten: give it [a very lightweight challenge](./challenges/metarefresh.mdx).
3. If the request weight is greater than or equal to ten, but less than twenty: give it [a slightly heavier challenge](./challenges/proof-of-work.mdx).
4. Otherwise, give it [the heaviest challenge](./challenges/proof-of-work.mdx).
Thresholds can be configured with the following options:
<table>
<thead>
<tr>
<th>Name</th>
<th>Description</th>
<th>Example</th>
</tr>
</thead>
<tbody>
<tr>
<td>`name`</td>
<td>The human-readable name for this threshold.</td>
<td>
```yaml
name: extreme-suspicion
```
</td>
</tr>
<tr>
<td>`expression`</td>
<td>A [CEL](https://cel.dev/) expression taking the request weight and returning true or false</td>
<td>
To check if the request weight is less than zero:
```yaml
expression: weight < 0
```
To check if it's between 0 and 10 (inclusive):
```yaml
expression:
all:
- weight >= 0
- weight < 10
```
</td>
</tr>
<tr>
<td>`action`</td>
<td>The Anubis action to apply: `ALLOW`, `CHALLENGE`, or `DENY`</td>
<td>
```yaml
action: ALLOW
```
If you set the CHALLENGE action, you must set challenge details:
```yaml
action: CHALLENGE
challenge:
algorithm: metarefresh
difficulty: 1
report_as: 1
```
</td>
</tr>
</tbody>
</table>

View File

@@ -4,6 +4,7 @@ title: Setting up Anubis
import RandomKey from "@site/src/components/RandomKey";
Anubis is meant to sit between your reverse proxy (such as Nginx or Caddy) and your target service. One instance of Anubis must be used per service you are protecting.
<center>
@@ -29,7 +30,7 @@ TLS terminator)
Anubis is shipped in the Docker repo [`ghcr.io/techarohq/anubis`](https://github.com/TecharoHQ/anubis/pkgs/container/anubis). The following tags exist for your convenience:
| Tag | Meaning |
| :------------------ | :--------------------------------------------------------------------------------------------------------------------------------- |
|:--------------------|:-----------------------------------------------------------------------------------------------------------------------------------|
| `latest` | The latest [tagged release](https://github.com/TecharoHQ/anubis/releases), if you are in doubt, start here. |
| `v<version number>` | The Anubis image for [any given tagged release](https://github.com/TecharoHQ/anubis/tags) |
| `main` | The current build on the `main` branch. Only use this if you need the latest and greatest features as they are merged into `main`. |
@@ -42,24 +43,12 @@ Anubis has very minimal system requirements. I suspect that 128Mi of ram may be
For more detailed information on installing Anubis with native packages, please read [the native install directions](./native-install.mdx).
## Configuration
Anubis is configurable via environment variables and [the policy file](./policies.mdx). Most settings are currently exposed with environment variables but they are being slowly moved over to the policy file.
### Configuration via the policy file
Currently the following settings are configurable via the policy file:
- [Bot policies](./policies.mdx)
- [Open Graph passthrough](./configuration/open-graph.mdx)
- [Weight thresholds](./configuration/thresholds.mdx)
### Environment variables
## Environment variables
Anubis uses these environment variables for configuration:
| Environment Variable | Default value | Explanation |
| :----------------------------- | :---------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|:-------------------------------|:------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `BASE_PREFIX` | unset | If set, adds a global prefix to all Anubis endpoints. For example, setting this to `/myapp` would make Anubis accessible at `/myapp/` instead of `/`. This is useful when running Anubis behind a reverse proxy that routes based on path prefixes. |
| `BIND` | `:8923` | The network address that Anubis listens on. For `unix`, set this to a path: `/run/anubis/instance.sock` |
| `BIND_NETWORK` | `tcp` | The address family that Anubis listens on. Accepts `tcp`, `unix` and anything Go's [`net.Listen`](https://pkg.go.dev/net#Listen) supports. |
@@ -71,9 +60,9 @@ Anubis uses these environment variables for configuration:
| `ED25519_PRIVATE_KEY_HEX_FILE` | unset | Path to a file containing the hex-encoded ed25519 private key. Only one of this or its sister option may be set. |
| `METRICS_BIND` | `:9090` | The network address that Anubis serves Prometheus metrics on. See `BIND` for more information. |
| `METRICS_BIND_NETWORK` | `tcp` | The address family that the Anubis metrics server listens on. See `BIND_NETWORK` for more information. |
| `OG_EXPIRY_TIME` | `24h` | The expiration time for the Open Graph tag cache. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_PASSTHROUGH` | `false` | If set to `true`, Anubis will enable Open Graph tag passthrough. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_CACHE_CONSIDER_HOST` | `false` | If set to `true`, Anubis will consider the host in the Open Graph tag cache key. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_EXPIRY_TIME` | `24h` | The expiration time for the Open Graph tag cache. |
| `OG_PASSTHROUGH` | `false` | If set to `true`, Anubis will enable Open Graph tag passthrough. |
| `OG_CACHE_CONSIDER_HOST` | `false` | If set to `true`, Anubis will consider the host in the Open Graph tag cache key. |
| `POLICY_FNAME` | unset | The file containing [bot policy configuration](./policies.mdx). See the bot policy documentation for more details. If unset, the default bot policy configuration is used. |
| `REDIRECT_DOMAINS` | unset | If set, restrict the domains that Anubis can redirect to when passing a challenge.<br/><br/>If this is unset, Anubis may redirect to any domain which could cause security issues in the unlikely case that an attacker passes a challenge for your browser and then tricks you into clicking a link to your domain.<br/><br/>Note that if you are hosting Anubis on a non-standard port (`https://example:com:8443`, `http://www.example.net:8080`, etc.), you must also include the port number here. |
| `SERVE_ROBOTS_TXT` | `false` | If set `true`, Anubis will serve a default `robots.txt` file that disallows all known AI scrapers by name and then additionally disallows every scraper. This is useful if facts and circumstances make it difficult to change the underlying service to serve such a `robots.txt` file. |
@@ -149,7 +138,6 @@ STRIP_BASE_PREFIX=true
```
With this configuration:
- A request to `/myapp/api/users` would be forwarded to your target service as `/api/users`
- A request to `/myapp/` would be forwarded as `/`

View File

@@ -233,10 +233,6 @@ remote_addresses:
</TabItem>
</Tabs>
## Imprint / Impressum support
Anubis has support for showing imprint / impressum information. This is defined in the `impressum` block of your configuration. See [Imprint / Impressum configuration](./configuration/impressum.mdx) for more information.
## Risk calculation for downstream services
In case your service needs it for risk calculation reasons, Anubis exposes information about the rules that any requests match using a few headers:
@@ -265,11 +261,17 @@ Anubis rules can also add or remove "weight" from requests, allowing administrat
adjust: -5
```
This would remove five weight points from the request, which would make Anubis present the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx) in the default configuration.
This would remove five weight points from the request, making Anubis present the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx).
### Weight Thresholds
For more information on configuring weight thresholds, see [Weight Threshold Configuration](./configuration/thresholds.mdx)
Weight thresholds and challenge associations will be configurable with CEL expressions in the configuration file in an upcoming patch, for now here's how Anubis configures the weight thresholds:
| Weight Expression | Action |
| -----------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------- |
| `weight < 0` (weight is less than 0) | Allow the request through. |
| `weight < 10` (weight is less than 10) | Challenge the client with the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx) at the default difficulty level. |
| `weight >= 10` (weight is greater than or equal to 10) | Challenge the client with the [Proof of Work challenge](./configuration/challenges/proof-of-work.mdx) at the default difficulty level. |
### Advice

View File

@@ -59,7 +59,7 @@ For example, to add 10 weight points to requests from Brazil and China:
- name: countries-with-aggressive-scrapers
action: WEIGH
geoip:
countries:
counties:
- BR
- CN
weight:

View File

@@ -58,9 +58,7 @@ This will build all static assets (CSS, JavaScript) for distribution.
make build
```
From this point it is up to you to make sure that `./var/anubis` and `./var/robots2policy` end up in
the right place. You may want to consult the `./run` folder for useful files such as a systemd unit
and `anubis.env.default` file.
From this point it is up to you to make sure that `./var/anubis` ends up in the right place. You may want to consult the `./run` folder for useful files such as a systemd unit and `anubis.env.default` file.
## "Pre-baked" tarball
@@ -77,7 +75,7 @@ When using this tarball, all you need to do is build `./cmd/anubis`:
make prebaked-build
```
Anubis will be built to `./var/anubis` and the robots2policy tool to `./var/robots2policy`.
Anubis will be built to `./var/anubis`.
## Development dependencies

View File

@@ -44,7 +44,6 @@ This page contains a non-exhaustive list with all websites using Anubis.
- https://squirreljme.cc/
- https://gitlab.postmarketos.org/
- https://wiki.koha-community.org/
- https://extensions.typo3.org/
- <details>
<summary>FreeCAD</summary>
- https://forum.freecad.org/

View File

@@ -70,55 +70,6 @@ bots:
dnsbl: false
impressum:
footer: |
This website is hosted by Techaro. If you have any complaints or notes about the service, please contact <a href="mailto:contact@techaro.lol">contact@techaro.lol</a> and we will assist you as soon as possible.
page:
title: Privacy Policy
body: |
<p>Last updated: June 2025</p>
<h2>Information that is gathered from visitors</h2>
<p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
<p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
<p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
<h2>How the Information is used</h2>
<p>The information is used to enhance the vistor's experience when using the website to display personalised content and possibly advertising.</p>
<p>E-mail addresses will not be sold, rented or leased to 3rd parties.</p>
<p>E-mail may be sent to inform you of news of our services or offers by us or our affiliates.</p>
<h2>Visitor Options</h2>
<p>If you have subscribed to one of our services, you may unsubscribe by following the instructions which are included in e-mail that you receive.</p>
<p>You may be able to block cookies via your browser settings but this may prevent you from access to certain features of the website.</p>
<h2>Cookies</h2>
<p>Cookies are small digital signature files that are stored by your web browser that allow your preferences to be recorded when visiting the website. Also they may be used to track your return visits to the website.</p>
<p>3rd party advertising companies may also use cookies for tracking purposes.</p>
<h2>Techaro Anubis</h2>
<p>This website uses a service called <a href="https://anubis.techaro.lol">Anubis</a> to filter malicious traffic. Anubis requires the use of browser cookies to ensure that web clients are running conformant software. Anubis also may report the following data to Techaro to improve service quality:</p>
<ul>
<li>IP address (for purposes of matching against geo-location and BGP autonomous systems numbers), which is stored in-memory and not persisted to disk.</li>
<li>Unique browser fingerprints (such as HTTP request fingerprints and encryption system fingerprints), which may be stored on Techaro's side for a period of up to one month.</li>
<li>HTTP request metadata that may include things such as the User-Agent header and other identifiers.</li>
</ul>
<p>This data is processed and stored for the legitimate interest of combatting abusive web clients. This data is encrypted at rest as much as possible and is only decrypted in memory for the purposes of fulfilling requests.</p>
# 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

View File

@@ -13,10 +13,6 @@ func (c *OGTagCache) GetOGTags(url *url.URL, originalHost string) (map[string]st
return nil, errors.New("nil URL provided, cannot fetch OG tags")
}
if len(c.ogOverride) != 0 {
return c.ogOverride, nil
}
target := c.getTarget(url)
cacheKey := c.generateCacheKey(target, originalHost)

View File

@@ -7,49 +7,10 @@ import (
"reflect"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestCacheReturnsDefault(t *testing.T) {
want := map[string]string{
"og:title": "Foo bar",
"og:description": "The best website ever made!!!1!",
}
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
Override: want,
})
u, err := url.Parse("https://anubis.techaro.lol")
if err != nil {
t.Fatal(err)
}
result, err := cache.GetOGTags(u, "anubis.techaro.lol")
if err != nil {
t.Fatal(err)
}
for k, v := range want {
t.Run(k, func(t *testing.T) {
if got := result[k]; got != v {
t.Logf("want: tags[%q] = %q", k, v)
t.Logf("got: tags[%q] = %q", k, got)
t.Error("invalid result from function")
}
})
}
}
func TestCheckCache(t *testing.T) {
cache := NewOGTagCache("http://example.com", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("http://example.com", true, time.Minute, false)
// Set up test data
urlStr := "http://example.com/page"
@@ -108,11 +69,7 @@ func TestGetOGTags(t *testing.T) {
defer ts.Close()
// Create an instance of OGTagCache with a short TTL for testing
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
// Parse the test server URL
parsedURL, err := url.Parse(ts.URL)
@@ -259,11 +216,7 @@ func TestGetOGTagsWithHostConsideration(t *testing.T) {
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
loadCount = 0 // Reset load count for each test case
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: tc.ogCacheConsiderHost,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, tc.ogCacheConsiderHost)
for i, req := range tc.requests {
ogTags, err := cache.GetOGTags(parsedURL, req.host)

View File

@@ -10,7 +10,6 @@ import (
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
@@ -81,11 +80,7 @@ func TestFetchHTMLDocument(t *testing.T) {
}))
defer ts.Close()
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("", true, time.Minute, false)
doc, err := cache.fetchHTMLDocument(ts.URL, "anything")
if tt.expectError {
@@ -112,11 +107,7 @@ func TestFetchHTMLDocumentInvalidURL(t *testing.T) {
t.Skip("test requires theoretical network egress")
}
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("", true, time.Minute, false)
doc, err := cache.fetchHTMLDocument("http://invalid.url.that.doesnt.exist.example", "anything")

View File

@@ -6,8 +6,6 @@ import (
"net/url"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestIntegrationGetOGTags(t *testing.T) {
@@ -106,11 +104,7 @@ func TestIntegrationGetOGTags(t *testing.T) {
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
// Create cache instance
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
// Create URL for test
testURL, _ := url.Parse(ts.URL)

View File

@@ -6,7 +6,6 @@ import (
"strings"
"testing"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
@@ -30,7 +29,7 @@ func BenchmarkGetTarget(b *testing.B) {
for _, tt := range tests {
b.Run(tt.name, func(b *testing.B) {
cache := NewOGTagCache(tt.target, config.OpenGraph{})
cache := NewOGTagCache(tt.target, false, 0, false)
urls := make([]*url.URL, len(tt.paths))
for i, path := range tt.paths {
u, _ := url.Parse(path)
@@ -66,7 +65,7 @@ func BenchmarkExtractOGTags(b *testing.B) {
</head><body><div><p>Content</p></div></body></html>`,
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
cache := NewOGTagCache("http://example.com", false, 0, false)
docs := make([]*html.Node, len(htmlSamples))
for i, sample := range htmlSamples {
@@ -84,7 +83,7 @@ func BenchmarkExtractOGTags(b *testing.B) {
// Memory usage test
func TestMemoryUsage(t *testing.T) {
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
cache := NewOGTagCache("http://example.com", false, 0, false)
// Force GC and wait for it to complete
runtime.GC()

View File

@@ -10,7 +10,6 @@ import (
"time"
"github.com/TecharoHQ/anubis/decaymap"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
const (
@@ -33,10 +32,9 @@ type OGTagCache struct {
ogTimeToLive time.Duration
ogCacheConsiderHost bool
ogPassthrough bool
ogOverride map[string]string
}
func NewOGTagCache(target string, conf config.OpenGraph) *OGTagCache {
func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration, ogTagsConsiderHost bool) *OGTagCache {
// Predefined approved tags and prefixes
defaultApprovedTags := []string{"description", "keywords", "author"}
defaultApprovedPrefixes := []string{"og:", "twitter:", "fediverse:"}
@@ -79,10 +77,9 @@ func NewOGTagCache(target string, conf config.OpenGraph) *OGTagCache {
return &OGTagCache{
cache: decaymap.New[string, map[string]string](),
targetURL: parsedTargetURL,
ogPassthrough: conf.Enabled,
ogTimeToLive: conf.TimeToLive,
ogCacheConsiderHost: conf.ConsiderHost,
ogOverride: conf.Override,
ogPassthrough: ogPassthrough,
ogTimeToLive: ogTimeToLive,
ogCacheConsiderHost: ogTagsConsiderHost,
approvedTags: defaultApprovedTags,
approvedPrefixes: defaultApprovedPrefixes,
client: client,

View File

@@ -6,7 +6,6 @@ import (
"testing"
"unicode/utf8"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
@@ -46,7 +45,7 @@ func FuzzGetTarget(f *testing.F) {
}
// Create cache - should not panic
cache := NewOGTagCache(target, config.OpenGraph{})
cache := NewOGTagCache(target, false, 0, false)
// Create URL
u := &url.URL{
@@ -130,7 +129,7 @@ func FuzzExtractOGTags(f *testing.F) {
return
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
cache := NewOGTagCache("http://example.com", false, 0, false)
// Should not panic
tags := cache.extractOGTags(doc)
@@ -186,7 +185,7 @@ func FuzzGetTargetRoundTrip(f *testing.F) {
t.Skip()
}
cache := NewOGTagCache(target, config.OpenGraph{})
cache := NewOGTagCache(target, false, 0, false)
u := &url.URL{Path: path, RawQuery: query}
result := cache.getTarget(u)
@@ -243,7 +242,7 @@ func FuzzExtractMetaTagInfo(f *testing.F) {
},
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
cache := NewOGTagCache("http://example.com", false, 0, false)
// Should not panic
property, content := cache.extractMetaTagInfo(node)
@@ -296,7 +295,7 @@ func BenchmarkFuzzedGetTarget(b *testing.B) {
for _, input := range inputs {
b.Run(input.name, func(b *testing.B) {
cache := NewOGTagCache(input.target, config.OpenGraph{})
cache := NewOGTagCache(input.target, false, 0, false)
u := &url.URL{Path: input.path, RawQuery: input.query}
b.ResetTimer()

View File

@@ -13,8 +13,6 @@ import (
"strings"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestNewOGTagCache(t *testing.T) {
@@ -40,11 +38,7 @@ func TestNewOGTagCache(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, config.OpenGraph{
Enabled: tt.ogPassthrough,
TimeToLive: tt.ogTimeToLive,
ConsiderHost: false,
})
cache := NewOGTagCache(tt.target, tt.ogPassthrough, tt.ogTimeToLive, false)
if cache == nil {
t.Fatal("expected non-nil cache, got nil")
@@ -80,11 +74,7 @@ func TestNewOGTagCache_UnixSocket(t *testing.T) {
socketPath := filepath.Join(tempDir, "test.sock")
target := "unix://" + socketPath
cache := NewOGTagCache(target, config.OpenGraph{
Enabled: true,
TimeToLive: 5 * time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(target, true, 5*time.Minute, false)
if cache == nil {
t.Fatal("expected non-nil cache, got nil")
@@ -165,11 +155,7 @@ func TestGetTarget(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(tt.target, false, time.Minute, false)
u := &url.URL{
Path: tt.path,
@@ -189,9 +175,7 @@ func TestGetTarget(t *testing.T) {
func TestIntegrationGetOGTags_UnixSocket(t *testing.T) {
tempDir := t.TempDir()
// XXX(Xe): if this is named longer, macOS fails with `bind: invalid argument`
// because the unix socket path is too long. I love computers.
socketPath := filepath.Join(tempDir, "t")
socketPath := filepath.Join(tempDir, "anubis-test.sock")
// Ensure the socket does not exist initially
_ = os.Remove(socketPath)
@@ -238,11 +222,7 @@ func TestIntegrationGetOGTags_UnixSocket(t *testing.T) {
// Create cache instance pointing to the Unix socket
targetURL := "unix://" + socketPath
cache := NewOGTagCache(targetURL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(targetURL, true, 1*time.Minute, false)
// Create a dummy URL for the request (path and query matter)
testReqURL, _ := url.Parse("/some/page?query=1")

View File

@@ -6,18 +6,13 @@ import (
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
// TestExtractOGTags updated with correct expectations based on filtering logic
func TestExtractOGTags(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", config.OpenGraph{
Enabled: false,
ConsiderHost: false,
TimeToLive: time.Minute,
})
testCache := NewOGTagCache("", false, time.Minute, false)
// Manually set approved tags/prefixes based on the user request for clarity
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}
@@ -194,11 +189,7 @@ func TestIsOGMetaTag(t *testing.T) {
func TestExtractMetaTagInfo(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", config.OpenGraph{
Enabled: false,
ConsiderHost: false,
TimeToLive: time.Minute,
})
testCache := NewOGTagCache("", false, time.Minute, false)
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}

View File

@@ -15,7 +15,6 @@ import (
"time"
"github.com/golang-jwt/jwt/v5"
"github.com/google/cel-go/common/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promauto"
@@ -77,8 +76,14 @@ type Server struct {
func (s *Server) challengeFor(r *http.Request, difficulty int) string {
fp := sha256.Sum256(s.pub[:])
acceptLanguage := r.Header.Get("Accept-Language")
if len(acceptLanguage) > 5 {
acceptLanguage = acceptLanguage[:5]
}
challengeData := fmt.Sprintf(
"X-Real-IP=%s,User-Agent=%s,WeekTime=%s,Fingerprint=%x,Difficulty=%d",
"Accept-Language=%s,X-Real-IP=%s,User-Agent=%s,WeekTime=%s,Fingerprint=%x,Difficulty=%d",
acceptLanguage,
r.Header.Get("X-Real-Ip"),
r.UserAgent(),
time.Now().UTC().Round(24*7*time.Hour).Format(time.RFC3339),
@@ -406,6 +411,12 @@ func cr(name string, rule config.Rule, weight int) policy.CheckResult {
}
}
var (
weightOkayStatic = policy.NewStaticHashChecker("weight/okay")
weightMildSusStatic = policy.NewStaticHashChecker("weight/mild-suspicion")
weightVerySusStatic = policy.NewStaticHashChecker("weight/extreme-suspicion")
)
// Check evaluates the list of rules, and returns the result
func (s *Server) check(r *http.Request) (policy.CheckResult, *policy.Bot, error) {
host := r.Header.Get("X-Real-Ip")
@@ -437,25 +448,34 @@ func (s *Server) check(r *http.Request) (policy.CheckResult, *policy.Bot, error)
}
}
for _, t := range s.policy.Thresholds {
result, _, err := t.Program.ContextEval(r.Context(), &policy.ThresholdRequest{Weight: weight})
if err != nil {
slog.Error("error when evaluating threshold expression", "expression", t.Expression.String(), "err", err)
continue
}
var matches bool
if val, ok := result.(types.Bool); ok {
matches = bool(val)
}
if matches {
return cr("threshold/"+t.Name, t.Action, weight), &policy.Bot{
Challenge: t.Challenge,
Rules: &checker.List{},
}, nil
}
switch {
case weight <= 0:
return cr("weight/okay", config.RuleAllow, weight), &policy.Bot{
Challenge: &config.ChallengeRules{
Difficulty: s.policy.DefaultDifficulty,
ReportAs: s.policy.DefaultDifficulty,
Algorithm: config.DefaultAlgorithm,
},
Rules: weightOkayStatic,
}, nil
case weight > 0 && weight < 10:
return cr("weight/mild-suspicion", config.RuleChallenge, weight), &policy.Bot{
Challenge: &config.ChallengeRules{
Difficulty: s.policy.DefaultDifficulty,
ReportAs: s.policy.DefaultDifficulty,
Algorithm: "metarefresh",
},
Rules: weightMildSusStatic,
}, nil
case weight >= 10:
return cr("weight/extreme-suspicion", config.RuleChallenge, weight), &policy.Bot{
Challenge: &config.ChallengeRules{
Difficulty: s.policy.DefaultDifficulty,
ReportAs: s.policy.DefaultDifficulty,
Algorithm: "fast",
},
Rules: weightVerySusStatic,
}, nil
}
return cr("default/allow", config.RuleAllow, weight), &policy.Bot{

View File

@@ -24,16 +24,12 @@ func init() {
internal.InitSlog("debug")
}
func loadPolicies(t *testing.T, fname string, difficulty int) *policy.ParsedConfig {
func loadPolicies(t *testing.T, fname string) *policy.ParsedConfig {
t.Helper()
ctx := thothmock.WithMockThoth(t)
if fname == "" {
fname = "./testdata/test_config.yaml"
}
anubisPolicy, err := LoadPoliciesOrDefault(ctx, fname, difficulty)
anubisPolicy, err := LoadPoliciesOrDefault(ctx, fname, anubis.DefaultDifficulty)
if err != nil {
t.Fatal(err)
}
@@ -44,10 +40,6 @@ func loadPolicies(t *testing.T, fname string, difficulty int) *policy.ParsedConf
func spawnAnubis(t *testing.T, opts Options) *Server {
t.Helper()
if opts.Policy == nil {
opts.Policy = loadPolicies(t, "", 4)
}
s, err := New(opts)
if err != nil {
t.Fatalf("can't construct libanubis.Server: %v", err)
@@ -184,7 +176,8 @@ func TestLoadPolicies(t *testing.T) {
// Regression test for CVE-2025-24369
func TestCVE2025_24369(t *testing.T) {
pol := loadPolicies(t, "", anubis.DefaultDifficulty)
pol := loadPolicies(t, "")
pol.DefaultDifficulty = 4
srv := spawnAnubis(t, Options{
Next: http.NewServeMux(),
@@ -207,7 +200,8 @@ func TestCVE2025_24369(t *testing.T) {
}
func TestCookieCustomExpiration(t *testing.T) {
pol := loadPolicies(t, "", 0)
pol := loadPolicies(t, "")
pol.DefaultDifficulty = 0
ckieExpiration := 10 * time.Minute
srv := spawnAnubis(t, Options{
@@ -256,7 +250,8 @@ func TestCookieCustomExpiration(t *testing.T) {
}
func TestCookieSettings(t *testing.T) {
pol := loadPolicies(t, "", 0)
pol := loadPolicies(t, "")
pol.DefaultDifficulty = 0
srv := spawnAnubis(t, Options{
Next: http.NewServeMux(),
@@ -321,7 +316,10 @@ func TestCheckDefaultDifficultyMatchesPolicy(t *testing.T) {
for i := 1; i < 10; i++ {
t.Run(fmt.Sprint(i), func(t *testing.T) {
anubisPolicy := loadPolicies(t, "", i)
anubisPolicy, err := LoadPoliciesOrDefault(t.Context(), "", i)
if err != nil {
t.Fatal(err)
}
s, err := New(Options{
Next: h,
@@ -339,13 +337,11 @@ func TestCheckDefaultDifficultyMatchesPolicy(t *testing.T) {
req.Header.Add("X-Real-Ip", "127.0.0.1")
cr, bot, err := s.check(req)
_, bot, err := s.check(req)
if err != nil {
t.Fatal(err)
}
t.Log(cr.Name)
if bot.Challenge.Difficulty != i {
t.Errorf("Challenge.Difficulty is wrong, wanted %d, got: %d", i, bot.Challenge.Difficulty)
}
@@ -393,7 +389,8 @@ func TestBasePrefix(t *testing.T) {
// Reset the global BasePrefix before each test
anubis.BasePrefix = ""
pol := loadPolicies(t, "", 4)
pol := loadPolicies(t, "")
pol.DefaultDifficulty = 4
srv := spawnAnubis(t, Options{
Next: h,
@@ -521,7 +518,8 @@ func TestCustomStatusCodes(t *testing.T) {
"DENY": 403,
}
pol := loadPolicies(t, "./testdata/aggressive_403.yaml", 4)
pol := loadPolicies(t, "./testdata/aggressive_403.yaml")
pol.DefaultDifficulty = 4
srv := spawnAnubis(t, Options{
Next: h,
@@ -555,7 +553,7 @@ func TestCustomStatusCodes(t *testing.T) {
func TestCloudflareWorkersRule(t *testing.T) {
for _, variant := range []string{"cel", "header"} {
t.Run(variant, func(t *testing.T) {
pol := loadPolicies(t, "./testdata/cloudflare-workers-"+variant+".yaml", 0)
pol := loadPolicies(t, "./testdata/cloudflare-workers-"+variant+".yaml")
h := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
fmt.Fprintln(w, "OK")
@@ -611,7 +609,8 @@ func TestCloudflareWorkersRule(t *testing.T) {
}
func TestRuleChange(t *testing.T) {
pol := loadPolicies(t, "testdata/rule_change.yaml", 0)
pol := loadPolicies(t, "testdata/rule_change.yaml")
pol.DefaultDifficulty = 0
ckieExpiration := 10 * time.Minute
srv := spawnAnubis(t, Options{

View File

@@ -7,7 +7,6 @@ import (
"sync"
"github.com/TecharoHQ/anubis/lib/policy"
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/a-h/templ"
)
@@ -41,19 +40,12 @@ func Methods() []string {
return result
}
type IssueInput struct {
Impressum *config.Impressum
Rule *policy.Bot
Challenge string
OGTags map[string]string
}
type Impl interface {
// Setup registers any additional routes with the Impl for assets or API routes.
Setup(mux *http.ServeMux)
// Issue a new challenge to the user, called by the Anubis.
Issue(r *http.Request, lg *slog.Logger, in *IssueInput) (templ.Component, error)
Issue(r *http.Request, lg *slog.Logger, rule *policy.Bot, challenge string, ogTags map[string]string) (templ.Component, error)
// Validate a challenge, making sure that it passes muster.
Validate(r *http.Request, lg *slog.Logger, rule *policy.Bot, challenge string) error

View File

@@ -23,7 +23,7 @@ type Impl struct{}
func (i *Impl) Setup(mux *http.ServeMux) {}
func (i *Impl) Issue(r *http.Request, lg *slog.Logger, in *challenge.IssueInput) (templ.Component, error) {
func (i *Impl) Issue(r *http.Request, lg *slog.Logger, rule *policy.Bot, challenge string, ogTags map[string]string) (templ.Component, error) {
u, err := r.URL.Parse(anubis.BasePrefix + "/.within.website/x/cmd/anubis/api/pass-challenge")
if err != nil {
return nil, fmt.Errorf("can't render page: %w", err)
@@ -31,10 +31,10 @@ func (i *Impl) Issue(r *http.Request, lg *slog.Logger, in *challenge.IssueInput)
q := u.Query()
q.Set("redir", r.URL.String())
q.Set("challenge", in.Challenge)
q.Set("challenge", challenge)
u.RawQuery = q.Encode()
component, err := web.BaseWithChallengeAndOGTags("Making sure you're not a bot!", page(in.Challenge, u.String(), in.Rule.Challenge.Difficulty), in.Impressum, in.Challenge, in.Rule.Challenge, in.OGTags)
component, err := web.BaseWithChallengeAndOGTags("Making sure you're not a bot!", page(challenge, u.String(), rule.Challenge.Difficulty), challenge, rule.Challenge, ogTags)
if err != nil {
return nil, fmt.Errorf("can't render page: %w", err)
}

View File

@@ -28,8 +28,8 @@ func (i *Impl) Setup(mux *http.ServeMux) {
/* no implementation required */
}
func (i *Impl) Issue(r *http.Request, lg *slog.Logger, in *chall.IssueInput) (templ.Component, error) {
component, err := web.BaseWithChallengeAndOGTags("Making sure you're not a bot!", web.Index(), in.Impressum, in.Challenge, in.Rule.Challenge, in.OGTags)
func (i *Impl) Issue(r *http.Request, lg *slog.Logger, rule *policy.Bot, challenge string, ogTags map[string]string) (templ.Component, error) {
component, err := web.BaseWithChallengeAndOGTags("Making sure you're not a bot!", web.Index(), challenge, rule.Challenge, ogTags)
if err != nil {
return nil, fmt.Errorf("can't render page: %w", err)
}

View File

@@ -124,12 +124,7 @@ func TestBasic(t *testing.T) {
t.Run(cs.name, func(t *testing.T) {
lg := slog.With()
inp := &challenge.IssueInput{
Rule: bot,
Challenge: cs.challengeStr,
}
if _, err := i.Issue(cs.req, lg, inp); err != nil {
if _, err := i.Issue(cs.req, lg, bot, cs.challengeStr, nil); err != nil {
t.Errorf("can't issue challenge: %v", err)
}

View File

@@ -21,27 +21,27 @@ import (
"github.com/TecharoHQ/anubis/internal/ogtags"
"github.com/TecharoHQ/anubis/lib/challenge"
"github.com/TecharoHQ/anubis/lib/policy"
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/TecharoHQ/anubis/web"
"github.com/TecharoHQ/anubis/xess"
"github.com/a-h/templ"
)
type Options struct {
Next http.Handler
Policy *policy.ParsedConfig
Target string
CookieDomain string
CookieName string
BasePrefix string
WebmasterEmail string
RedirectDomains []string
PrivateKey ed25519.PrivateKey
CookieExpiration time.Duration
StripBasePrefix bool
OpenGraph config.OpenGraph
CookiePartitioned bool
ServeRobotsTXT bool
Next http.Handler
Policy *policy.ParsedConfig
Target string
CookieDomain string
CookieName string
BasePrefix string
WebmasterEmail string
RedirectDomains []string
PrivateKey ed25519.PrivateKey
CookieExpiration time.Duration
OGTimeToLive time.Duration
StripBasePrefix bool
OGCacheConsidersHost bool
OGPassthrough bool
CookiePartitioned bool
ServeRobotsTXT bool
}
func LoadPoliciesOrDefault(ctx context.Context, fname string, defaultDifficulty int) (*policy.ParsedConfig, error) {
@@ -112,7 +112,7 @@ func New(opts Options) (*Server, error) {
policy: opts.Policy,
opts: opts,
DNSBLCache: decaymap.New[string, dnsbl.DroneBLResponse](),
OGTags: ogtags.NewOGTagCache(opts.Target, opts.Policy.OpenGraph),
OGTags: ogtags.NewOGTagCache(opts.Target, opts.OGPassthrough, opts.OGTimeToLive, opts.OGCacheConsidersHost),
cookieName: cookieName,
}
@@ -150,14 +150,6 @@ func New(opts Options) (*Server, error) {
}), "GET")
}
if opts.Policy.Impressum != nil {
registerWithPrefix(anubis.APIPrefix+"imprint", http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
templ.Handler(
web.Base(opts.Policy.Impressum.Page.Title, opts.Policy.Impressum.Page, opts.Policy.Impressum),
).ServeHTTP(w, r)
}), "GET")
}
registerWithPrefix(anubis.APIPrefix+"pass-challenge", http.HandlerFunc(result.PassChallenge), "GET")
registerWithPrefix(anubis.APIPrefix+"check", http.HandlerFunc(result.maybeReverseProxyHttpStatusOnly), "")
registerWithPrefix("/", http.HandlerFunc(result.maybeReverseProxyOrPage), "")

View File

@@ -26,7 +26,7 @@ func TestBadConfigs(t *testing.T) {
for _, st := range finfos {
st := st
t.Run(st.Name(), func(t *testing.T) {
if _, err := LoadPoliciesOrDefault(t.Context(), filepath.Join("policy", "config", "testdata", "bad", st.Name()), anubis.DefaultDifficulty); err == nil {
if _, err := LoadPoliciesOrDefault(t.Context(), filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err == nil {
t.Fatal(err)
} else {
t.Log(err)

View File

@@ -80,7 +80,7 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
challengeStr := s.challengeFor(r, rule.Challenge.Difficulty)
var ogTags map[string]string = nil
if s.opts.OpenGraph.Enabled {
if s.opts.OGPassthrough {
var err error
ogTags, err = s.OGTags.GetOGTags(r.URL, r.Host)
if err != nil {
@@ -102,14 +102,7 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
return
}
in := &challenge.IssueInput{
Impressum: s.policy.Impressum,
Rule: rule,
Challenge: challengeStr,
OGTags: ogTags,
}
component, err := impl.Issue(r, lg, in)
component, err := impl.Issue(r, lg, rule, challengeStr, ogTags)
if err != nil {
lg.Error("[unexpected] render failed, please open an issue", "err", err) // This is likely a bug in the template. Should never be triggered as CI tests for this.
s.respondWithError(w, r, "Internal Server Error: please contact the administrator and ask them to look for the logs around \"RenderIndex\"")
@@ -125,7 +118,7 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
func (s *Server) RenderBench(w http.ResponseWriter, r *http.Request) {
templ.Handler(
web.Base("Benchmarking Anubis!", web.Bench(), s.policy.Impressum),
web.Base("Benchmarking Anubis!", web.Bench()),
).ServeHTTP(w, r)
}
@@ -134,7 +127,7 @@ func (s *Server) respondWithError(w http.ResponseWriter, r *http.Request, messag
}
func (s *Server) respondWithStatus(w http.ResponseWriter, r *http.Request, msg string, status int) {
templ.Handler(web.Base("Oh noes!", web.ErrorPage(msg, s.opts.WebmasterEmail), s.policy.Impressum), templ.WithStatus(status)).ServeHTTP(w, r)
templ.Handler(web.Base("Oh noes!", web.ErrorPage(msg, s.opts.WebmasterEmail)), templ.WithStatus(status)).ServeHTTP(w, r)
}
func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
@@ -187,7 +180,7 @@ func (s *Server) ServeHTTPNext(w http.ResponseWriter, r *http.Request) {
}
templ.Handler(
web.Base("You are not a bot!", web.StaticHappy(), s.policy.Impressum),
web.Base("You are not a bot!", web.StaticHappy()),
).ServeHTTP(w, r)
} else {
requestsProxied.WithLabelValues(r.Host).Inc()

View File

@@ -17,18 +17,47 @@ type CELChecker struct {
}
func NewCELChecker(cfg *config.ExpressionOrList) (*CELChecker, error) {
env, err := expressions.BotEnvironment()
env, err := expressions.NewEnvironment()
if err != nil {
return nil, err
}
program, err := expressions.Compile(env, cfg.String())
var src string
var ast *cel.Ast
if cfg.Expression != "" {
src = cfg.Expression
var iss *cel.Issues
intermediate, iss := env.Compile(src)
if iss != nil {
return nil, iss.Err()
}
ast, iss = env.Check(intermediate)
if iss != nil {
return nil, iss.Err()
}
}
if len(cfg.All) != 0 {
ast, err = expressions.Join(env, expressions.JoinAnd, cfg.All...)
}
if len(cfg.Any) != 0 {
ast, err = expressions.Join(env, expressions.JoinOr, cfg.Any...)
}
if err != nil {
return nil, err
}
program, err := expressions.Compile(env, ast)
if err != nil {
return nil, fmt.Errorf("can't compile CEL program: %w", err)
}
return &CELChecker{
src: cfg.String(),
src: src,
program: program,
}, nil
}

View File

@@ -1,55 +0,0 @@
package config
import (
"errors"
"fmt"
"testing"
)
func TestASNsValid(t *testing.T) {
for _, tt := range []struct {
name string
input *ASNs
err error
}{
{
name: "basic valid",
input: &ASNs{
Match: []uint32{13335}, // Cloudflare
},
},
{
name: "private ASN",
input: &ASNs{
Match: []uint32{64513, 4206942069}, // 16 and 32 bit private ASN
},
err: ErrPrivateASN,
},
} {
t.Run(tt.name, func(t *testing.T) {
if err := tt.input.Valid(); !errors.Is(err, tt.err) {
t.Logf("want: %v", tt.err)
t.Logf("got: %v", err)
t.Error("got wrong validation error")
}
})
}
}
func TestIsPrivateASN(t *testing.T) {
for _, tt := range []struct {
input uint32
output bool
}{
{13335, false}, // Cloudflare
{64513, true}, // 16 bit private ASN
{4206942069, true}, // 32 bit private ASN
} {
t.Run(fmt.Sprint(tt.input, "->", tt.output), func(t *testing.T) {
result := isPrivateASN(tt.input)
if result != tt.output {
t.Errorf("wanted isPrivateASN(%d) == %v, got: %v", tt.input, tt.output, result)
}
})
}
}

View File

@@ -10,7 +10,6 @@ import (
"os"
"regexp"
"strings"
"time"
"github.com/TecharoHQ/anubis/data"
"k8s.io/apimachinery/pkg/util/yaml"
@@ -44,15 +43,6 @@ const (
RuleBenchmark Rule = "DEBUG_BENCHMARK"
)
func (r Rule) Valid() error {
switch r {
case RuleAllow, RuleDeny, RuleChallenge, RuleWeigh, RuleBenchmark:
return nil
default:
return ErrUnknownAction
}
}
const DefaultAlgorithm = "fast"
type BotConfig struct {
@@ -194,18 +184,13 @@ type ChallengeRules struct {
}
var (
ErrChallengeDifficultyTooLow = errors.New("config.ChallengeRules: difficulty is too low (must be >= 1)")
ErrChallengeDifficultyTooHigh = errors.New("config.ChallengeRules: difficulty is too high (must be <= 64)")
ErrChallengeMustHaveAlgorithm = errors.New("config.ChallengeRules: must have algorithm name set")
ErrChallengeDifficultyTooLow = errors.New("config.Bot.ChallengeRules: difficulty is too low (must be >= 1)")
ErrChallengeDifficultyTooHigh = errors.New("config.Bot.ChallengeRules: difficulty is too high (must be <= 64)")
)
func (cr ChallengeRules) Valid() error {
var errs []error
if cr.Algorithm == "" {
errs = append(errs, ErrChallengeMustHaveAlgorithm)
}
if cr.Difficulty < 1 {
errs = append(errs, fmt.Errorf("%w, got: %d", ErrChallengeDifficultyTooLow, cr.Difficulty))
}
@@ -324,29 +309,20 @@ func (sc StatusCodes) Valid() error {
}
type fileConfig struct {
Bots []BotOrImport `json:"bots"`
DNSBL bool `json:"dnsbl"`
OpenGraph openGraphFileConfig `json:"openGraph,omitempty"`
Impressum *Impressum `json:"impressum,omitempty"`
StatusCodes StatusCodes `json:"status_codes"`
Thresholds []Threshold `json:"thresholds"`
Bots []BotOrImport `json:"bots"`
DNSBL bool `json:"dnsbl"`
StatusCodes StatusCodes `json:"status_codes"`
}
func (c *fileConfig) Valid() error {
func (c fileConfig) Valid() error {
var errs []error
if len(c.Bots) == 0 {
errs = append(errs, ErrNoBotRulesDefined)
}
for i, b := range c.Bots {
for _, b := range c.Bots {
if err := b.Valid(); err != nil {
errs = append(errs, fmt.Errorf("bot %d: %w", i, err))
}
}
if c.OpenGraph.Enabled {
if err := c.OpenGraph.Valid(); err != nil {
errs = append(errs, err)
}
}
@@ -355,12 +331,6 @@ func (c *fileConfig) Valid() error {
errs = append(errs, err)
}
for i, t := range c.Thresholds {
if err := t.Valid(); err != nil {
errs = append(errs, fmt.Errorf("threshold %d: %w", i, err))
}
}
if len(errs) != 0 {
return fmt.Errorf("config is not valid:\n%w", errors.Join(errs...))
}
@@ -369,13 +339,11 @@ func (c *fileConfig) Valid() error {
}
func Load(fin io.Reader, fname string) (*Config, error) {
c := &fileConfig{
StatusCodes: StatusCodes{
Challenge: http.StatusOK,
Deny: http.StatusOK,
},
var c fileConfig
c.StatusCodes = StatusCodes{
Challenge: http.StatusOK,
Deny: http.StatusOK,
}
if err := yaml.NewYAMLToJSONDecoder(fin).Decode(&c); err != nil {
return nil, fmt.Errorf("can't parse policy config YAML %s: %w", fname, err)
}
@@ -385,21 +353,10 @@ func Load(fin io.Reader, fname string) (*Config, error) {
}
result := &Config{
DNSBL: c.DNSBL,
OpenGraph: OpenGraph{
Enabled: c.OpenGraph.Enabled,
ConsiderHost: c.OpenGraph.ConsiderHost,
Override: c.OpenGraph.Override,
},
DNSBL: c.DNSBL,
StatusCodes: c.StatusCodes,
}
if c.OpenGraph.TimeToLive != "" {
// XXX(Xe): already validated in Valid()
ogTTL, _ := time.ParseDuration(c.OpenGraph.TimeToLive)
result.OpenGraph.TimeToLive = ogTTL
}
var validationErrs []error
for _, boi := range c.Bots {
@@ -422,27 +379,6 @@ func Load(fin io.Reader, fname string) (*Config, error) {
}
}
if c.Impressum != nil {
if err := c.Impressum.Valid(); err != nil {
validationErrs = append(validationErrs, err)
}
result.Impressum = c.Impressum
}
if len(c.Thresholds) == 0 {
c.Thresholds = DefaultThresholds
}
for _, t := range c.Thresholds {
if err := t.Valid(); err != nil {
validationErrs = append(validationErrs, err)
continue
}
result.Thresholds = append(result.Thresholds, t)
}
if len(validationErrs) > 0 {
return nil, fmt.Errorf("errors validating policy config %s: %w", fname, errors.Join(validationErrs...))
}
@@ -452,10 +388,7 @@ func Load(fin io.Reader, fname string) (*Config, error) {
type Config struct {
Bots []BotConfig
Thresholds []Threshold
DNSBL bool
Impressum *Impressum
OpenGraph OpenGraph
StatusCodes StatusCodes
}

View File

@@ -8,6 +8,7 @@ import (
"testing"
"github.com/TecharoHQ/anubis/data"
"k8s.io/apimachinery/pkg/util/yaml"
)
func p[V any](v V) *V { return &v }
@@ -312,8 +313,12 @@ func TestConfigValidBad(t *testing.T) {
}
defer fin.Close()
_, err = Load(fin, filepath.Join("testdata", "bad", st.Name()))
if err == nil {
var c fileConfig
if err := yaml.NewYAMLToJSONDecoder(fin).Decode(&c); err != nil {
t.Fatalf("can't decode file: %v", err)
}
if err := c.Valid(); err == nil {
t.Fatal("validation should have failed but didn't somehow")
} else {
t.Log(err)

View File

@@ -3,9 +3,7 @@ package config
import (
"encoding/json"
"errors"
"fmt"
"slices"
"strings"
)
var (
@@ -20,32 +18,6 @@ type ExpressionOrList struct {
Any []string `json:"any,omitempty" yaml:"any,omitempty"`
}
func (eol ExpressionOrList) String() string {
switch {
case len(eol.Expression) != 0:
return eol.Expression
case len(eol.All) != 0:
var sb strings.Builder
for i, pred := range eol.All {
if i != 0 {
fmt.Fprintf(&sb, " && ")
}
fmt.Fprintf(&sb, "( %s )", pred)
}
return sb.String()
case len(eol.Any) != 0:
var sb strings.Builder
for i, pred := range eol.Any {
if i != 0 {
fmt.Fprintf(&sb, " || ")
}
fmt.Fprintf(&sb, "( %s )", pred)
}
return sb.String()
}
panic("this should not happen")
}
func (eol ExpressionOrList) Equal(rhs *ExpressionOrList) bool {
if eol.Expression != rhs.Expression {
return false

View File

@@ -213,54 +213,3 @@ func TestExpressionOrListUnmarshalJSON(t *testing.T) {
})
}
}
func TestExpressionOrListString(t *testing.T) {
for _, tt := range []struct {
name string
in ExpressionOrList
out string
}{
{
name: "single expression",
in: ExpressionOrList{
Expression: "true",
},
out: "true",
},
{
name: "all",
in: ExpressionOrList{
All: []string{"true"},
},
out: "( true )",
},
{
name: "all with &&",
in: ExpressionOrList{
All: []string{"true", "true"},
},
out: "( true ) && ( true )",
},
{
name: "any",
in: ExpressionOrList{
All: []string{"true"},
},
out: "( true )",
},
{
name: "any with ||",
in: ExpressionOrList{
Any: []string{"true", "true"},
},
out: "( true ) || ( true )",
},
} {
t.Run(tt.name, func(t *testing.T) {
result := tt.in.String()
if result != tt.out {
t.Errorf("wanted %q, got: %q", tt.out, result)
}
})
}
}

View File

@@ -8,7 +8,7 @@ import (
)
var (
countryCodeRegexp = regexp.MustCompile(`^[a-zA-Z]{2}$`)
countryCodeRegexp = regexp.MustCompile(`^\w{2}$`)
ErrNotCountryCode = errors.New("config.Bot: invalid country code")
)

View File

@@ -1,36 +0,0 @@
package config
import (
"errors"
"testing"
)
func TestGeoIPValid(t *testing.T) {
for _, tt := range []struct {
name string
input *GeoIP
err error
}{
{
name: "basic valid",
input: &GeoIP{
Countries: []string{"CA"},
},
},
{
name: "invalid country",
input: &GeoIP{
Countries: []string{"XOB"},
},
err: ErrNotCountryCode,
},
} {
t.Run(tt.name, func(t *testing.T) {
if err := tt.input.Valid(); !errors.Is(err, tt.err) {
t.Logf("want: %v", tt.err)
t.Logf("got: %v", err)
t.Error("got wrong validation error")
}
})
}
}

View File

@@ -1,71 +0,0 @@
package config
import (
"context"
"errors"
"fmt"
"io"
)
var ErrMissingValue = errors.New("config: missing value")
type Impressum struct {
Footer string `json:"footer" yaml:"footer"`
Page ImpressumPage `json:"page" yaml:"page"`
}
func (i Impressum) Render(_ context.Context, w io.Writer) error {
if _, err := fmt.Fprint(w, i.Footer); err != nil {
return err
}
return nil
}
func (i Impressum) Valid() error {
var errs []error
if len(i.Footer) == 0 {
errs = append(errs, fmt.Errorf("%w: impressum footer must be defined", ErrMissingValue))
}
if err := i.Page.Valid(); err != nil {
errs = append(errs, err)
}
if len(errs) != 0 {
return errors.Join(errs...)
}
return nil
}
type ImpressumPage struct {
Title string `json:"title" yaml:"title"`
Body string `json:"body" yaml:"body"`
}
func (ip ImpressumPage) Render(_ context.Context, w io.Writer) error {
if _, err := fmt.Fprint(w, ip.Body); err != nil {
return err
}
return nil
}
func (ip ImpressumPage) Valid() error {
var errs []error
if len(ip.Title) == 0 {
errs = append(errs, fmt.Errorf("%w: impressum page title must be defined", ErrMissingValue))
}
if len(ip.Body) == 0 {
errs = append(errs, fmt.Errorf("%w: impressum body title must be defined", ErrMissingValue))
}
if len(errs) != 0 {
return errors.Join(errs...)
}
return nil
}

View File

@@ -1,62 +0,0 @@
package config
import (
"bytes"
"errors"
"testing"
)
func TestImpressumValid(t *testing.T) {
for _, cs := range []struct {
name string
inp Impressum
err error
}{
{
name: "basic happy path",
inp: Impressum{
Footer: "<p>Website hosted by Techaro.<p>",
Page: ImpressumPage{
Title: "Techaro Imprint",
Body: "<p>This is an imprint page.</p>",
},
},
err: nil,
},
{
name: "no footer",
inp: Impressum{
Footer: "",
Page: ImpressumPage{
Title: "Techaro Imprint",
Body: "<p>This is an imprint page.</p>",
},
},
err: ErrMissingValue,
},
{
name: "page not valid",
inp: Impressum{
Footer: "test page please ignore",
},
err: ErrMissingValue,
},
} {
t.Run(cs.name, func(t *testing.T) {
if err := cs.inp.Valid(); !errors.Is(err, cs.err) {
t.Logf("want: %v", cs.err)
t.Logf("got: %v", err)
t.Error("validation failed")
}
var buf bytes.Buffer
if err := cs.inp.Render(t.Context(), &buf); err != nil {
t.Errorf("can't render footer: %v", err)
}
if err := cs.inp.Page.Render(t.Context(), &buf); err != nil {
t.Errorf("can't render page: %v", err)
}
})
}
}

View File

@@ -1,51 +0,0 @@
package config
import (
"errors"
"fmt"
"time"
)
var (
ErrInvalidOpenGraphConfig = errors.New("config.OpenGraph: invalid OpenGraph configuration")
ErrOpenGraphTTLDoesNotParse = errors.New("config.OpenGraph: ttl does not parse as a Duration, see https://pkg.go.dev/time#ParseDuration (formatted like 5m -> 5 minutes, 2h -> 2 hours, etc)")
ErrOpenGraphMissingProperty = errors.New("config.OpenGraph: default opengraph tags missing a property")
)
type openGraphFileConfig struct {
Enabled bool `json:"enabled" yaml:"enabled"`
ConsiderHost bool `json:"considerHost" yaml:"enabled"`
TimeToLive string `json:"ttl" yaml:"ttl"`
Override map[string]string `json:"override,omitempty" yaml:"override,omitempty"`
}
type OpenGraph struct {
Enabled bool `json:"enabled" yaml:"enabled"`
ConsiderHost bool `json:"considerHost" yaml:"enabled"`
Override map[string]string `json:"override,omitempty" yaml:"override,omitempty"`
TimeToLive time.Duration `json:"ttl" yaml:"ttl"`
}
func (og *openGraphFileConfig) Valid() error {
var errs []error
if _, err := time.ParseDuration(og.TimeToLive); err != nil {
errs = append(errs, fmt.Errorf("%w: ParseDuration(%q) returned: %w", ErrOpenGraphTTLDoesNotParse, og.TimeToLive, err))
}
if len(og.Override) != 0 {
for _, tag := range []string{
"og:title",
} {
if _, ok := og.Override[tag]; !ok {
errs = append(errs, fmt.Errorf("%w: %s", ErrOpenGraphMissingProperty, tag))
}
}
}
if len(errs) != 0 {
return errors.Join(ErrInvalidOpenGraphConfig, errors.Join(errs...))
}
return nil
}

View File

@@ -1,67 +0,0 @@
package config
import (
"errors"
"testing"
)
func TestOpenGraphFileConfigValid(t *testing.T) {
for _, tt := range []struct {
name string
input *openGraphFileConfig
err error
}{
{
name: "basic happy path",
input: &openGraphFileConfig{
Enabled: true,
ConsiderHost: false,
TimeToLive: "1h",
Override: map[string]string{},
},
err: nil,
},
{
name: "basic happy path with default",
input: &openGraphFileConfig{
Enabled: true,
ConsiderHost: false,
TimeToLive: "1h",
Override: map[string]string{
"og:title": "foobar",
},
},
err: nil,
},
{
name: "invalid time duration",
input: &openGraphFileConfig{
Enabled: true,
ConsiderHost: false,
TimeToLive: "taco",
Override: map[string]string{},
},
err: ErrOpenGraphTTLDoesNotParse,
},
{
name: "missing og:title in defaults",
input: &openGraphFileConfig{
Enabled: true,
ConsiderHost: false,
TimeToLive: "1h",
Override: map[string]string{
"description": "foobar",
},
},
err: ErrOpenGraphMissingProperty,
},
} {
t.Run(tt.name, func(t *testing.T) {
if err := tt.input.Valid(); !errors.Is(err, tt.err) {
t.Logf("wanted error: %v", tt.err)
t.Logf("got error: %v", err)
t.Error("validation failed")
}
})
}
}

View File

@@ -1,11 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
impressum:
page:
title: Test
body: <p>This is a test</p>

View File

@@ -1,10 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
impressum:
footer: "Hi there these are WORDS on the INTERNET."
page: {}

View File

@@ -1,12 +0,0 @@
bots:
- name: everything
user_agent_regex: .*
action: DENY
openGraph:
enabled: true
considerHost: false
ttl: taco
default:
"og:title": "Xe's magic land of fun"
"og:description": "We're no strangers to love, you know the rules and so do I"

View File

@@ -1,11 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
thresholds:
- name: extreme-suspicion
expression: "true"
action: WEIGH

View File

@@ -1,15 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
thresholds:
- name: extreme-suspicion
expression: "true"
action: WEIGH
challenge:
algorithm: fast
difficulty: 4
report_as: 4

View File

@@ -1 +0,0 @@
}

View File

@@ -1 +0,0 @@
}

View File

@@ -1,10 +0,0 @@
bots:
- name: simple
action: CHALLENGE
user_agent_regex: Mozilla
impressum:
footer: "Hi these are WORDS on the INTERNET."
page:
title: Test
body: <p>This is a test</p>

View File

@@ -1,8 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
thresholds: []

View File

@@ -1,12 +0,0 @@
bots:
- name: everything
user_agent_regex: .*
action: DENY
openGraph:
enabled: true
considerHost: false
ttl: 1h
default:
"og:title": "Xe's magic land of fun"
"og:description": "We're no strangers to love, you know the rules and so do I"

View File

@@ -1,38 +0,0 @@
bots:
- name: simple-weight-adjust
action: WEIGH
user_agent_regex: Mozilla
weight:
adjust: 5
thresholds:
- name: minimal-suspicion
expression: weight < 0
action: ALLOW
- name: mild-suspicion
expression:
all:
- weight >= 0
- weight < 10
action: CHALLENGE
challenge:
algorithm: metarefresh
difficulty: 1
report_as: 1
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 2
report_as: 2
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 4
report_as: 4

View File

@@ -1,80 +0,0 @@
package config
import (
"errors"
"fmt"
"github.com/TecharoHQ/anubis"
)
var (
ErrNoThresholdRulesDefined = errors.New("config: no thresholds defined")
ErrThresholdMustHaveName = errors.New("config.Threshold: must set name")
ErrThresholdMustHaveExpression = errors.New("config.Threshold: must set expression")
ErrThresholdChallengeMustHaveChallenge = errors.New("config.Threshold: a threshold with the CHALLENGE action must have challenge set")
ErrThresholdCannotHaveWeighAction = errors.New("config.Threshold: a threshold cannot have the WEIGH action")
DefaultThresholds = []Threshold{
{
Name: "legacy-anubis-behaviour",
Expression: &ExpressionOrList{
Expression: "weight > 0",
},
Action: RuleChallenge,
Challenge: &ChallengeRules{
Algorithm: "fast",
Difficulty: anubis.DefaultDifficulty,
ReportAs: anubis.DefaultDifficulty,
},
},
}
)
type Threshold struct {
Name string `json:"name" yaml:"name"`
Expression *ExpressionOrList `json:"expression" yaml:"expression"`
Action Rule `json:"action" yaml:"action"`
Challenge *ChallengeRules `json:"challenge" yaml:"challenge"`
}
func (t Threshold) Valid() error {
var errs []error
if len(t.Name) == 0 {
errs = append(errs, ErrThresholdMustHaveName)
}
if t.Expression == nil {
errs = append(errs, ErrThresholdMustHaveExpression)
}
if t.Expression != nil {
if err := t.Expression.Valid(); err != nil {
errs = append(errs, err)
}
}
if err := t.Action.Valid(); err != nil {
errs = append(errs, err)
}
if t.Action == RuleWeigh {
errs = append(errs, ErrThresholdCannotHaveWeighAction)
}
if t.Action == RuleChallenge && t.Challenge == nil {
errs = append(errs, ErrThresholdChallengeMustHaveChallenge)
}
if t.Challenge != nil {
if err := t.Challenge.Valid(); err != nil {
errs = append(errs, err)
}
}
if len(errs) != 0 {
return fmt.Errorf("config: threshold entry for %q is not valid:\n%w", t.Name, errors.Join(errs...))
}
return nil
}

View File

@@ -1,111 +0,0 @@
package config
import (
"errors"
"fmt"
"os"
"path/filepath"
"testing"
)
func TestThresholdValid(t *testing.T) {
for _, tt := range []struct {
name string
input *Threshold
err error
}{
{
name: "basic allow",
input: &Threshold{
Name: "basic-allow",
Expression: &ExpressionOrList{Expression: "true"},
Action: RuleAllow,
},
err: nil,
},
{
name: "basic challenge",
input: &Threshold{
Name: "basic-challenge",
Expression: &ExpressionOrList{Expression: "true"},
Action: RuleChallenge,
Challenge: &ChallengeRules{
Algorithm: "fast",
Difficulty: 1,
ReportAs: 1,
},
},
err: nil,
},
{
name: "no name",
input: &Threshold{},
err: ErrThresholdMustHaveName,
},
{
name: "no expression",
input: &Threshold{},
err: ErrThresholdMustHaveName,
},
{
name: "invalid expression",
input: &Threshold{
Expression: &ExpressionOrList{},
},
err: ErrExpressionEmpty,
},
{
name: "invalid action",
input: &Threshold{},
err: ErrUnknownAction,
},
{
name: "challenge action but no challenge",
input: &Threshold{
Action: RuleChallenge,
},
err: ErrThresholdChallengeMustHaveChallenge,
},
{
name: "challenge invalid",
input: &Threshold{
Action: RuleChallenge,
Challenge: &ChallengeRules{Difficulty: 0, ReportAs: 0},
},
err: ErrChallengeDifficultyTooLow,
},
} {
t.Run(tt.name, func(t *testing.T) {
if err := tt.input.Valid(); !errors.Is(err, tt.err) {
t.Errorf("threshold is invalid: %v", err)
}
})
}
}
func TestDefaultThresholdsValid(t *testing.T) {
for i, th := range DefaultThresholds {
t.Run(fmt.Sprintf("%d %s", i, th.Name), func(t *testing.T) {
if err := th.Valid(); err != nil {
t.Errorf("threshold invalid: %v", err)
}
})
}
}
func TestLoadActuallyLoadsThresholds(t *testing.T) {
fin, err := os.Open(filepath.Join(".", "testdata", "good", "thresholds.yaml"))
if err != nil {
t.Fatal(err)
}
defer fin.Close()
c, err := Load(fin, fin.Name())
if err != nil {
t.Fatal(err)
}
if len(c.Thresholds) != 4 {
t.Errorf("wanted 4 thresholds, got %d thresholds", len(c.Thresholds))
}
}

View File

@@ -9,32 +9,12 @@ import (
"github.com/google/cel-go/ext"
)
// BotEnvironment creates a new CEL environment, this is the set of
// NewEnvironment creates a new CEL environment, this is the set of
// variables and functions that are passed into the CEL scope so that
// Anubis can fail loudly and early when something is invalid instead
// of blowing up at runtime.
func BotEnvironment() (*cel.Env, error) {
return New(
// Variables exposed to CEL programs:
cel.Variable("remoteAddress", cel.StringType),
cel.Variable("host", cel.StringType),
cel.Variable("method", cel.StringType),
cel.Variable("userAgent", cel.StringType),
cel.Variable("path", cel.StringType),
cel.Variable("query", cel.MapType(cel.StringType, cel.StringType)),
cel.Variable("headers", cel.MapType(cel.StringType, cel.StringType)),
)
}
// NewThreshold creates a new CEL environment for threshold checking.
func ThresholdEnvironment() (*cel.Env, error) {
return New(
cel.Variable("weight", cel.IntType),
)
}
func New(opts ...cel.EnvOption) (*cel.Env, error) {
args := []cel.EnvOption{
func NewEnvironment() (*cel.Env, error) {
return cel.NewEnv(
ext.Strings(
ext.StringsLocale("en_US"),
ext.StringsValidateFormatCalls(true),
@@ -43,7 +23,16 @@ func New(opts ...cel.EnvOption) (*cel.Env, error) {
// default all timestamps to UTC
cel.DefaultUTCTimeZone(true),
// Functions exposed to all CEL programs:
// Variables exposed to CEL programs:
cel.Variable("remoteAddress", cel.StringType),
cel.Variable("host", cel.StringType),
cel.Variable("method", cel.StringType),
cel.Variable("userAgent", cel.StringType),
cel.Variable("path", cel.StringType),
cel.Variable("query", cel.MapType(cel.StringType, cel.StringType)),
cel.Variable("headers", cel.MapType(cel.StringType, cel.StringType)),
// Functions exposed to CEL programs:
cel.Function("randInt",
cel.Overload("randInt_int",
[]*cel.Type{cel.IntType},
@@ -58,25 +47,12 @@ func New(opts ...cel.EnvOption) (*cel.Env, error) {
}),
),
),
}
args = append(args, opts...)
return cel.NewEnv(args...)
)
}
// Compile takes CEL environment and syntax tree then emits an optimized
// Program for execution.
func Compile(env *cel.Env, src string) (cel.Program, error) {
intermediate, iss := env.Compile(src)
if iss != nil {
return nil, iss.Err()
}
ast, iss := env.Check(intermediate)
if iss != nil {
return nil, iss.Err()
}
func Compile(env *cel.Env, ast *cel.Ast) (cel.Program, error) {
return env.Program(
ast,
cel.EvalOptions(

View File

@@ -0,0 +1,104 @@
package expressions
import (
"errors"
"fmt"
"strings"
"github.com/google/cel-go/cel"
)
// JoinOperator is a type wrapper for and/or operators.
//
// This is a separate type so that validation can be done at the type level.
type JoinOperator string
// Possible values for JoinOperator
const (
JoinAnd JoinOperator = "&&"
JoinOr JoinOperator = "||"
)
// Valid ensures that JoinOperator is semantically valid.
func (jo JoinOperator) Valid() error {
switch jo {
case JoinAnd, JoinOr:
return nil
default:
return ErrWrongJoinOperator
}
}
var (
ErrWrongJoinOperator = errors.New("expressions: invalid join operator")
ErrNoExpressions = errors.New("expressions: cannot join zero expressions")
ErrCantCompile = errors.New("expressions: can't compile one expression")
)
// JoinClauses joins a list of compiled clauses into one big if statement.
//
// Imagine the following two clauses:
//
// ball.color == "red"
// ball.shape == "round"
//
// JoinClauses would emit one "joined" clause such as:
//
// ( ball.color == "red" ) && ( ball.shape == "round" )
func JoinClauses(env *cel.Env, operator JoinOperator, clauses ...*cel.Ast) (*cel.Ast, error) {
if err := operator.Valid(); err != nil {
return nil, fmt.Errorf("%w: wanted && or ||, got: %q", err, operator)
}
switch len(clauses) {
case 0:
return nil, ErrNoExpressions
case 1:
return clauses[0], nil
}
var exprs []string
var errs []error
for _, clause := range clauses {
clauseStr, err := cel.AstToString(clause)
if err != nil {
errs = append(errs, err)
continue
}
exprs = append(exprs, "( "+clauseStr+" )")
}
if len(errs) != 0 {
return nil, fmt.Errorf("errors while decompiling statements: %w", errors.Join(errs...))
}
statement := strings.Join(exprs, " "+string(operator)+" ")
result, iss := env.Compile(statement)
if iss != nil {
return nil, iss.Err()
}
return result, nil
}
func Join(env *cel.Env, operator JoinOperator, clauses ...string) (*cel.Ast, error) {
var statements []*cel.Ast
var errs []error
for _, clause := range clauses {
stmt, iss := env.Compile(clause)
if iss != nil && iss.Err() != nil {
errs = append(errs, fmt.Errorf("%w: %q gave: %w", ErrCantCompile, clause, iss.Err()))
continue
}
statements = append(statements, stmt)
}
if len(errs) != 0 {
return nil, fmt.Errorf("errors while joining clauses: %w", errors.Join(errs...))
}
return JoinClauses(env, operator, statements...)
}

View File

@@ -0,0 +1,90 @@
package expressions
import (
"errors"
"testing"
"github.com/google/cel-go/cel"
)
func TestJoin(t *testing.T) {
env, err := NewEnvironment()
if err != nil {
t.Fatal(err)
}
for _, tt := range []struct {
err error
name string
op JoinOperator
resultStr string
clauses []string
}{
{
name: "no-clauses",
clauses: []string{},
op: JoinAnd,
err: ErrNoExpressions,
},
{
name: "one-clause-identity",
clauses: []string{`remoteAddress == "8.8.8.8"`},
op: JoinAnd,
err: nil,
resultStr: `remoteAddress == "8.8.8.8"`,
},
{
name: "multi-clause-and",
clauses: []string{
`remoteAddress == "8.8.8.8"`,
`host == "anubis.techaro.lol"`,
},
op: JoinAnd,
err: nil,
resultStr: `remoteAddress == "8.8.8.8" && host == "anubis.techaro.lol"`,
},
{
name: "multi-clause-or",
clauses: []string{
`remoteAddress == "8.8.8.8"`,
`host == "anubis.techaro.lol"`,
},
op: JoinOr,
err: nil,
resultStr: `remoteAddress == "8.8.8.8" || host == "anubis.techaro.lol"`,
},
{
name: "git-user-agent",
clauses: []string{
`userAgent.startsWith("git/") || userAgent.contains("libgit")`,
`"Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"`,
},
op: JoinAnd,
err: nil,
resultStr: `(userAgent.startsWith("git/") || userAgent.contains("libgit")) && "Git-Protocol" in headers &&
headers["Git-Protocol"] == "version=2"`,
},
} {
t.Run(tt.name, func(t *testing.T) {
result, err := Join(env, tt.op, tt.clauses...)
if !errors.Is(err, tt.err) {
t.Errorf("wanted error %v but got: %v", tt.err, err)
}
if tt.err != nil {
return
}
program, err := cel.AstToString(result)
if err != nil {
t.Fatalf("can't decompile program: %v", err)
}
if tt.resultStr != program {
t.Logf("wanted: %s", tt.resultStr)
t.Logf("got: %s", program)
t.Error("program did not compile as expected")
}
})
}
}

View File

@@ -6,7 +6,6 @@ import (
"fmt"
"io"
"log/slog"
"sync/atomic"
"github.com/TecharoHQ/anubis/internal/thoth"
"github.com/TecharoHQ/anubis/lib/policy/checker"
@@ -22,17 +21,13 @@ var (
}, []string{"rule", "action"})
ErrChallengeRuleHasWrongAlgorithm = errors.New("config.Bot.ChallengeRules: algorithm is invalid")
warnedAboutThresholds = &atomic.Bool{}
)
type ParsedConfig struct {
orig *config.Config
Bots []Bot
Thresholds []*Threshold
DNSBL bool
Impressum *config.Impressum
OpenGraph config.OpenGraph
DefaultDifficulty int
StatusCodes config.StatusCodes
}
@@ -40,7 +35,6 @@ type ParsedConfig struct {
func NewParsedConfig(orig *config.Config) *ParsedConfig {
return &ParsedConfig{
orig: orig,
OpenGraph: orig.OpenGraph,
StatusCodes: orig.StatusCodes,
}
}
@@ -151,33 +145,11 @@ func ParseConfig(ctx context.Context, fin io.Reader, fname string, defaultDiffic
parsedBot.Weight = b.Weight
}
result.Impressum = c.Impressum
parsedBot.Rules = cl
result.Bots = append(result.Bots, parsedBot)
}
for _, t := range c.Thresholds {
if t.Name == "legacy-anubis-behaviour" && t.Expression.String() == "true" {
if !warnedAboutThresholds.Load() {
slog.Warn("configuration file does not contain thresholds, see docs for details on how to upgrade", "fname", fname, "docs_url", "https://anubis.techaro.lol/docs/admin/configuration/thresholds/")
warnedAboutThresholds.Store(true)
}
t.Challenge.Difficulty = defaultDifficulty
t.Challenge.ReportAs = defaultDifficulty
}
threshold, err := ParsedThresholdFromConfig(t)
if err != nil {
validationErrs = append(validationErrs, fmt.Errorf("can't compile threshold config for %s: %w", t.Name, err))
continue
}
result.Thresholds = append(result.Thresholds, threshold)
}
if len(validationErrs) > 0 {
return nil, fmt.Errorf("errors validating policy config JSON %s: %w", fname, errors.Join(validationErrs...))
}

View File

@@ -1,47 +0,0 @@
package policy
import (
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/TecharoHQ/anubis/lib/policy/expressions"
"github.com/google/cel-go/cel"
)
type Threshold struct {
config.Threshold
Program cel.Program
}
func ParsedThresholdFromConfig(t config.Threshold) (*Threshold, error) {
result := &Threshold{
Threshold: t,
}
env, err := expressions.ThresholdEnvironment()
if err != nil {
return nil, err
}
program, err := expressions.Compile(env, t.Expression.String())
if err != nil {
return nil, err
}
result.Program = program
return result, nil
}
type ThresholdRequest struct {
Weight int
}
func (tr *ThresholdRequest) Parent() cel.Activation { return nil }
func (tr *ThresholdRequest) ResolveName(name string) (any, bool) {
switch name {
case "weight":
return tr.Weight, true
default:
return nil, false
}
}

View File

@@ -1,12 +1,12 @@
bots:
- name: deny
user_agent_regex: DENY
action: DENY
- name: deny
user_agent_regex: DENY
action: DENY
- name: challenge
user_agent_regex: CHALLENGE
action: CHALLENGE
- name: challenge
user_agent_regex: CHALLENGE
action: CHALLENGE
status_codes:
CHALLENGE: 401
DENY: 403
DENY: 403

View File

@@ -1,38 +0,0 @@
bots:
- import: (data)/bots/_deny-pathological.yaml
- import: (data)/bots/aggressive-brazilian-scrapers.yaml
- import: (data)/meta/ai-block-aggressive.yaml
- import: (data)/crawlers/_allow-good.yaml
- import: (data)/clients/x-firefox-ai.yaml
- import: (data)/common/keep-internet-working.yaml
- name: countries-with-aggressive-scrapers
action: WEIGH
geoip:
countries:
- BR
- CN
weight:
adjust: 10
- name: aggressive-asns-without-functional-abuse-contact
action: WEIGH
asns:
match:
- 13335 # Cloudflare
- 136907 # Huawei Cloud
- 45102 # Alibaba Cloud
weight:
adjust: 10
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: WEIGH
weight:
adjust: 10
dnsbl: false
status_codes:
CHALLENGE: 200
DENY: 200
thresholds: []

4
package-lock.json generated
View File

@@ -1,12 +1,12 @@
{
"name": "@techaro/anubis",
"version": "1.20.0-pre2",
"version": "1.19.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@techaro/anubis",
"version": "1.20.0-pre2",
"version": "1.19.1",
"license": "ISC",
"devDependencies": {
"cssnano": "^7.0.7",

View File

@@ -1,6 +1,6 @@
{
"name": "@techaro/anubis",
"version": "1.20.0-pre2",
"version": "1.19.1",
"description": "",
"main": "index.js",
"scripts": {

View File

@@ -6,12 +6,12 @@ import (
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func Base(title string, body templ.Component, impressum *config.Impressum) templ.Component {
return base(title, body, impressum, nil, nil)
func Base(title string, body templ.Component) templ.Component {
return base(title, body, nil, nil)
}
func BaseWithChallengeAndOGTags(title string, body templ.Component, impressum *config.Impressum, challenge string, rules *config.ChallengeRules, ogTags map[string]string) (templ.Component, error) {
return base(title, body, impressum, struct {
func BaseWithChallengeAndOGTags(title string, body templ.Component, challenge string, rules *config.ChallengeRules, ogTags map[string]string) (templ.Component, error) {
return base(title, body, struct {
Rules *config.ChallengeRules `json:"rules"`
Challenge string `json:"challenge"`
}{

View File

@@ -1,13 +1,11 @@
package web
import (
"fmt"
"github.com/TecharoHQ/anubis"
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/TecharoHQ/anubis/xess"
)
templ base(title string, body templ.Component, impressum *config.Impressum, challenge any, ogTags map[string]string) {
templ base(title string, body templ.Component, challenge any, ogTags map[string]string) {
<!DOCTYPE html>
<html lang="en">
<head>
@@ -38,16 +36,16 @@ templ base(title string, body templ.Component, impressum *config.Impressum, chal
}
#progress {
display: none;
width: 90%;
width: min(20rem, 90%);
height: 2rem;
border-radius: 1rem;
overflow: hidden;
margin: 1rem 0 2rem;
outline-offset: 2px;
outline: #b16286 solid 4px;
}
display: none;
width: 90%;
width: min(20rem, 90%);
height: 2rem;
border-radius: 1rem;
overflow: hidden;
margin: 1rem 0 2rem;
outline-offset: 2px;
outline: #b16286 solid 4px;
}
.bar-inner {
background-color: #b16286;
@@ -55,7 +53,7 @@ templ base(title string, body templ.Component, impressum *config.Impressum, chal
width: 0;
transition: width 0.25s ease-in;
}
</style>
</style>
@templ.JSONScript("anubis_version", anubis.Version)
if challenge != nil {
@templ.JSONScript("anubis_challenge", challenge)
@@ -76,10 +74,6 @@ templ base(title string, body templ.Component, impressum *config.Impressum, chal
>Techaro</a>. Made with ❤️ in 🇨🇦.
</p>
<p>Mascot design by <a href="https://bsky.app/profile/celphase.bsky.social">CELPHASE</a>.</p>
if impressum != nil {
<p>@templ.Raw(impressum.Footer)
-- <a href={ templ.SafeURL(fmt.Sprintf("%simprint", anubis.APIPrefix)) }>Imprint</a></p>
}
</center>
</footer>
</main>

239
web/index_templ.go generated
View File

@@ -9,13 +9,11 @@ import "github.com/a-h/templ"
import templruntime "github.com/a-h/templ/runtime"
import (
"fmt"
"github.com/TecharoHQ/anubis"
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/TecharoHQ/anubis/xess"
)
func base(title string, body templ.Component, impressum *config.Impressum, challenge any, ogTags map[string]string) templ.Component {
func base(title string, body templ.Component, challenge any, ogTags map[string]string) templ.Component {
return templruntime.GeneratedTemplate(func(templ_7745c5c3_Input templruntime.GeneratedComponentInput) (templ_7745c5c3_Err error) {
templ_7745c5c3_W, ctx := templ_7745c5c3_Input.Writer, templ_7745c5c3_Input.Context
if templ_7745c5c3_CtxErr := ctx.Err(); templ_7745c5c3_CtxErr != nil {
@@ -43,7 +41,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
var templ_7745c5c3_Var2 string
templ_7745c5c3_Var2, templ_7745c5c3_Err = templ.JoinStringErrs(title)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 14, Col: 17}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 12, Col: 17}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var2))
if templ_7745c5c3_Err != nil {
@@ -56,7 +54,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
var templ_7745c5c3_Var3 string
templ_7745c5c3_Var3, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + xess.URL)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 15, Col: 61}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 13, Col: 61}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var3))
if templ_7745c5c3_Err != nil {
@@ -74,7 +72,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
var templ_7745c5c3_Var4 string
templ_7745c5c3_Var4, templ_7745c5c3_Err = templ.JoinStringErrs(key)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 19, Col: 24}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 17, Col: 24}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var4))
if templ_7745c5c3_Err != nil {
@@ -87,7 +85,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
var templ_7745c5c3_Var5 string
templ_7745c5c3_Var5, templ_7745c5c3_Err = templ.JoinStringErrs(value)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 19, Col: 42}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 17, Col: 42}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var5))
if templ_7745c5c3_Err != nil {
@@ -98,7 +96,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
return templ_7745c5c3_Err
}
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 7, "<style>\n body,\n html {\n height: 100%;\n display: flex;\n justify-content: center;\n align-items: center;\n margin-left: auto;\n margin-right: auto;\n }\n\n .centered-div {\n text-align: center;\n }\n\n #status {\n font-variant-numeric: tabular-nums;\n }\n\n #progress {\n display: none;\n width: 90%;\n width: min(20rem, 90%);\n height: 2rem;\n border-radius: 1rem;\n overflow: hidden;\n margin: 1rem 0 2rem;\n\t\t\t\t\toutline-offset: 2px;\n\t\t\t\t\toutline: #b16286 solid 4px;\n\t\t\t\t}\n\n .bar-inner {\n background-color: #b16286;\n height: 100%;\n width: 0;\n transition: width 0.25s ease-in;\n }\n \t</style>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 7, "<style>\n body,\n html {\n height: 100%;\n display: flex;\n justify-content: center;\n align-items: center;\n margin-left: auto;\n margin-right: auto;\n }\n\n .centered-div {\n text-align: center;\n }\n\n #status {\n font-variant-numeric: tabular-nums;\n }\n\n #progress {\n display: none;\n width: 90%;\n width: min(20rem, 90%);\n height: 2rem;\n border-radius: 1rem;\n overflow: hidden;\n margin: 1rem 0 2rem;\n\t\t\toutline-offset: 2px;\n\t\t\toutline: #b16286 solid 4px;\n\t\t}\n\n .bar-inner {\n background-color: #b16286;\n height: 100%;\n width: 0;\n transition: width 0.25s ease-in;\n }\n </style>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
@@ -123,7 +121,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
var templ_7745c5c3_Var6 string
templ_7745c5c3_Var6, templ_7745c5c3_Err = templ.JoinStringErrs(title)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 68, Col: 49}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 66, Col: 49}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var6))
if templ_7745c5c3_Err != nil {
@@ -137,38 +135,7 @@ func base(title string, body templ.Component, impressum *config.Impressum, chall
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 10, "<footer><center><p>Protected by <a href=\"https://github.com/TecharoHQ/anubis\">Anubis</a> from <a href=\"https://techaro.lol\">Techaro</a>. Made with ❤️ in 🇨🇦.</p><p>Mascot design by <a href=\"https://bsky.app/profile/celphase.bsky.social\">CELPHASE</a>.</p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
if impressum != nil {
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 11, "<p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templ.Raw(impressum.Footer).Render(ctx, templ_7745c5c3_Buffer)
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 12, "-- <a href=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var7 templ.SafeURL
templ_7745c5c3_Var7, templ_7745c5c3_Err = templ.JoinURLErrs(templ.SafeURL(fmt.Sprintf("%simprint", anubis.APIPrefix)))
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 81, Col: 70}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var7))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 13, "\">Imprint</a></p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 14, "</center></footer></main></body></html>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 10, "<footer><center><p>Protected by <a href=\"https://github.com/TecharoHQ/anubis\">Anubis</a> from <a href=\"https://techaro.lol\">Techaro</a>. Made with ❤️ in 🇨🇦.</p><p>Mascot design by <a href=\"https://bsky.app/profile/celphase.bsky.social\">CELPHASE</a>.</p></center></footer></main></body></html>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
@@ -192,64 +159,64 @@ func index() templ.Component {
}()
}
ctx = templ.InitializeContext(ctx)
templ_7745c5c3_Var8 := templ.GetChildren(ctx)
if templ_7745c5c3_Var8 == nil {
templ_7745c5c3_Var8 = templ.NopComponent
templ_7745c5c3_Var7 := templ.GetChildren(ctx)
if templ_7745c5c3_Var7 == nil {
templ_7745c5c3_Var7 = templ.NopComponent
}
ctx = templ.ClearChildren(ctx)
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "<div class=\"centered-div\"><img id=\"image\" style=\"width:100%;max-width:256px;\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 11, "<div class=\"centered-div\"><img id=\"image\" style=\"width:100%;max-width:256px;\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var8 string
templ_7745c5c3_Var8, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/pensive.webp?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 86, Col: 165}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var8))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 12, "\"> <img style=\"display:none;\" style=\"width:100%;max-width:256px;\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var9 string
templ_7745c5c3_Var9, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/pensive.webp?cacheBuster=" + anubis.Version)
templ_7745c5c3_Var9, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/happy.webp?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 92, Col: 165}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 87, Col: 174}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var9))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "\"> <img style=\"display:none;\" style=\"width:100%;max-width:256px;\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 13, "\"><p id=\"status\">Loading...</p><script async type=\"module\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var10 string
templ_7745c5c3_Var10, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/happy.webp?cacheBuster=" + anubis.Version)
templ_7745c5c3_Var10, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/js/main.mjs?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 93, Col: 174}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 89, Col: 136}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var10))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 17, "\"><p id=\"status\">Loading...</p><script async type=\"module\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 14, "\"></script><div id=\"progress\" role=\"progressbar\" aria-labelledby=\"status\"><div class=\"bar-inner\"></div></div><details><summary>Why am I seeing this?</summary><p>You are seeing this because the administrator of this website has set up <a href=\"https://github.com/TecharoHQ/anubis\">Anubis</a> to protect the server against the scourge of <a href=\"https://thelibre.news/foss-infrastructure-is-under-attack-by-ai-companies/\">AI companies aggressively scraping websites</a>. This can and does cause downtime for the websites, which makes their resources inaccessible for everyone.</p><p>Anubis is a compromise. Anubis uses a <a href=\"https://anubis.techaro.lol/docs/design/why-proof-of-work\">Proof-of-Work</a> scheme in the vein of <a href=\"https://en.wikipedia.org/wiki/Hashcash\">Hashcash</a>, a proposed proof-of-work scheme for reducing email spam. The idea is that at individual scales the additional load is ignorable, but at mass scraper levels it adds up and makes scraping much more expensive.</p><p>Ultimately, this is a hack whose real purpose is to give a \"good enough\" placeholder solution so that more time can be spent on fingerprinting and identifying headless browsers (EG: via how they do font rendering) so that the challenge proof of work page doesn't need to be presented to users that are much more likely to be legitimate.</p><p>Please note that Anubis requires the use of modern JavaScript features that plugins like <a href=\"https://jshelter.org/\">JShelter</a> will disable. Please disable JShelter or other such plugins for this domain.</p><p>This website is running Anubis version <code>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var11 string
templ_7745c5c3_Var11, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/js/main.mjs?cacheBuster=" + anubis.Version)
templ_7745c5c3_Var11, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 95, Col: 136}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 125, Col: 67}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var11))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 18, "\"></script><div id=\"progress\" role=\"progressbar\" aria-labelledby=\"status\"><div class=\"bar-inner\"></div></div><details><summary>Why am I seeing this?</summary><p>You are seeing this because the administrator of this website has set up <a href=\"https://github.com/TecharoHQ/anubis\">Anubis</a> to protect the server against the scourge of <a href=\"https://thelibre.news/foss-infrastructure-is-under-attack-by-ai-companies/\">AI companies aggressively scraping websites</a>. This can and does cause downtime for the websites, which makes their resources inaccessible for everyone.</p><p>Anubis is a compromise. Anubis uses a <a href=\"https://anubis.techaro.lol/docs/design/why-proof-of-work\">Proof-of-Work</a> scheme in the vein of <a href=\"https://en.wikipedia.org/wiki/Hashcash\">Hashcash</a>, a proposed proof-of-work scheme for reducing email spam. The idea is that at individual scales the additional load is ignorable, but at mass scraper levels it adds up and makes scraping much more expensive.</p><p>Ultimately, this is a hack whose real purpose is to give a \"good enough\" placeholder solution so that more time can be spent on fingerprinting and identifying headless browsers (EG: via how they do font rendering) so that the challenge proof of work page doesn't need to be presented to users that are much more likely to be legitimate.</p><p>Please note that Anubis requires the use of modern JavaScript features that plugins like <a href=\"https://jshelter.org/\">JShelter</a> will disable. Please disable JShelter or other such plugins for this domain.</p><p>This website is running Anubis version <code>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var12 string
templ_7745c5c3_Var12, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 131, Col: 67}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var12))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 19, "</code>.</p></details><noscript><p>Sadly, you must enable JavaScript to get past this challenge. This is required because AI companies have changed the social contract around how website hosting works. A no-JS solution is a work-in-progress.</p></noscript><div id=\"testarea\"></div></div>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "</code>.</p></details><noscript><p>Sadly, you must enable JavaScript to get past this challenge. This is required because AI companies have changed the social contract around how website hosting works. A no-JS solution is a work-in-progress.</p></noscript><div id=\"testarea\"></div></div>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
@@ -273,79 +240,79 @@ func errorPage(message string, mail string) templ.Component {
}()
}
ctx = templ.InitializeContext(ctx)
templ_7745c5c3_Var13 := templ.GetChildren(ctx)
if templ_7745c5c3_Var13 == nil {
templ_7745c5c3_Var13 = templ.NopComponent
templ_7745c5c3_Var12 := templ.GetChildren(ctx)
if templ_7745c5c3_Var12 == nil {
templ_7745c5c3_Var12 = templ.NopComponent
}
ctx = templ.ClearChildren(ctx)
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 20, "<div class=\"centered-div\"><img id=\"image\" alt=\"Sad Anubis\" style=\"width:100%;max-width:256px;\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "<div class=\"centered-div\"><img id=\"image\" alt=\"Sad Anubis\" style=\"width:100%;max-width:256px;\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var13 string
templ_7745c5c3_Var13, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/reject.webp?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 140, Col: 181}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var13))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 17, "\"><p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var14 string
templ_7745c5c3_Var14, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/reject.webp?cacheBuster=" + anubis.Version)
templ_7745c5c3_Var14, templ_7745c5c3_Err = templ.JoinStringErrs(message)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 146, Col: 181}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 141, Col: 14}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var14))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 21, "\"><p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var15 string
templ_7745c5c3_Var15, templ_7745c5c3_Err = templ.JoinStringErrs(message)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 147, Col: 14}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var15))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 22, ".</p><button onClick=\"window.location.reload();\">Try again</button> ")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 18, ".</p><button onClick=\"window.location.reload();\">Try again</button> ")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
if mail != "" {
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 23, "<p><a href=\"/\">Go home</a> or if you believe you should not be blocked, please contact the webmaster at <a href=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 19, "<p><a href=\"/\">Go home</a> or if you believe you should not be blocked, please contact the webmaster at <a href=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var16 templ.SafeURL
templ_7745c5c3_Var16, templ_7745c5c3_Err = templ.JoinURLErrs("mailto:" + templ.SafeURL(mail))
var templ_7745c5c3_Var15 templ.SafeURL
templ_7745c5c3_Var15, templ_7745c5c3_Err = templ.JoinURLErrs("mailto:" + templ.SafeURL(mail))
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 152, Col: 45}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 146, Col: 45}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var15))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 20, "\">")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var16 string
templ_7745c5c3_Var16, templ_7745c5c3_Err = templ.JoinStringErrs(mail)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 147, Col: 11}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var16))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 24, "\">")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var17 string
templ_7745c5c3_Var17, templ_7745c5c3_Err = templ.JoinStringErrs(mail)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 153, Col: 11}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var17))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 25, "</a></p>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 21, "</a></p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
} else {
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 26, "<p><a href=\"/\">Go home</a></p>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 22, "<p><a href=\"/\">Go home</a></p>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 27, "</div>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 23, "</div>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
@@ -369,26 +336,26 @@ func StaticHappy() templ.Component {
}()
}
ctx = templ.InitializeContext(ctx)
templ_7745c5c3_Var18 := templ.GetChildren(ctx)
if templ_7745c5c3_Var18 == nil {
templ_7745c5c3_Var18 = templ.NopComponent
templ_7745c5c3_Var17 := templ.GetChildren(ctx)
if templ_7745c5c3_Var17 == nil {
templ_7745c5c3_Var17 = templ.NopComponent
}
ctx = templ.ClearChildren(ctx)
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 28, "<div class=\"centered-div\"><img style=\"display:none;\" style=\"width:100%;max-width:256px;\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 24, "<div class=\"centered-div\"><img style=\"display:none;\" style=\"width:100%;max-width:256px;\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var19 string
templ_7745c5c3_Var19, templ_7745c5c3_Err = templ.JoinStringErrs("/.within.website/x/cmd/anubis/static/img/happy.webp?cacheBuster=" +
var templ_7745c5c3_Var18 string
templ_7745c5c3_Var18, templ_7745c5c3_Err = templ.JoinStringErrs("/.within.website/x/cmd/anubis/static/img/happy.webp?cacheBuster=" +
anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 168, Col: 18}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 162, Col: 18}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var19))
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var18))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 29, "\"><p>This is just a check endpoint for your reverse proxy to use.</p></div>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 25, "\"><p>This is just a check endpoint for your reverse proxy to use.</p></div>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
@@ -412,38 +379,38 @@ func bench() templ.Component {
}()
}
ctx = templ.InitializeContext(ctx)
templ_7745c5c3_Var20 := templ.GetChildren(ctx)
if templ_7745c5c3_Var20 == nil {
templ_7745c5c3_Var20 = templ.NopComponent
templ_7745c5c3_Var19 := templ.GetChildren(ctx)
if templ_7745c5c3_Var19 == nil {
templ_7745c5c3_Var19 = templ.NopComponent
}
ctx = templ.ClearChildren(ctx)
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 30, "<div style=\"height:20rem;display:flex\"><table style=\"margin-top:1rem;display:grid;grid-template:auto 1fr/auto auto;gap:0 0.5rem\"><thead style=\"border-bottom:1px solid black;padding:0.25rem 0;display:grid;grid-template:1fr/subgrid;grid-column:1/-1\"><tr id=\"table-header\" style=\"display:contents\"><th style=\"width:4.5rem\">Time</th><th style=\"width:4rem\">Iters</th></tr><tr id=\"table-header-compare\" style=\"display:none\"><th style=\"width:4.5rem\">Time A</th><th style=\"width:4rem\">Iters A</th><th style=\"width:4.5rem\">Time B</th><th style=\"width:4rem\">Iters B</th></tr></thead> <tbody id=\"results\" style=\"padding-top:0.25rem;display:grid;grid-template-columns:subgrid;grid-auto-rows:min-content;grid-column:1/-1;row-gap:0.25rem;overflow-y:auto;font-variant-numeric:tabular-nums\"></tbody></table><div class=\"centered-div\"><img id=\"image\" style=\"width:100%;max-width:256px;\" src=\"")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 26, "<div style=\"height:20rem;display:flex\"><table style=\"margin-top:1rem;display:grid;grid-template:auto 1fr/auto auto;gap:0 0.5rem\"><thead style=\"border-bottom:1px solid black;padding:0.25rem 0;display:grid;grid-template:1fr/subgrid;grid-column:1/-1\"><tr id=\"table-header\" style=\"display:contents\"><th style=\"width:4.5rem\">Time</th><th style=\"width:4rem\">Iters</th></tr><tr id=\"table-header-compare\" style=\"display:none\"><th style=\"width:4.5rem\">Time A</th><th style=\"width:4rem\">Iters A</th><th style=\"width:4.5rem\">Time B</th><th style=\"width:4rem\">Iters B</th></tr></thead> <tbody id=\"results\" style=\"padding-top:0.25rem;display:grid;grid-template-columns:subgrid;grid-auto-rows:min-content;grid-column:1/-1;row-gap:0.25rem;overflow-y:auto;font-variant-numeric:tabular-nums\"></tbody></table><div class=\"centered-div\"><img id=\"image\" style=\"width:100%;max-width:256px;\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var20 string
templ_7745c5c3_Var20, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/pensive.webp?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 191, Col: 166}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var20))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 27, "\"><p id=\"status\" style=\"max-width:256px\">Loading...</p><script async type=\"module\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var21 string
templ_7745c5c3_Var21, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/pensive.webp?cacheBuster=" + anubis.Version)
templ_7745c5c3_Var21, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/js/bench.mjs?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 197, Col: 166}
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 193, Col: 138}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var21))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 31, "\"><p id=\"status\" style=\"max-width:256px\">Loading...</p><script async type=\"module\" src=\"")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
var templ_7745c5c3_Var22 string
templ_7745c5c3_Var22, templ_7745c5c3_Err = templ.JoinStringErrs(anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/js/bench.mjs?cacheBuster=" + anubis.Version)
if templ_7745c5c3_Err != nil {
return templ.Error{Err: templ_7745c5c3_Err, FileName: `index.templ`, Line: 199, Col: 138}
}
_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var22))
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 32, "\"></script><div id=\"sparkline\"></div><noscript><p>Running the benchmark tool requires JavaScript to be enabled.</p></noscript></div></div><form id=\"controls\" style=\"position:fixed;top:0.5rem;right:0.5rem\"><div style=\"display:flex;justify-content:end\"><label for=\"difficulty-input\" style=\"margin-right:0.5rem\">Difficulty:</label> <input id=\"difficulty-input\" type=\"number\" name=\"difficulty\" style=\"width:3rem\"></div><div style=\"margin-top:0.25rem;display:flex;justify-content:end\"><label for=\"algorithm-select\" style=\"margin-right:0.5rem\">Algorithm:</label> <select id=\"algorithm-select\" name=\"algorithm\"></select></div><div style=\"margin-top:0.25rem;display:flex;justify-content:end\"><label for=\"compare-select\" style=\"margin-right:0.5rem\">Compare:</label> <select id=\"compare-select\" name=\"compare\"><option value=\"NONE\">-</option></select></div></form>")
templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 28, "\"></script><div id=\"sparkline\"></div><noscript><p>Running the benchmark tool requires JavaScript to be enabled.</p></noscript></div></div><form id=\"controls\" style=\"position:fixed;top:0.5rem;right:0.5rem\"><div style=\"display:flex;justify-content:end\"><label for=\"difficulty-input\" style=\"margin-right:0.5rem\">Difficulty:</label> <input id=\"difficulty-input\" type=\"number\" name=\"difficulty\" style=\"width:3rem\"></div><div style=\"margin-top:0.25rem;display:flex;justify-content:end\"><label for=\"algorithm-select\" style=\"margin-right:0.5rem\">Algorithm:</label> <select id=\"algorithm-select\" name=\"algorithm\"></select></div><div style=\"margin-top:0.25rem;display:flex;justify-content:end\"><label for=\"compare-select\" style=\"margin-right:0.5rem\">Compare:</label> <select id=\"compare-select\" name=\"compare\"><option value=\"NONE\">-</option></select></div></form>")
if templ_7745c5c3_Err != nil {
return templ_7745c5c3_Err
}

View File

@@ -70,7 +70,7 @@ function processTask() {
let hash;
let nonce = 0;
do {
if ((nonce & 1023) === 0) {
if (nonce & (1023 === 0)) {
postMessage(nonce);
}
hash = await sha256(data + nonce++);

View File

@@ -21,9 +21,7 @@ User-agent: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: EchoboxBot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
@@ -44,7 +42,6 @@ User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
@@ -57,17 +54,12 @@ User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: PhindBot
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-CT
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: TikTokSpider