From 8c94ddba40d794b194f614091a84f5fc1d00a4b0 Mon Sep 17 00:00:00 2001
From: MDLeom <2809763-curben@users.noreply.gitlab.com>
Date: Sat, 8 Jan 2022 02:09:42 +0000
Subject: [PATCH] refactor: deploy filters to gitlab pages
- number of commits is becoming unwieldly
- gitlab pages is much faster than downloading from raw git
* main download link is still curben.gitlab.io/malware-filter/
* the cons is relying on gitlab ci/pages, previous approach was more portable
---
.gitignore | 4 +
.gitlab-ci.yml | 30 +++
.nvmrc | 1 +
LICENSE.md | 42 ++++
README.md | 588 ++++++++++++++++++++++++++++++++++++++++++++++++
package.json | 14 ++
src/build.js | 30 +++
src/exclude.txt | 77 +++++++
src/script.sh | 407 +++++++++++++++++++++++++++++++++
9 files changed, 1193 insertions(+)
create mode 100644 .gitignore
create mode 100644 .gitlab-ci.yml
create mode 100644 .nvmrc
create mode 100644 LICENSE.md
create mode 100644 README.md
create mode 100644 package.json
create mode 100644 src/build.js
create mode 100644 src/exclude.txt
create mode 100644 src/script.sh
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..4cae446e
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+tmp/
+.vscode/
+public/
+node_modules/
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
new file mode 100644
index 00000000..0758a6dc
--- /dev/null
+++ b/.gitlab-ci.yml
@@ -0,0 +1,30 @@
+image: alpine:latest # Use the latest version of Alpine Linux docker image
+
+build_job:
+ stage: build
+
+ before_script:
+ - apk update && apk add brotli curl grep
+
+ script:
+ - sh src/script.sh
+ - find public -type f -regex '.*\.\(txt\|conf\|tpl\|rules\)$' -exec gzip -f -k -9 {} \;
+ - find public -type f -regex '.*\.\(txt\|conf\|tpl\|rules\)$' -exec brotli -f -k -9 {} \;
+
+ artifacts:
+ paths:
+ - tmp
+ - public
+
+pages:
+ stage: deploy
+
+ script:
+ - echo
+
+ artifacts:
+ paths:
+ - public
+
+include:
+ - template: Security/Secret-Detection.gitlab-ci.yml
diff --git a/.nvmrc b/.nvmrc
new file mode 100644
index 00000000..b009dfb9
--- /dev/null
+++ b/.nvmrc
@@ -0,0 +1 @@
+lts/*
diff --git a/LICENSE.md b/LICENSE.md
new file mode 100644
index 00000000..b81428ec
--- /dev/null
+++ b/LICENSE.md
@@ -0,0 +1,42 @@
+CC0 1.0 Universal
+==================
+
+Statement of Purpose
+---------------------
+
+The laws of most jurisdictions throughout the world automatically confer exclusive Copyright and Related Rights (defined below) upon the creator and subsequent owner(s) (each and all, an "owner") of an original work of authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for the purpose of contributing to a commons of creative, cultural and scientific works ("Commons") that the public can reliably and without fear of later claims of infringement build upon, modify, incorporate in other works, reuse and redistribute as freely as possible in any form whatsoever and for any purposes, including without limitation commercial purposes. These owners may contribute to the Commons to promote the ideal of a free culture and the further production of creative, cultural and scientific works, or to gain reputation or greater distribution for their Work in part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any expectation of additional consideration or compensation, the person associating CC0 with a Work (the "Affirmer"), to the extent that he or she is an owner of Copyright and Related Rights in the Work, voluntarily elects to apply CC0 to the Work and publicly distribute the Work under its terms, with knowledge of his or her Copyright and Related Rights in the Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights.
+--------------------------------
+A Work made available under CC0 may be protected by copyright and related or neighboring rights ("Copyright and Related Rights"). Copyright and Related Rights include, but are not limited to, the following:
+
+i. the right to reproduce, adapt, distribute, perform, display, communicate, and translate a Work;
+ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or likeness depicted in a Work;
+iv. rights protecting against unfair competition in regards to a Work, subject to the limitations in paragraph 4(a), below;
+v. rights protecting the extraction, dissemination, use and reuse of data in a Work;
+vi. database rights (such as those arising under Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, and under any national implementation thereof, including any amended or successor version of such directive); and
+vii. other similar, equivalent or corresponding rights throughout the world based on applicable law or treaty, and any national implementations thereof.
+
+2. Waiver.
+-----------
+To the greatest extent permitted by, but not in contravention of, applicable law, Affirmer hereby overtly, fully, permanently, irrevocably and unconditionally waives, abandons, and surrenders all of Affirmer's Copyright and Related Rights and associated claims and causes of action, whether now known or unknown (including existing as well as future claims and causes of action), in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each member of the public at large and to the detriment of Affirmer's heirs and successors, fully intending that such Waiver shall not be subject to revocation, rescission, cancellation, termination, or any other legal or equitable action to disrupt the quiet enjoyment of the Work by the public as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback.
+----------------------------
+Should any part of the Waiver for any reason be judged legally invalid or ineffective under applicable law, then the Waiver shall be preserved to the maximum extent permitted taking into account Affirmer's express Statement of Purpose. In addition, to the extent the Waiver is so judged Affirmer hereby grants to each affected person a royalty-free, non transferable, non sublicensable, non exclusive, irrevocable and unconditional license to exercise Affirmer's Copyright and Related Rights in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "License"). The License shall be deemed effective as of the date CC0 was applied by Affirmer to the Work. Should any part of the License for any reason be judged legally invalid or ineffective under applicable law, such partial invalidity or ineffectiveness shall not invalidate the remainder of the License, and in such case Affirmer hereby affirms that he or she will not (i) exercise any of his or her remaining Copyright and Related Rights in the Work or (ii) assert any associated claims and causes of action with respect to the Work, in either case contrary to Affirmer's express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+--------------------------------
+
+a. No trademark or patent rights held by Affirmer are waived, abandoned, surrendered, licensed or otherwise affected by this document.
+b. Affirmer offers the Work as-is and makes no representations or warranties of any kind concerning the Work, express, implied, statutory or otherwise, including without limitation warranties of title, merchantability, fitness for a particular purpose, non infringement, or the absence of latent or other defects, accuracy, or the present or absence of errors, whether or not discoverable, all to the greatest extent permissible under applicable law.
+c. Affirmer disclaims responsibility for clearing rights of other persons that may apply to the Work or any use thereof, including without limitation any person's Copyright and Related Rights in the Work. Further, Affirmer disclaims responsibility for obtaining any necessary consents, permissions or other rights required for any use of the Work.
+d. Affirmer understands and acknowledges that Creative Commons is not a party to this document and has no duty or obligation with respect to this CC0 or use of the Work.
+
+For more information, please see
+https://creativecommons.org/publicdomain/zero/1.0/
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 00000000..c1c4cfa1
--- /dev/null
+++ b/README.md
@@ -0,0 +1,588 @@
+# Malicious URL Blocklist
+
+> Edit 2021/01/08: the default branch has changed to **main**.
+
+A blocklist of malicious websites that are being used for malware distribution, based on the **Database dump (CSV)** of Abuse.ch [URLhaus](https://urlhaus.abuse.ch/). Blocklist is updated twice a day.
+
+There are multiple formats available, refer to the appropriate section according to the program used:
+
+- uBlock Origin (uBO) -> [URL-based](#url-based) section (recommended)
+- Pi-hole -> [Domain-based](#domain-based) or [Hosts-based](#hosts-based) section
+- AdGuard Home -> [Domain-based (AdGuard Home)](#domain-based-adguard-home) or [Hosts-based](#hosts-based) section
+- AdGuard (browser extension) -> [URL-based (AdGuard)](#url-based-adguard)
+- Vivaldi -> [URL-based (Vivaldi)](#url-based-vivaldi)
+- [Hosts](#hosts-based)
+- [Dnsmasq](#dnsmasq)
+- BIND -> BIND [zone](#bind) or [RPZ](#response-policy-zone)
+- [Unbound](#unbound)
+- [dnscrypt-proxy](#dnscrypt-proxy)
+- Internet Explorer -> [Tracking Protection List (IE)](#tracking-protection-list-ie)
+- [Snort2](#snort2)
+- [Snort3](#snort3)
+- [Suricata](#suricata)
+
+Not sure which format to choose? See [Compatibility](https://gitlab.com/curben/urlhaus-filter/wikis/compatibility) page in the wiki.
+
+Check out my other filters:
+
+- [phishing-filter](https://gitlab.com/curben/phishing-filter)
+- [pup-filter](https://gitlab.com/curben/pup-filter)
+- [tracking-filter](https://gitlab.com/curben/tracking-filter)
+
+## URL-based
+
+Import the following URL into uBO to subscribe (includes online and **offline** malicious websites):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter.txt
+
+
+
+
+
+Lite version (**online** links only):
+
+_enabled by default in uBO >=[1.28.2](https://github.com/gorhill/uBlock/releases/tag/1.28.2)_
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-online.txt
+
+
+
+**Note:** Lite version is 99% smaller by excluding offline urls. The status of urls is determined by the upstream Abuse.ch. However, the test is not 100% accurate and some malicious urls that are otherwise accessible may be missed. If bandwidth (9 MB/day) is not a constraint, I recommend the regular version; browser extensions may utilise [HTTP compression](https://developer.mozilla.org/en-US/docs/Web/HTTP/Compression) that can save 70% of bandwidth.
+
+Regular version contains >260K filters, do note that uBO can [easily handle](https://github.com/uBlockOrigin/uBlock-issues/issues/338#issuecomment-452843669) 500K filters.
+
+If you've installed the lite version but prefer to use the regular version, it's better to remove it beforehand. Having two versions at the same time won't cause any conflict issue, uBO can detect duplicate network filters and adjust accordingly, but it's a waste of your bandwidth.
+
+**AdGuard Home** users should use [this blocklist](#domain-based-adguard-home).
+
+## URL-based (AdGuard)
+
+Import the following URL into AdGuard browser extensions to subscribe (includes online and **offline** malicious websites):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-ag.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-ag.txt
+
+
+
+
+
+Lite version (**online** links only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-ag-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-ag-online.txt
+
+
+
+## URL-based (Vivaldi)
+
+_Requires Vivaldi Desktop/Android 3.3+, blocking level must be at least "Block Trackers"_
+
+Import the following URL into Vivaldi's **Tracker Blocking Sources** to subscribe (includes online and **offline** malicious websites):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-vivaldi.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-vivaldi.txt
+
+
+
+
+
+Lite version (**online** links only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-vivaldi-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-vivaldi-online.txt
+
+
+
+## Domain-based
+
+This blocklist includes domains and IP addresses.
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-domains.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-domains.txt
+
+
+
+
+Lite version (online domains/IPs only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-domains-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-domains-online.txt
+
+
+
+## Domain-based (AdGuard Home)
+
+This AdGuard Home-compatible blocklist includes domains and IP addresses.
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-agh.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-agh.txt
+
+
+
+
+Lite version (online domains/IPs only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-agh-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-agh-online.txt
+
+
+
+## Hosts-based
+
+This blocklist includes domains only.
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-hosts.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-hosts.txt
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-hosts-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-hosts-online.txt
+
+
+
+## Dnsmasq
+
+This blocklist includes domains only.
+
+### Install
+
+```
+# Create a new folder to store the blocklist
+mkdir -p /usr/local/etc/dnsmasq/
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-dnsmasq.conf" -o "/usr/local/etc/dnsmasq/urlhaus-filter-dnsmasq.conf"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+
+# Configure dnsmasq to use the blocklist
+printf "\nconf-file=/usr/local/etc/dnsmasq/urlhaus-filter-dnsmasq.conf\n" >> /etc/dnsmasq.conf
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnsmasq.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnsmasq.conf
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnsmasq-online.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnsmasq-online.conf
+
+
+
+## BIND
+
+This blocklist includes domains only.
+
+### Install
+
+```
+# Create a new folder to store the blocklist
+mkdir -p /usr/local/etc/bind/
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-bind.conf" -o "/usr/local/etc/bind/urlhaus-filter-bind.conf"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+
+# Configure BIND to use the blocklist
+printf '\ninclude "/usr/local/etc/bind/urlhaus-filter-bind.conf";\n' >> /etc/bind/named.conf
+```
+
+Add this to "/etc/bind/null.zone.file" (skip this step if the file already exists):
+
+```
+$TTL 86400 ; one day
+@ IN SOA ns.nullzone.loc. ns.nullzone.loc. (
+ 2017102203
+ 28800
+ 7200
+ 864000
+ 86400 )
+ NS ns.nullzone.loc.
+ A 0.0.0.0
+@ IN A 0.0.0.0
+* IN A 0.0.0.0
+```
+
+Zone file is derived from [here](https://github.com/tomzuu/blacklist-named/blob/master/null.zone.file).
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-bind.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-bind.conf
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-bind-online.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-bind-online.conf
+
+
+
+## Response Policy Zone
+
+This blocklist includes domains only.
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-rpz.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-rpz.conf
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-rpz-online.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-rpz-online.conf
+
+
+
+## Unbound
+
+This blocklist includes domains only.
+
+### Install
+
+```
+# Create a new folder to store the blocklist
+mkdir -p /usr/local/etc/unbound/
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-unbound.conf" -o "/usr/local/etc/unbound/urlhaus-filter-unbound.conf"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+
+# Configure Unbound to use the blocklist
+printf '\n include: "/usr/local/etc/unbound/urlhaus-filter-unbound.conf"\n' >> /etc/unbound/unbound.conf
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-unbound.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-unbound.conf
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-unbound-online.conf
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-unbound-online.conf
+
+
+
+## dnscrypt-proxy
+
+### Install
+
+```
+# Create a new folder to store the blocklist
+mkdir -p /etc/dnscrypt-proxy/
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-names.txt" -o "/etc/dnscrypt-proxy/urlhaus-filter-dnscrypt-blocked-names.txt"\n' > /etc/cron.daily/urlhaus-filter
+printf '\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-ips.txt" -o "/etc/dnscrypt-proxy/urlhaus-filter-dnscrypt-blocked-ips.txt"\n' >> /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+```
+
+Configure dnscrypt-proxy to use the blocklist:
+
+``` diff
+[blocked_names]
++ blocked_names_file = '/etc/dnscrypt-proxy/urlhaus-filter-dnscrypt-blocked-names.txt'
+
+[blocked_ips]
++ blocked_ips_file = '/etc/dnscrypt-proxy/urlhaus-filter-dnscrypt-blocked-ips.txt'
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-names.txt
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-ips.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnscrypt-blocked-names.txt
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnscrypt-blocked-ips.txt
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-names-online.txt
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-dnscrypt-blocked-ips-online.txt
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnscrypt-blocked-names-online.txt
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-dnscrypt-blocked-ips-online.txt
+
+
+
+
+## Tracking Protection List (IE)
+
+This blocklist includes domains only. Supported in Internet Explorer 9+.
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter.tpl
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter.tpl
+
+
+
+
+Lite version (online domains only):
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-online.tpl
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-online.tpl
+
+
+
+## Snort2
+
+This ruleset includes online URLs only. Not compatible with [Snort3](#snort3).
+
+### Install
+
+```
+# Download ruleset
+curl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-snort2-online.rules" -o "/etc/snort/rules/urlhaus-filter-snort2-online.rules"
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-snort2-online.rules" -o "/etc/snort/rules/urlhaus-filter-snort2-online.rules"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+
+# Configure Snort to use the ruleset
+printf "\ninclude \$RULE_PATH/urlhaus-filter-snort2-online.rules\n" >> /etc/snort/snort.conf
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-snort2-online.rules
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-snort2-online.rules
+
+
+
+## Snort3
+
+This ruleset includes online URLs only. Not compatible with [Snort2](#snort2).
+
+### Install
+
+```
+# Download ruleset
+curl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-snort3-online.rules" -o "/etc/snort/rules/urlhaus-filter-snort3-online.rules"
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-snort3-online.rules" -o "/etc/snort/rules/urlhaus-filter-snort3-online.rules"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+```
+
+Configure Snort to use the ruleset:
+
+``` diff
+# /etc/snort/snort.lua
+ips =
+{
+ variables = default_variables,
++ include = 'rules/urlhaus-filter-snort3-online.rules'
+}
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-snort3-online.rules
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-snort3-online.rules
+
+
+
+## Suricata
+
+This ruleset includes online URLs only.
+
+### Install
+
+```
+# Download ruleset
+curl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-suricata-online.rules" -o "/etc/suricata/rules/urlhaus-filter-suricata-online.rules"
+
+# Create a new cron job for daily update
+printf '#!/bin/sh\ncurl -L "https://curben.gitlab.io/malware-filter/urlhaus-filter-suricata-online.rules" -o "/etc/suricata/rules/urlhaus-filter-suricata-online.rules"\n' > /etc/cron.daily/urlhaus-filter
+
+# cron job requires execution permission
+chmod 755 /etc/cron.daily/urlhaus-filter
+```
+
+Configure Suricata to use the ruleset:
+
+``` diff
+# /etc/suricata/suricata.yaml
+rule-files:
+ - local.rules
++ - urlhaus-filter-suricata-online.rules
+```
+
+- https://curben.gitlab.io/malware-filter/urlhaus-filter-suricata-online.rules
+
+
+Mirrors
+
+- https://curben.gitlab.io/urlhaus-filter/urlhaus-filter-suricata-online.rules
+
+
+
+## Third-party mirrors
+
+
+iosprivacy/urlhaus-filter-mirror
+
+TBC
+
+
+
+## Issues
+
+This blocklist operates by blocking the **whole** website, instead of specific webpages; exceptions are made on popular websites (e.g. `https://docs.google.com/`), in which webpages are specified instead (e.g. `https://docs.google.com/malware-page`). Malicious webpages are only listed in the [URL-based](#url-based) filter, popular websites are excluded from other filters.
+
+*Popular* websites are as listed in the [Umbrella Popularity List](https://s3-us-west-1.amazonaws.com/umbrella-static/index.html) (top 1M domains + subdomains), [Tranco List](https://tranco-list.eu/) (top 1M domains) and this [custom list](src/exclude.txt).
+
+If you wish to exclude certain website(s) that you believe is sufficiently well-known, please create an [issue](https://gitlab.com/curben/urlhaus-filter/issues) or [merge request](https://gitlab.com/curben/urlhaus-filter/merge_requests). If the website is quite obscure but you still want to visit it, you can add a new line `||legitsite.com^$badfilter` to "My filters" tab of uBO; use a subdomain if relevant, `||sub.legitsite.com^$badfilter`.
+
+This filter **only** accepts new malware URLs from [URLhaus](https://urlhaus.abuse.ch/).
+
+Please report new malware URL to the upstream maintainer through https://urlhaus.abuse.ch/api/#submit.
+
+## Cloning
+
+Since the filter is updated frequently, cloning the repo would become slower over time as the revision grows.
+
+Use shallow clone to get the recent revisions only. Getting the last five revisions should be sufficient for a valid MR.
+
+`git clone --depth 5 https://gitlab.com/curben/urlhaus-filter.git`
+
+## FAQ
+
+See [FAQ](https://gitlab.com/curben/urlhaus-filter/wikis/faq).
+
+## License
+
+[Creative Commons Zero v1.0 Universal](LICENSE.md)
+
+[badge.sh](src/badge.sh) & [.gitlab/](.gitlab/) contain badges that are licensed by [Shields.io](https://shields.io) under [CC0 1.0](LICENSE.md)
+
+[URLhaus](https://urlhaus.abuse.ch/): [CC0](https://creativecommons.org/publicdomain/zero/1.0/)
+
+[Tranco List](https://tranco-list.eu/): [MIT License](https://choosealicense.com/licenses/mit/)
+
+[Umbrella Popularity List](https://s3-us-west-1.amazonaws.com/umbrella-static/index.html): Available free of charge by Cisco Umbrella
+
+This repository is not endorsed by Abuse.ch.
diff --git a/package.json b/package.json
new file mode 100644
index 00000000..23c83e99
--- /dev/null
+++ b/package.json
@@ -0,0 +1,14 @@
+{
+ "name": "urlhaus-filter",
+ "private": true,
+ "scripts": {
+ "build": "node src/build.js"
+ },
+ "dependencies": {
+ "extract-zip": "^2.0.1",
+ "got": "^11.8.3"
+ },
+ "engines": {
+ "node": ">= 14.15.0"
+ }
+}
diff --git a/src/build.js b/src/build.js
new file mode 100644
index 00000000..2f228e2e
--- /dev/null
+++ b/src/build.js
@@ -0,0 +1,30 @@
+'use strict'
+
+// for deployment outside of GitLab CI, e.g. Cloudflare Pages and Netlify
+
+const { stream: gotStream } = require('got')
+const unzip = require('extract-zip')
+const { join } = require('path')
+const { mkdir } = require('fs/promises')
+const { createWriteStream } = require('fs')
+const { pipeline } = require('stream/promises')
+
+const rootPath = join(__dirname, '..')
+const tmpPath = join(rootPath, 'tmp')
+const zipPath = join(tmpPath, 'artifacts.zip')
+const artifactsUrl = 'https://gitlab.com/curben/urlhaus-filter/-/jobs/artifacts/main/download?job=pages'
+
+const f = async () => {
+ await mkdir(tmpPath, { recursive: true })
+
+ console.log(`Downloading artifacts.zip from "${artifactsUrl}"`)
+ await pipeline(
+ gotStream(artifactsUrl),
+ createWriteStream(zipPath)
+ )
+
+ console.log('Extracting artifacts.zip...')
+ await unzip(zipPath, { dir: rootPath })
+}
+
+f()
diff --git a/src/exclude.txt b/src/exclude.txt
new file mode 100644
index 00000000..9c2c27e5
--- /dev/null
+++ b/src/exclude.txt
@@ -0,0 +1,77 @@
+# Exclusion list
+# malicious links are still included in "urlhaus-filter.txt" & "urlhaus-filter-online.txt"
+shellter-static.s3.amazonaws.com
+void.cat
+lists.infradead.org
+cdimage.debian.org
+pdesaa.cimaa.pt
+shengen.ru
+cdn-frm-eu.wargaming.net
+hampsteadclinic.co.uk
+users.skynet.be
+users.telenet.be
+u.teknik.io
+digitalschnitt.de
+debonosu.jp
+cd.textfiles.com
+a.uguu.se
+s3.us-east-2.amazonaws.com
+s3.us-east-1.amazonaws.com
+s3.amazonaws.com
+s3.us-west-1.amazonaws.com
+s3.us-west-2.amazonaws.com
+s3.af-south-1.amazonaws.com
+s3.ap-east-1.amazonaws.com
+s3.ap-south-1.amazonaws.com
+s3.ap-northeast-3.amazonaws.com
+s3.ap-northeast-2.amazonaws.com
+s3.ap-southeast-1.amazonaws.com
+s3.ap-southeast-2.amazonaws.com
+s3.ap-northeast-1.amazonaws.com
+s3.ca-central-1.amazonaws.com
+s3.cn-north-1.amazonaws.com.cn
+s3.cn-northwest-1.amazonaws.com.cn
+s3.eu-central-1.amazonaws.com
+s3.eu-west-1.amazonaws.com
+s3.eu-west-2.amazonaws.com
+s3.eu-south-1.amazonaws.com
+s3.eu-west-3.amazonaws.com
+s3.eu-north-1.amazonaws.com
+s3.sa-east-1.amazonaws.com
+s3.me-south-1.amazonaws.com
+s3.us-gov-east-1.amazonaws.com
+s3.us-gov-west-1.amazonaws.com
+s3-us-east-2.amazonaws.com
+s3-us-east-1.amazonaws.com
+s3-us-west-1.amazonaws.com
+s3-us-west-2.amazonaws.com
+s3-af-south-1.amazonaws.com
+s3-ap-east-1.amazonaws.com
+s3-ap-south-1.amazonaws.com
+s3-ap-northeast-3.amazonaws.com
+s3-ap-northeast-2.amazonaws.com
+s3-ap-southeast-1.amazonaws.com
+s3-ap-southeast-2.amazonaws.com
+s3-ap-northeast-1.amazonaws.com
+s3-ca-central-1.amazonaws.com
+s3-cn-north-1.amazonaws.com.cn
+s3-cn-northwest-1.amazonaws.com.cn
+s3-eu-central-1.amazonaws.com
+s3-eu-west-1.amazonaws.com
+s3-eu-west-2.amazonaws.com
+s3-eu-south-1.amazonaws.com
+s3-eu-west-3.amazonaws.com
+s3-eu-north-1.amazonaws.com
+s3-sa-east-1.amazonaws.com
+s3-me-south-1.amazonaws.com
+s3-us-gov-east-1.amazonaws.com
+s3-us-gov-west-1.amazonaws.com
+srv-store4.gofile.io
+srv-store6.gofile.io
+srv-file9.gofile.io
+blog.theodo.com
+ronnietucker.co.uk
+cdn.tmooc.cn
+104.244.72.54
+dl.packetstormsecurity.net
+screenshield.us
diff --git a/src/script.sh b/src/script.sh
new file mode 100644
index 00000000..e855a802
--- /dev/null
+++ b/src/script.sh
@@ -0,0 +1,407 @@
+#!/bin/sh
+
+set -efux -o pipefail
+
+## Create a temporary working folder
+mkdir -p "tmp/"
+cd "tmp/"
+
+
+## Prepare datasets
+curl -L "https://urlhaus.abuse.ch/downloads/csv/" -o "urlhaus.zip"
+curl -L "https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip" -o "top-1m-umbrella.zip"
+curl -L "https://tranco-list.eu/top-1m.csv.zip" -o "top-1m-tranco.zip"
+
+cp -f "../src/exclude.txt" "."
+
+## Prepare URLhaus.csv
+unzip -p "urlhaus.zip" | \
+# Convert DOS to Unix line ending
+dos2unix | \
+tr "[:upper:]" "[:lower:]" | \
+# Remove comment
+sed "/^#/d" > "URLhaus.csv"
+
+## Parse URLs
+cat "URLhaus.csv" | \
+cut -f 6 -d '"' | \
+cut -f 3- -d "/" | \
+# Domain must have at least a 'dot'
+grep -F "." | \
+# Remove invalid protocol, see #32
+sed -E "s/^(ttps:\/\/|https:\/|http\/)//g" | \
+# Remove www.
+sed "s/^www\.//g" | \
+sort -u > "urlhaus.txt"
+
+## Parse domain and IP address only
+cat "urlhaus.txt" | \
+cut -f 1 -d "/" | \
+cut -f 1 -d ":" | \
+# Remove invalid domains, see #15
+grep -vF "??" | \
+cut -f 1 -d "?" | \
+sort -u > "urlhaus-domains.txt"
+
+## Parse online URLs only
+cat "URLhaus.csv" | \
+grep '"online"' | \
+cut -f 6 -d '"' | \
+cut -f 3- -d "/" | \
+sed "s/^www\.//g" | \
+sort -u > "urlhaus-online.txt"
+
+cat "urlhaus-online.txt" | \
+cut -f 1 -d "/" | \
+cut -f 1 -d ":" | \
+grep -vF "??" | \
+cut -f 1 -d "?" | \
+sort -u > "urlhaus-domains-online.txt"
+
+
+## Parse the Umbrella 1 Million
+unzip -p "top-1m-umbrella.zip" | \
+dos2unix | \
+tr "[:upper:]" "[:lower:]" | \
+# Parse domains only
+cut -f 2 -d "," | \
+grep -F "." | \
+# Remove www.
+sed "s/^www\.//g" | \
+sort -u > "top-1m-umbrella.txt"
+
+## Parse the Tranco 1 Million
+unzip -p "top-1m-tranco.zip" | \
+dos2unix | \
+tr "[:upper:]" "[:lower:]" | \
+# Parse domains only
+cut -f 2 -d "," | \
+grep -F "." | \
+# Remove www.
+sed "s/^www\.//g" | \
+sort -u > "top-1m-tranco.txt"
+
+# Merge Umbrella and self-maintained top domains
+cat "top-1m-umbrella.txt" "top-1m-tranco.txt" "exclude.txt" | \
+sort -u > "top-1m-well-known.txt"
+
+
+## Parse popular domains from URLhaus
+cat "urlhaus-domains.txt" | \
+# grep match whole line
+grep -Fx -f "top-1m-well-known.txt" > "urlhaus-top-domains.txt"
+
+
+## Parse domains from URLhaus excluding popular domains
+cat "urlhaus-domains.txt" | \
+grep -F -vf "urlhaus-top-domains.txt" | \
+# Remove blank lines
+sed "/^$/d" > "malware-domains.txt"
+
+cat "urlhaus-domains-online.txt" | \
+grep -F -vf "urlhaus-top-domains.txt" | \
+sed "/^$/d" > "malware-domains-online.txt"
+
+## Parse malware URLs from popular domains
+cat "urlhaus.txt" | \
+grep -F -f "urlhaus-top-domains.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$all/g" > "malware-url-top-domains.txt"
+
+cat "urlhaus-online.txt" | \
+grep -F -f "urlhaus-top-domains.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$all/g" > "malware-url-top-domains-online.txt"
+
+cat "urlhaus-online.txt" | \
+grep -F -f "urlhaus-top-domains.txt" > "malware-url-top-domains-raw-online.txt"
+
+
+## Merge malware domains and URLs
+CURRENT_TIME="$(date -R -u)"
+FIRST_LINE="! Title: Malicious URL Blocklist"
+SECOND_LINE="! Updated: $CURRENT_TIME"
+THIRD_LINE="! Expires: 1 day (update frequency)"
+FOURTH_LINE="! Homepage: https://gitlab.com/curben/urlhaus-filter"
+FIFTH_LINE="! License: https://gitlab.com/curben/urlhaus-filter#license"
+SIXTH_LINE="! Source: https://urlhaus.abuse.ch/api/"
+ANNOUNCEMENT_1="\n! 2021/01/08: There has been a major change to the mirrors, check the repo for the new mirrors."
+ANNOUNCEMENT_2="! Old mirrors will be deprecated in 3 months. The main download link \"curben.gitlab.io/malware-filter/\" _is not affected_."
+COMMENT_ABP="$FIRST_LINE\n$SECOND_LINE\n$THIRD_LINE\n$FOURTH_LINE\n$FIFTH_LINE\n$SIXTH_LINE\n$ANNOUNCEMENT_1\n$ANNOUNCEMENT_2"
+
+mkdir -p "../public/"
+
+cat "malware-domains.txt" "malware-url-top-domains.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' > "../public/urlhaus-filter.txt"
+
+cat "malware-domains-online.txt" "malware-url-top-domains-online.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Malicious/Online Malicious/" > "../public/urlhaus-filter-online.txt"
+
+
+# Adguard Home (#19, #22)
+cat "malware-domains.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/^/g" > "malware-domains-adguard-home.txt"
+
+cat "malware-domains-online.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/^/g" > "malware-domains-online-adguard-home.txt"
+
+cat "malware-domains-adguard-home.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Blocklist/Blocklist (AdGuard Home)/" > "../public/urlhaus-filter-agh.txt"
+
+cat "malware-domains-online-adguard-home.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Malicious/Online Malicious/" | \
+sed "1s/Blocklist/Blocklist (AdGuard Home)/" > "../public/urlhaus-filter-agh-online.txt"
+
+
+# Adguard browser extension
+cat "malware-domains.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$all/g" > "malware-domains-adguard.txt"
+
+cat "malware-domains-online.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$all/g" > "malware-domains-online-adguard.txt"
+
+cat "malware-domains-adguard.txt" "malware-url-top-domains.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Blocklist/Blocklist (AdGuard)/" > "../public/urlhaus-filter-ag.txt"
+
+cat "malware-domains-online-adguard.txt" "malware-url-top-domains-online.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Malicious/Online Malicious/" | \
+sed "1s/Blocklist/Blocklist (AdGuard)/" > "../public/urlhaus-filter-ag-online.txt"
+
+
+# Vivaldi
+cat "malware-domains.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$document/g" > "malware-domains-vivaldi.txt"
+
+cat "malware-domains-online.txt" | \
+sed "s/^/||/g" | \
+sed "s/$/\$document/g" > "malware-domains-online-vivaldi.txt"
+
+cat "malware-domains-vivaldi.txt" "malware-url-top-domains.txt" | \
+sed "s/\$all$/\$document/g" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Blocklist/Blocklist (Vivaldi)/" > "../public/urlhaus-filter-vivaldi.txt"
+
+cat "malware-domains-online-vivaldi.txt" "malware-url-top-domains-online.txt" | \
+sed "s/\$all$/\$document/g" | \
+sort | \
+sed '1 i\'"$COMMENT_ABP"'' | \
+sed "1s/Malicious/Online Malicious/" | \
+sed "1s/Blocklist/Blocklist (Vivaldi)/" > "../public/urlhaus-filter-vivaldi-online.txt"
+
+
+## Domains-only blocklist
+# awk + head is a workaround for sed prepend
+COMMENT=$(printf "$COMMENT_ABP" | sed "s/^!/#/g" | sed "1s/URL/Domains/" | awk '{printf "%s\\n", $0}' | head -c -2)
+COMMENT_ONLINE=$(printf "$COMMENT" | sed "1s/Malicious/Online Malicious/" | awk '{printf "%s\\n", $0}' | head -c -2)
+
+cat "malware-domains.txt" | \
+sort | \
+sed '1 i\'"$COMMENT"'' > "../public/urlhaus-filter-domains.txt"
+
+cat "malware-domains-online.txt" | \
+sort | \
+sed '1 i\'"$COMMENT_ONLINE"'' > "../public/urlhaus-filter-domains-online.txt"
+
+
+## Hosts only
+cat "malware-domains.txt" | \
+sort | \
+# Remove IPv4 address
+grep -vE "^([0-9]{1,3}[\.]){3}[0-9]{1,3}$" > "malware-hosts.txt"
+
+cat "malware-domains-online.txt" | \
+sort | \
+# Remove IPv4 address
+grep -vE "^([0-9]{1,3}[\.]){3}[0-9]{1,3}$" > "malware-hosts-online.txt"
+
+
+## Hosts file blocklist
+cat "malware-hosts.txt" | \
+sed "s/^/0.0.0.0 /g" | \
+# Re-insert comment
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Domains/Hosts/" > "../public/urlhaus-filter-hosts.txt"
+
+cat "malware-hosts-online.txt" | \
+sed "s/^/0.0.0.0 /g" | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Domains/Hosts/" > "../public/urlhaus-filter-hosts-online.txt"
+
+
+## Dnsmasq-compatible blocklist
+cat "malware-hosts.txt" | \
+sed "s/^/address=\//g" | \
+sed "s/$/\/0.0.0.0/g" | \
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Blocklist/dnsmasq Blocklist/" > "../public/urlhaus-filter-dnsmasq.conf"
+
+cat "malware-hosts-online.txt" | \
+sed "s/^/address=\//g" | \
+sed "s/$/\/0.0.0.0/g" | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Blocklist/dnsmasq Blocklist/" > "../public/urlhaus-filter-dnsmasq-online.conf"
+
+
+## BIND-compatible blocklist
+cat "malware-hosts.txt" | \
+sed 's/^/zone "/g' | \
+sed 's/$/" { type master; notify no; file "null.zone.file"; };/g' | \
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Blocklist/BIND Blocklist/" > "../public/urlhaus-filter-bind.conf"
+
+cat "malware-hosts-online.txt" | \
+sed 's/^/zone "/g' | \
+sed 's/$/" { type master; notify no; file "null.zone.file"; };/g' | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Blocklist/BIND Blocklist/" > "../public/urlhaus-filter-bind-online.conf"
+
+
+## DNS Response Policy Zone (RPZ)
+CURRENT_UNIX_TIME="$(date +%s)"
+RPZ_SYNTAX="\n\$TTL 30\n@ IN SOA rpz.curben.gitlab.io. hostmaster.rpz.curben.gitlab.io. $CURRENT_UNIX_TIME 86400 3600 604800 30\n NS localhost.\n"
+
+cat "malware-hosts.txt" | \
+sed "s/$/ CNAME ./g" | \
+sed '1 i\'"$RPZ_SYNTAX"'' | \
+sed '1 i\'"$COMMENT"'' | \
+sed "s/^#/;/g" | \
+sed "1s/Blocklist/RPZ Blocklist/" > "../public/urlhaus-filter-rpz.conf"
+
+cat "malware-hosts-online.txt" | \
+sed "s/$/ CNAME ./g" | \
+sed '1 i\'"$RPZ_SYNTAX"'' | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "s/^#/;/g" | \
+sed "1s/Blocklist/RPZ Blocklist/" > "../public/urlhaus-filter-rpz-online.conf"
+
+
+## Unbound-compatible blocklist
+cat "malware-hosts.txt" | \
+sed 's/^/local-zone: "/g' | \
+sed 's/$/" always_nxdomain/g' | \
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Blocklist/Unbound Blocklist/" > "../public/urlhaus-filter-unbound.conf"
+
+cat "malware-hosts-online.txt" | \
+sed 's/^/local-zone: "/g' | \
+sed 's/$/" always_nxdomain/g' | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Blocklist/Unbound Blocklist/" > "../public/urlhaus-filter-unbound-online.conf"
+
+
+## dnscrypt-proxy blocklists
+# name-based
+cat "malware-hosts.txt" | \
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Domains/Names/" > "../public/urlhaus-filter-dnscrypt-blocked-names.txt"
+
+cat "malware-hosts-online.txt" | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Domains/Names/" > "../public/urlhaus-filter-dnscrypt-blocked-names-online.txt"
+
+## IPv4-based
+cat "malware-domains.txt" | \
+sort | \
+grep -E "^([0-9]{1,3}[\.]){3}[0-9]{1,3}$" | \
+sed '1 i\'"$COMMENT"'' | \
+sed "1s/Domains/IPs/" > "../public/urlhaus-filter-dnscrypt-blocked-ips.txt"
+
+cat "malware-domains-online.txt" | \
+sort | \
+grep -E "^([0-9]{1,3}[\.]){3}[0-9]{1,3}$" | \
+sed '1 i\'"$COMMENT_ONLINE"'' | \
+sed "1s/Domains/IPs/" > "../public/urlhaus-filter-dnscrypt-blocked-ips-online.txt"
+
+
+## Temporarily disable command print
+set +x
+
+
+# Snort & Suricata
+rm -f "../public/urlhaus-filter-snort2-online.rules" \
+ "../public/urlhaus-filter-snort3-online.rules" \
+ "../public/urlhaus-filter-suricata-online.rules"
+
+SID="100000001"
+while read DOMAIN; do
+ SN_RULE="alert tcp \$HOME_NET any -> \$EXTERNAL_NET [80,443] (msg:\"urlhaus-filter malicious website detected\"; flow:established,from_client; content:\"GET\"; http_method; content:\"$DOMAIN\"; content:\"Host\"; http_header; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ SN3_RULE="alert http \$HOME_NET any -> \$EXTERNAL_NET any (msg:\"urlhaus-filter malicious website detected\"; http_header:field host; content:\"$DOMAIN\",nocase; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ SR_RULE="alert http \$HOME_NET any -> \$EXTERNAL_NET any (msg:\"urlhaus-filter malicious website detected\"; flow:established,from_client; http.method; content:\"GET\"; http.host; content:\"$DOMAIN\"; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ echo "$SN_RULE" >> "../public/urlhaus-filter-snort2-online.rules"
+ echo "$SN3_RULE" >> "../public/urlhaus-filter-snort3-online.rules"
+ echo "$SR_RULE" >> "../public/urlhaus-filter-suricata-online.rules"
+
+ SID=$(( $SID + 1 ))
+done < "malware-domains-online.txt"
+
+while read URL; do
+ HOST=$(echo "$URL" | cut -d"/" -f1)
+ URI=$(echo "$URL" | sed -e "s/^$HOST//" -e "s/;/\\\;/g")
+
+ # Snort2 only supports <=2047 characters of `content`
+ SN_RULE="alert tcp \$HOME_NET any -> \$EXTERNAL_NET [80,443] (msg:\"urlhaus-filter malicious website detected\"; flow:established,from_client; content:\"GET\"; http_method; content:\"$(echo $URI | cut -c -2047)\"; http_uri; nocase; content:\"$HOST\"; content:\"Host\"; http_header; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ SN3_RULE="alert http \$HOME_NET any -> \$EXTERNAL_NET any (msg:\"urlhaus-filter malicious website detected\"; http_header:field host; content:\"$HOST\",nocase; http_uri; content:\"$URI\",nocase; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ SR_RULE="alert http \$HOME_NET any -> \$EXTERNAL_NET any (msg:\"urlhaus-filter malicious website detected\"; flow:established,from_client; http.method; content:\"GET\"; http.uri; content:\"$URI\"; endswith; nocase; http.host; content:\"$HOST\"; classtype:trojan-activity; sid:$SID; rev:1;)"
+
+ echo "$SN_RULE" >> "../public/urlhaus-filter-snort2-online.rules"
+ echo "$SN3_RULE" >> "../public/urlhaus-filter-snort3-online.rules"
+ echo "$SR_RULE" >> "../public/urlhaus-filter-suricata-online.rules"
+
+ SID=$(( $SID + 1 ))
+done < "malware-url-top-domains-raw-online.txt"
+
+## Re-enable command print
+set -x
+
+sed -i '1 i\'"$COMMENT_ONLINE"'' "../public/urlhaus-filter-snort2-online.rules"
+sed -i "1s/Domains Blocklist/URL Snort2 Ruleset/" "../public/urlhaus-filter-snort2-online.rules"
+
+sed -i '1 i\'"$COMMENT_ONLINE"'' "../public/urlhaus-filter-snort3-online.rules"
+sed -i "1s/Domains Blocklist/URL Snort3 Ruleset/" "../public/urlhaus-filter-snort3-online.rules"
+
+sed -i '1 i\'"$COMMENT_ONLINE"'' "../public/urlhaus-filter-suricata-online.rules"
+sed -i "1s/Domains Blocklist/URL Suricata Ruleset/" "../public/urlhaus-filter-suricata-online.rules"
+
+
+## IE blocklist
+COMMENT_IE="msFilterList\n$COMMENT\n: Expires=1\n#"
+COMMENT_ONLINE_IE="msFilterList\n$COMMENT_ONLINE\n: Expires=1\n#"
+
+cat "malware-hosts.txt" | \
+sed "s/^/-d /g" | \
+sed '1 i\'"$COMMENT_IE"'' | \
+sed "2s/Domains Blocklist/Hosts Blocklist (IE)/" > "../public/urlhaus-filter.tpl"
+
+cat "malware-hosts-online.txt" | \
+sed "s/^/-d /g" | \
+sed '1 i\'"$COMMENT_ONLINE_IE"'' | \
+sed "2s/Domains Blocklist/Hosts Blocklist (IE)/" > "../public/urlhaus-filter-online.tpl"
+
+
+## Clean up artifacts
+rm -f "URLhaus.csv" "top-1m-umbrella.zip" "top-1m-umbrella.txt" "top-1m-tranco.txt"
+
+
+cd ../