generate a knot-resolver (kresd) blacklist.rpz from pihole sources

config

-- Refer to manual: https://knot-resolver.readthedocs.io/en/latest/daemon.html#configuration

-- Listen on all interfaces (localhost would not work in Docker)
net.listen('0.0.0.0')
net.listen('0.0.0.0', 853, {tls=true})

-- Auto-maintain root TA
trust_anchors.file = '/data/root.keys'

-- Load Useful modules
modules = {
    'policy',                -- Block queries to local zones/bad sites
    'serve_stale < cache',   -- Allows stale-ness by up to one day, after roughly four seconds trying to contact the servers
    'workarounds < iterate', -- Alters resolver behavior on specific broken sub-domains
    'predict',               -- Prefetch expiring/frequent records
    'stats',                 -- Track internal statistics
    http = {                 -- HTTP server for serving stats etc...
        host = '192.168.2.110',
        port = 8053,
        cert = false,
    },
}

-- Smaller cache size
cache.size = 20 * MB

-- Block Ads and Malware Domains
policy.add(policy.rpz(policy.DENY, '/data/blacklist.rpz'))

-- Forward DNS to CloudFlare using TLS
policy.add(policy.all(
  policy.TLS_FORWARD({
    {'1.1.1.1', hostname='cloudflare-dns.com', ca_file='/data/DigiCertGlobalRootCA.crt' },
    {'1.0.0.1', hostname='cloudflare-dns.com', ca_file='/data/DigiCertGlobalRootCA.crt' },
  })
))

generate_blacklist.py

# Copyright (c) 2019 Jimmy Zelinskie
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

import re

from contextlib import closing
from urllib2 import urlopen


domain_blacklist = [
    "",
    "localhost",
    "127.0.0.1",
    "0.0.0.0",
    "255.225.225.255",
    "::1",
]


IP_REGEX = "(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])"
HOST_REGEX = "(([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.)*([A-Za-z0-9]|[A-Za-z0-9][A-Za-z0-9\-]*[A-Za-z0-9])"
HOSTSFILE_PREFIX = IP_REGEX + "|" + HOST_REGEX
HOSTSFILE_PREFIX_REGEX = re.compile(HOSTSFILE_PREFIX + "(\s+)")


HOSTSFILES_URLS = [
    "http://sysctl.org/cameleon/hosts",
    "https://hosts-file.net/ad_servers.txt",
    "https://hosts-file.net/grm.txt",
    "https://pgl.yoyo.org/adservers/serverlist.php?hostformat=hosts;showintro=0",
    "https://raw.githubusercontent.com/StevenBlack/hosts/master/hosts",
    "https://raw.githubusercontent.com/StevenBlack/hosts/master/data/KADhosts/hosts",
    "https://raw.githubusercontent.com/anudeepND/blacklist/master/adservers.txt",
    "https://reddestdream.github.io/Projects/MinimalHosts/etc/MinimalHostsBlocker/minimalhosts",
]


DOMAIN_LIST_URLS = [
    "https://gitlab.com/quidsup/notrack-blocklists/raw/master/notrack-blocklist.txt",
    "https://mirror1.malwaredomains.com/files/justdomains",
    "https://s3.amazonaws.com/lists.disconnect.me/simple_ad.txt",
    "https://s3.amazonaws.com/lists.disconnect.me/simple_tracking.txt",
    "https://v.firebog.net/hosts/AdguardDNS.txt",
    "https://v.firebog.net/hosts/Easyprivacy.txt",
    "https://zeustracker.abuse.ch/blocklist.php?download=domainblocklist",
]


def strip_comment(line):
    return line.split("#")[0].strip()


def domains_from_domain_list(fstream):
    for linebytes in fstream:
        line = linebytes.decode("utf-8").strip()
        if line.startswith("#"):
            continue

        domain = strip_comment(line)
        if domain not in domain_blacklist:
            yield domain


def domains_from_hostfile(fstream):
    for linebytes in fstream:
        line = linebytes.decode("utf-8").strip()
        prefix = HOSTSFILE_PREFIX_REGEX.match(line)
        if prefix is None:
            continue

        domain = strip_comment(line[prefix.end():])
        if domain in domain_blacklist:
            continue

        yield domain


def main():
    print "$TTL\t2\n" \
    "@\tIN\tSOA\tlocalhost.\troot.localhost.\t(\n" \
    "\t\t2\t;\tserial\n" \
    "\t\t2w\t;\trefresh\n" \
    "\t\t2w\t;\tretry\n" \
    "\t\t2w\t;\texpiry\n" \
    "\t\t2w\t;\tminimum\n" \
    "\t\tIN\tNS\tlocalhost.\n\n"

    domains = set()
    for url in HOSTSFILES_URLS:
        with closing(urlopen(url)) as f:
            domains = domains.union(set([domain for domain in domains_from_hostfile(f)]))

    for url in DOMAIN_LIST_URLS:
        with closing(urlopen(url)) as f:
            domains = domains.union(set([domain for domain in domains_from_domain_list(f)]))

    for domain in sorted(domains):
        print domain + "\tCNAME\t."
        print "*." + domain + "\tCNAME\t."


if __name__ == '__main__':
    main()