Import the generate-domains-blacklists tool

This commit is contained in:
Frank Denis 2018-01-17 15:28:07 +01:00
parent 6ad53c75e6
commit 35e32b823f
5 changed files with 391 additions and 0 deletions

View File

@ -0,0 +1,93 @@
##################################################################################
# #
# Generate a black list of domains using public data sources, and the local #
# domains-blacklist-local-additions.txt file. #
# #
# Comment the URLs of the sources you want to disable, and run the script to #
# build the dnscrypt-blacklist-domains.txt file: #
# #
# $ generate-domains-blacklist.py > dnscrypt-blacklist-domains.txt #
# #
# That blacklist file can then be used in the dnscrypt-proxy configuration: #
# #
# BlackList domains:/etc/dnscrypt-blacklist-domains.txt #
# #
##################################################################################
# Local additions
file:domains-blacklist-local-additions.txt
# Bambenek malware C2s
http://osint.bambenekconsulting.com/feeds/c2-dommasterlist.txt
# hpHosts Ad and tracking servers
http://hosts-file.net/.%5Cad_servers.txt
# Malware domains
http://mirror1.malwaredomains.com/files/justdomains
# Abuse.ch Ransomware Tracker
http://ransomwaretracker.abuse.ch/downloads/RW_DOMBL.txt
# Malware Domain List
http://www.malwaredomainlist.com/mdlcsv.php?inactive=off
# Adblock Warning Removal List
https://easylist-downloads.adblockplus.org/antiadblockfilters.txt
# EasyList
https://easylist-downloads.adblockplus.org/easylist_noelemhide.txt
# EasyList China
https://easylist-downloads.adblockplus.org/easylistchina.txt
# Fanboys Social Blocking List
https://easylist-downloads.adblockplus.org/fanboy-social.txt
# Peter Lowes Ad and tracking server list
https://pgl.yoyo.org/adservers/serverlist.php
# Spam404
https://raw.githubusercontent.com/Dawsey21/Lists/master/adblock-list.txt
# CJX Annoyance List
https://raw.githubusercontent.com/cjx82630/cjxlist/master/cjxlist.txt
# EU: Prebake - Filter Obtrusive Cookie Notices
https://raw.githubusercontent.com/liamja/Prebake/master/obtrusive.txt
# Malvertising filter list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_malvertising.txt
# Malware filter list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_malware.txt
# Basic tracking list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_tracking.txt
# Quidsup NoTrack
https://raw.githubusercontent.com/quidsup/notrack/master/trackers.txt
# Sysctl list (ads)
http://sysctl.org/cameleon/hosts
# KAD host file (fraud/adware) - https://github.com/azet12/KADhosts
https://raw.githubusercontent.com/azet12/KADhosts/master/KADhosts.txt
# Fake news sites
https://raw.githubusercontent.com/marktron/fakenews/master/fakenews
# Dynamic DNS services, sadly often used by malware
http://mirror2.malwaredomains.com/files/dynamic_dns.txt
# Block pornography
https://raw.githubusercontent.com/Clefspeare13/pornhosts/master/0.0.0.0/hosts
https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/pornography-hosts
http://securemecca.com/Downloads/hosts.txt
# Block gambling sites
https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/gambling-hosts
# Block social media sites
# https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/social-hosts

View File

@ -0,0 +1,29 @@
# Local set of patterns to block
ad.*
ads.*
banner.*
banners.*
creatives.*
oas.*
oascentral.*
stats.*
tag.*
telemetry.*
tracker.*
# My Macbook constantly sends a lot of useless queries to *.local,
# so I block them. *.lan is apparently another common one, and
# *.localdomain and *.workgroup are common on Windows.
*.lan
*.local
*.localdomain
*.workgroup
# eth0.me is hardcoded in tools such as Archey, but is not available any
# more, causing issues such as terminal sessions taking a long time to
# start.
eth0.me

View File

@ -0,0 +1,106 @@
##################################################################################
# #
# Generate a black list of domains using public data sources, and the local #
# domains-blacklist-local-additions.txt file. #
# #
# The default configuration is just indicative, and corresponds to the one #
# used to produce the public "mybase" set. #
# #
# Comment out the URLs of the sources you wish to disable, leave the ones #
# you would like enabled uncommented. Then run the script to build the #
# dnscrypt-blacklist-domains.txt file: #
# #
# $ generate-domains-blacklist.py > dnscrypt-blacklist-domains.txt #
# #
# Domains that should never be blocked can be put into a file named #
# domains-whitelist.txt. #
# #
# That blacklist file can then be used in the dnscrypt-proxy configuration: #
# #
# BlackList domains:/etc/dnscrypt-blacklist-domains.txt #
# #
##################################################################################
# Local additions
file:domains-blacklist-local-additions.txt
# Bambenek malware C2s
http://osint.bambenekconsulting.com/feeds/c2-dommasterlist.txt
# hpHosts Ad and tracking servers
http://hosts-file.net/.%5Cad_servers.txt
# Malware domains
http://mirror1.malwaredomains.com/files/justdomains
# Abuse.ch Ransomware Tracker
http://ransomwaretracker.abuse.ch/downloads/RW_DOMBL.txt
# Malware Domain List
http://www.malwaredomainlist.com/mdlcsv.php?inactive=off
# Adblock Warning Removal List
https://easylist-downloads.adblockplus.org/antiadblockfilters.txt
# EasyList
https://easylist-downloads.adblockplus.org/easylist_noelemhide.txt
# EasyList China
https://easylist-downloads.adblockplus.org/easylistchina.txt
# Fanboys Social Blocking List
https://easylist-downloads.adblockplus.org/fanboy-social.txt
# Peter Lowes Ad and tracking server list
https://pgl.yoyo.org/adservers/serverlist.php
# Spam404
https://raw.githubusercontent.com/Dawsey21/Lists/master/adblock-list.txt
# CJX Annoyance List
https://raw.githubusercontent.com/cjx82630/cjxlist/master/cjxlist.txt
# EU: Prebake - Filter Obtrusive Cookie Notices
https://raw.githubusercontent.com/liamja/Prebake/master/obtrusive.txt
# Malvertising filter list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_malvertising.txt
# Malware filter list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_malware.txt
# Basic tracking list by Disconnect
https://s3.amazonaws.com/lists.disconnect.me/simple_tracking.txt
# Sysctl list (ads)
http://sysctl.org/cameleon/hosts
# KAD host file (fraud/adware) - https://github.com/azet12/KADhosts
https://raw.githubusercontent.com/azet12/KADhosts/master/KADhosts.txt
# BarbBlock list (spurious and invalid DMCA takedowns)
https://ssl.bblck.me/blacklists/domain-list.txt
# Dan Pollock's hosts list
http://someonewhocares.org/hosts/hosts
# Websites potentially publishing fake news
# https://raw.githubusercontent.com/marktron/fakenews/master/fakenews
# Quidsup NoTrack - Contains too many false positives to be enabled by default
# https://raw.githubusercontent.com/quidsup/notrack/master/trackers.txt
# Dynamic DNS services, sadly often used by malware
# http://mirror2.malwaredomains.com/files/dynamic_dns.txt
# Block pornography
# https://raw.githubusercontent.com/Clefspeare13/pornhosts/master/0.0.0.0/hosts
# https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/pornography-hosts
# http://securemecca.com/Downloads/hosts.txt
# Block gambling sites
# https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/gambling-hosts
# Block social media sites
# https://raw.githubusercontent.com/Sinfonietta/hostfiles/master/social-hosts

View File

@ -0,0 +1,23 @@
a-msedge.net
amazon.com
appsflyer.com
azurewebsites.net
cdnetworks.com
cloudapp.net
edgekey.net
elasticbeanstalk.com
invalid
j.mp
l-msedge.net
lan
localdomain
microsoft.com
msedge.net
nsatc.net
ovh.net
pusher.com
pusherapp.com
spotify.com
tagcommander.com
tracker.debian.org
windows.net

View File

@ -0,0 +1,140 @@
#! /usr/bin/env python
# run with python generate-domains-blacklist.py > list.txt.tmp && mv -f list.txt.tmp list
import argparse
import re
import sys
import urllib2
def parse_blacklist(content, trusted=False):
rx_comment = re.compile(r'^(#|$)')
rx_inline_comment = re.compile(r'\s*#\s*[a-z0-9-].*$')
rx_u = re.compile(r'^@*\|\|([a-z0-9.-]+[.][a-z]{2,})\^?(\$(popup|third-party))?$')
rx_l = re.compile(r'^([a-z0-9.-]+[.][a-z]{2,})$')
rx_h = re.compile(r'^[0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}\s+([a-z0-9.-]+[.][a-z]{2,})$')
rx_mdl = re.compile(r'^"[^"]+","([a-z0-9.-]+[.][a-z]{2,})",')
rx_b = re.compile(r'^([a-z0-9.-]+[.][a-z]{2,}),.+,[0-9: /-]+,')
rx_trusted = re.compile(r'^([*a-z0-9.-]+)$')
names = set()
rx_set = [rx_u, rx_l, rx_h, rx_mdl, rx_b]
if trusted:
rx_set = [rx_trusted]
for line in content.splitlines():
line = str.lower(str.strip(line))
if rx_comment.match(line):
continue
line = rx_inline_comment.sub('', line)
for rx in rx_set:
matches = rx.match(line)
if not matches:
continue
name = matches.group(1)
names.add(name)
return names
def list_from_url(url):
sys.stderr.write("Loading data from [{}]\n".format(url))
req = urllib2.Request(url)
trusted = False
if req.get_type() == "file":
trusted = True
response = None
try:
response = urllib2.urlopen(req, timeout=10)
except urllib2.URLError as err:
raise Exception("[{}] could not be loaded: {}\n".format(url, err))
if trusted is False and response.getcode() != 200:
raise Exception("[{}] returned HTTP code {}\n".format(url, response.getcode()))
content = response.read()
return parse_blacklist(content, trusted)
def name_cmp(name):
parts = name.split(".")
parts.reverse()
return str.join(".", parts)
def has_suffix(names, name):
parts = str.split(name, ".")
while parts:
parts = parts[1:]
if str.join(".", parts) in names:
return True
return False
def whitelist_from_url(url):
if not url:
return set()
return list_from_url(url)
def blacklists_from_config_file(file, whitelist, ignore_retrieval_failure):
blacklists = {}
all_names = set()
unique_names = set()
if whitelist and not re.match(r'^[a-z0-9]+:', whitelist):
whitelist = "file:" + whitelist
whitelisted_names = whitelist_from_url(whitelist)
with open(file) as fd:
for line in fd:
line = str.strip(line)
if str.startswith(line, "#") or line == "":
continue
url = line
try:
names = list_from_url(url)
blacklists[url] = names
all_names |= names
except Exception as e:
sys.stderr.write(e.message)
if not ignore_retrieval_failure:
exit(1)
for url, names in blacklists.items():
print("\n\n########## Blacklist from {} ##########\n".format(url))
ignored, whitelisted = 0, 0
list_names = list()
for name in names:
if has_suffix(all_names, name) or name in unique_names:
ignored = ignored + 1
elif has_suffix(whitelisted_names, name) or name in whitelisted_names:
whitelisted = whitelisted + 1
else:
list_names.append(name)
unique_names.add(name)
list_names.sort(key=name_cmp)
if ignored:
print("# Ignored duplicates: {}\n".format(ignored))
if whitelisted:
print("# Ignored entries due to the whitelist: {}\n".format(whitelisted))
for name in list_names:
print(name)
argp = argparse.ArgumentParser(description="Create a unified blacklist from a set of local and remote files")
argp.add_argument("-c", "--config", default="domains-blacklist.conf",
help="file containing blacklist sources")
argp.add_argument("-w", "--whitelist", default="domains-whitelist.txt",
help="file containing a set of names to exclude from the blacklist")
argp.add_argument("-i", "--ignore-retrieval-failure", action='store_true',
help="generate list even if some urls couldn't be retrieved")
args = argp.parse_args()
conf = args.config
whitelist = args.whitelist
ignore_retrieval_failure = args.ignore_retrieval_failure
blacklists_from_config_file(conf, whitelist, ignore_retrieval_failure)