Generates a host list of first-party trackers for ad-blocking.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

52 lines
2.6 KiB

#!/usr/bin/env bash
function log() {
echo -e "\033[33m$@\033[0m"
}
function dl() {
echo "Downloading $1 to $2"
curl --silent "$1" > "$2"
if [ $? -ne 0 ]
then
echo "Failed!"
fi
}
log "Retrieving rules…"
rm -f rules*/*.cache.*
dl https://easylist.to/easylist/easyprivacy.txt rules_adblock/easyprivacy.cache.txt
# From firebog.net Tracking & Telemetry Lists
# dl https://v.firebog.net/hosts/Prigent-Ads.txt rules/prigent-ads.cache.list
# dl https://gitlab.com/quidsup/notrack-blocklists/raw/master/notrack-blocklist.txt rules/notrack-blocklist.cache.list
# False positives: https://github.com/WaLLy3K/wally3k.github.io/issues/73 -> 69.media.tumblr.com chicdn.net
dl https://raw.githubusercontent.com/StevenBlack/hosts/master/data/add.2o7Net/hosts rules_hosts/add2o7.cache.txt
dl https://raw.githubusercontent.com/crazy-max/WindowsSpyBlocker/master/data/hosts/spy.txt rules_hosts/spy.cache.txt
# dl https://raw.githubusercontent.com/Kees1958/WS3_annual_most_used_survey_blocklist/master/w3tech_hostfile.txt rules/w3tech.cache.list
# False positives: agreements.apple.com -> edgekey.net
# dl https://www.github.developerdan.com/hosts/lists/ads-and-tracking-extended.txt rules_hosts/ads-and-tracking-extended.cache.txt # Lots of false-positives
# dl https://raw.githubusercontent.com/Perflyst/PiHoleBlocklist/master/android-tracking.txt rules_hosts/android-tracking.cache.txt
# dl https://raw.githubusercontent.com/Perflyst/PiHoleBlocklist/master/SmartTV.txt rules_hosts/smart-tv.cache.txt
# dl https://raw.githubusercontent.com/Perflyst/PiHoleBlocklist/master/AmazonFireTV.txt rules_hosts/amazon-fire-tv.cache.txt
log "Retrieving TLD list…"
dl http://data.iana.org/TLD/tlds-alpha-by-domain.txt temp/all_tld.temp.list
grep -v '^#' temp/all_tld.temp.list | awk '{print tolower($0)}' > temp/all_tld.list
log "Retrieving nameservers…"
dl https://public-dns.info/nameservers.txt nameservers/public-dns.list
log "Retrieving top subdomains…"
dl http://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip top-1m.csv.zip
unzip top-1m.csv.zip
sed 's|^[0-9]\+,||' top-1m.csv > temp/cisco-umbrella_popularity.fresh.list
rm top-1m.csv top-1m.csv.zip
if [ -f subdomains/cisco-umbrella_popularity.cache.list ]
then
cp subdomains/cisco-umbrella_popularity.cache.list temp/cisco-umbrella_popularity.old.list
pv temp/cisco-umbrella_popularity.old.list temp/cisco-umbrella_popularity.fresh.list | sort -u > subdomains/cisco-umbrella_popularity.cache.list
rm temp/cisco-umbrella_popularity.old.list temp/cisco-umbrella_popularity.fresh.list
else
mv temp/cisco-umbrella_popularity.fresh.list subdomains/cisco-umbrella_popularity.cache.list
fi