eulaurarien/export_lists.sh

#!/usr/bin/env bash

function log() {
    echo -e "\033[33m$@\033[0m"
}

log "Exporting lists…"
./export.py --first-party --output dist/firstparty-trackers.txt
./export.py --first-party --end-chain --output dist/firstparty-only-trackers.txt
./export.py --output dist/multiparty-trackers.txt
./export.py --end-chain --output dist/multiparty-only-trackers.txt

log "Generating statistics…"
./export.py --count --first-party > temp/count_recs_firstparty.txt
./export.py --count > temp/count_recs_multiparty.txt
./export.py --rules --count --first-party > temp/count_rules_firstparty.txt
./export.py --rules --count > temp/count_rules_multiparty.txt

log "Sorting lists…"
sort -u dist/firstparty-trackers.txt -o dist/firstparty-trackers.txt
sort -u dist/firstparty-only-trackers.txt -o dist/firstparty-only-trackers.txt
sort -u dist/multiparty-trackers.txt -o dist/multiparty-trackers.txt
sort -u dist/multiparty-only-trackers.txt -o dist/multiparty-only-trackers.txt

log "Generating hosts lists…"
function generate_hosts {
    basename="$1"
    description="$2"
    description2="$3"

    (
        echo "# First-party trackers host list"
        echo "# $description"
        echo "# $description2"
        echo "#"
        echo "# About first-party trackers: https://git.frogeye.fr/geoffrey/eulaurarien#whats-a-first-party-tracker"
        echo "# Source code: https://git.frogeye.fr/geoffrey/eulaurarien"
        echo "#"
        echo "# In case of false positives/negatives, or any other question,"
        echo "# contact me the way you like: https://geoffrey.frogeye.fr"
        echo "#"
        echo "# Latest version:"
        echo "# - First-party trackers  : https://hostfiles.frogeye.fr/firstparty-trackers-hosts.txt"
        echo "# - … excluding redirected: https://hostfiles.frogeye.fr/firstparty-only-trackers-hosts.txt"
        echo "# - First and third party : https://hostfiles.frogeye.fr/multiparty-trackers-hosts.txt"
        echo "# - … excluding redirected: https://hostfiles.frogeye.fr/multiparty-only-trackers-hosts.txt"
        echo '# (you can remove `-hosts` to get the raw list)'
        echo "#"
        echo "# Generation date: $(date -Isec)"
        echo "# Generation software: eulaurarien $(git describe --tags)"
        echo "# Number of source websites: $(wc -l temp/all_websites.list | cut -d' ' -f1)"
        echo "# Number of source subdomains: $(wc -l temp/all_subdomains.list | cut -d' ' -f1)"
        echo "# Number of source DNS records: ~2E9 + $(wc -l temp/all_resolved.json | cut -d' ' -f1)" # TODO
        echo "#"
        echo "# Known first-party trackers: $(cat temp/count_rules_firstparty.txt)"
        echo "# Found first-party trackers: $(cat temp/count_recs_firstparty.txt)"
        echo "# Number of first-party hostnames: $(wc -l dist/firstparty-trackers.txt | cut -d' ' -f1)"
        echo "# … excluding redirected: $(wc -l dist/firstparty-only-trackers.txt | cut -d' ' -f1)"
        echo "#"
        echo "# Known multi-party trackers: $(cat temp/count_rules_multiparty.txt)"
        echo "# Found multi-party trackers: $(cat temp/count_recs_multiparty.txt)"
        echo "# Number of multi-party hostnames: $(wc -l dist/multiparty-trackers.txt | cut -d' ' -f1)"
        echo "# … excluding redirected: $(wc -l dist/multiparty-only-trackers.txt | cut -d' ' -f1)"
        echo
        sed 's|^|0.0.0.0 |' "dist/$basename.txt"
    ) > "dist/$basename-hosts.txt"
}

generate_hosts "firstparty-trackers" "Generated from a curated list of first-party trackers" ""
generate_hosts "firstparty-only-trackers" "Generated from a curated list of first-party trackers" "Only contain the first chain of redirection."
generate_hosts "multiparty-trackers" "Generated from known third-party trackers." "Also contains trackers used as third-party."
generate_hosts "multiparty-only-trackers" "Generated from known third-party trackers." "Do not contain trackers used in third-party. Use in combination with third-party lists."