eulaurarien/export_lists.sh
Geoffrey Frogeye 3b6f7a58b3
Remove support for Rapid7
They changed their privacy / pricing model and as such I don't have
access to their massive DNS dataset anymore,
even after asking.

Since 2022-01-02, I put the list on freeze while looking for an alternative,
but couldn't find any.
To make the list update again with the remaining DNS sources I have,
I put the last version of the list generated with the Rapid7 dataset
as an input for subdomains, that will now get resolved with MassDNS.
2022-11-13 20:10:27 +01:00

99 lines
3.8 KiB
Bash
Executable file

#!/usr/bin/env bash
function log() {
echo -e "\033[33m$@\033[0m"
}
log "Calculating statistics…"
oldest="$(cat last_updates/*.txt | sort -n | head -1)"
oldest_date=$(date -Isec -d @$oldest)
gen_date=$(date -Isec)
gen_software=$(git describe --tags)
number_websites=$(wc -l < temp/all_websites.list)
number_subdomains=$(wc -l < temp/all_subdomains.list)
number_dns=$(grep 'NOERROR' temp/all_resolved.txt | wc -l)
for partyness in {first,multi}
do
if [ $partyness = "first" ]
then
partyness_flags="--first-party"
else
partyness_flags=""
fi
rules_input=$(./export.py --count --base-rules $partyness_flags)
rules_found=$(./export.py --count --rules $partyness_flags)
rules_found_nd=$(./export.py --count --rules --no-dupplicates $partyness_flags)
echo
echo "Statistics for ${partyness}-party trackers"
echo "Input rules: $rules_input"
echo "Subsequent rules: $rules_found"
echo "Subsequent rules (no dupplicate): $rules_found_nd"
echo "Output hostnames: $(./export.py --count $partyness_flags)"
echo "Output hostnames (no dupplicate): $(./export.py --count --no-dupplicates $partyness_flags)"
echo "Output hostnames (end-chain only): $(./export.py --count --end-chain $partyness_flags)"
echo "Output hostnames (no dupplicate, end-chain only): $(./export.py --count --no-dupplicates --end-chain $partyness_flags)"
for trackerness in {trackers,only-trackers}
do
if [ $trackerness = "trackers" ]
then
trackerness_flags=""
else
trackerness_flags="--no-dupplicates"
fi
file_list="dist/${partyness}party-${trackerness}.txt"
file_host="dist/${partyness}party-${trackerness}-hosts.txt"
log "Generating lists for variant ${partyness}-party ${trackerness}"
# Real export heeere
./export.py $partyness_flags $trackerness_flags > $file_list
# Sometimes a bit heavy to have the DB open and sort the output
# so this is done in two steps
sort -u $file_list -o $file_list
rules_output=$(./export.py --count $partyness_flags $trackerness_flags)
(
echo "# First-party trackers host list"
echo "# Variant: ${partyness}-party ${trackerness}"
echo "#"
echo "# About first-party trackers: https://hostfiles.frogeye.fr/#whats-a-first-party-tracker"
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 versions and variants: https://hostfiles.frogeye.fr/#list-variants"
echo "# Source code: https://git.frogeye.fr/geoffrey/eulaurarien"
echo "# License: https://git.frogeye.fr/geoffrey/eulaurarien/src/branch/master/LICENSE"
echo "# Acknowledgements: https://hostfiles.frogeye.fr/#acknowledgements"
echo "#"
echo "# Generation software: eulaurarien $gen_software"
echo "# List generation date: $gen_date"
echo "# Oldest record: $oldest_date"
echo "# Number of source websites: $number_websites"
echo "# Number of source subdomains: $number_subdomains"
echo "# Number of source DNS records: $number_dns"
echo "#"
echo "# Input rules: $rules_input"
echo "# Subsequent rules: $rules_found"
echo "# … no dupplicates: $rules_found_nd"
echo "# Output rules: $rules_output"
echo "#"
echo
sed 's|^|0.0.0.0 |' "$file_list"
) > "$file_host"
done
done
if [ -d explanations ]
then
filename="$(date -Isec).txt"
./export.py --explain > "explanations/$filename"
ln --force --symbolic "$filename" "explanations/latest.txt"
fi