relayearly_extractor.sh

#!/bin/sh -e

# https://collector.torproject.org/archive/relay-descriptors/server-descriptors/server-descriptors-YYYY-MM.tar.xz

tar xvJf "$1"
basename=`basename "$1" .tar.xz`

      grep -lr '^router Unnamed (50\.7|204\.45)\.' "$basename" |
xargs grep -l  '^platform Tor 0\.2\.4\.18-rc'    > "$basename.descriptors"

xargs grep -h '^fingerprint ' < "$basename.descriptors" |
cut -d ' ' -f 2- | tr -d ' ' |
sort -u > "$basename.fingerprints"

xargs grep -h '^router ' < "$basename.descriptors" |
cut -d ' '  -f 3 |
sort -u > "$basename.ipaddresses"