2019-05-11 09:19:25 +00:00
|
|
|
#!/bin/sh
|
|
|
|
|
|
2019-05-27 05:31:57 +00:00
|
|
|
set -e -x
|
|
|
|
|
|
2019-05-11 09:19:25 +00:00
|
|
|
## Parse popular domains from URLhaus
|
|
|
|
|
|
2019-05-28 00:29:02 +00:00
|
|
|
cat urlhaus.txt | \
|
2019-05-11 09:19:25 +00:00
|
|
|
# Exclude Umbrella Top 1M and well-known domains
|
2019-05-12 03:10:44 +00:00
|
|
|
# grep match whole line
|
2019-05-11 09:19:25 +00:00
|
|
|
grep -Fx -f top-1m-well-known.txt > urlhaus-top-domains.txt
|
