diff --git a/utils/script.sh b/utils/script.sh index 99803fc0..c7c6a835 100755 --- a/utils/script.sh +++ b/utils/script.sh @@ -25,7 +25,7 @@ cut -f 1 -d ':' | \ # Remove www # Only matches domains that start with www # Not examplewww.com -sed ':a;N;$!ba;s/\nwww\./\n/g' | \ +sed -e ':a' -e 'N' -e '$!ba' -e 's/\nwww\./\n/g' | \ # Sort and remove duplicates sort -u | \ # Exclude Umbrella Top 1M. grep inverse match whole line diff --git a/utils/umbrella-top-1m.sh b/utils/umbrella-top-1m.sh index 904e9085..185c04b5 100755 --- a/utils/umbrella-top-1m.sh +++ b/utils/umbrella-top-1m.sh @@ -16,7 +16,7 @@ cut -f 2 -d ',' | \ # Remove www # Only matches domains that start with www # Not examplewww.com -sed ':a;N;$!ba;s/\nwww\./\n/g' | \ +sed -e ':a' -e 'N' -e '$!ba' -e 's/\nwww\./\n/g' | \ # Remove duplicates sort -u > ../src/top-1m.txt