2018-10-10 06:25:29 +00:00
|
|
|
#!/bin/sh
|
|
|
|
|
|
|
|
|
|
# Download the Cisco Umbrella 1 Million
|
|
|
|
|
# More info:
|
|
|
|
|
# https://s3-us-west-1.amazonaws.com/umbrella-static/index.html
|
|
|
|
|
|
|
|
|
|
# Download the list
|
2018-10-11 00:53:07 +00:00
|
|
|
wget https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip -O top-1m.csv.zip
|
|
|
|
|
|
2018-10-10 07:48:36 +00:00
|
|
|
# Decompress the zip and write output to stdout
|
2018-10-11 01:49:15 +00:00
|
|
|
unzip -p top-1m.csv.zip | \
|
2018-10-11 03:20:48 +00:00
|
|
|
# Convert DOS to Unix line ending
|
2018-10-11 03:45:59 +00:00
|
|
|
dos2unix | \
|
2018-10-10 06:25:29 +00:00
|
|
|
# Parse domains only
|
2018-10-11 03:20:48 +00:00
|
|
|
cut -f 2 -d ',' | \
|
2018-10-11 03:45:59 +00:00
|
|
|
# Remove www
|
|
|
|
|
# Only matches domains that start with www
|
|
|
|
|
# Not examplewww.com
|
2018-10-11 04:10:18 +00:00
|
|
|
sed -e 's/^www\.//g' | \
|
2018-10-11 03:20:48 +00:00
|
|
|
# Remove duplicates
|
|
|
|
|
sort -u > ../src/top-1m.txt
|
2018-10-11 00:53:07 +00:00
|
|
|
|
|
|
|
|
# Remove downloaded zip file
|
|
|
|
|
rm top-1m.csv.zip
|
