From bb9e8ca7cf3009f51290e96ac0731bda8d181c48 Mon Sep 17 00:00:00 2001
From: curben <2809763-curben@users.noreply.gitlab.com>
Date: Wed, 1 Apr 2020 11:07:54 +0100
Subject: [PATCH] feat: use Tranco list

- replace Cisco Umbrella
- Tranco's ranking method is open-source
  * https://github.com/DistriNet/tranco-list
  * https://tranco-list.eu/
---
 script.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/script.sh b/script.sh
index 33a00bfa..add6cdd5 100644
--- a/script.sh
+++ b/script.sh
@@ -8,7 +8,7 @@ mkdir -p "tmp/" && cd "tmp/"
 
 ## Prepare datasets
 wget "https://urlhaus.abuse.ch/downloads/csv/" -O "urlhaus.zip"
-wget "https://s3-us-west-1.amazonaws.com/umbrella-static/top-1m.csv.zip" -O "top-1m.csv.zip"
+wget "https://tranco-list.eu/top-1m.csv.zip" -O "top-1m.csv.zip"
 
 cp "../src/exclude.txt" "."
 
@@ -49,7 +49,7 @@ cut -f 1 -d ":" | \
 sort -u > "urlhaus-domains-online.txt"
 
 
-## Parse the Cisco Umbrella 1 Million
+## Parse the Tranco 1 Million
 unzip -p "top-1m.csv.zip" | \
 dos2unix | \
 # Parse domains only