From 5a4a8bb9bc55a01d86826b8db3b84cbb0848950a Mon Sep 17 00:00:00 2001
From: MDLeom <2809763-curben@users.noreply.gitlab.com>
Date: Thu, 1 Dec 2022 10:00:32 +0000
Subject: [PATCH] refactor: xmlstarlet -> html-xml-utils

---
 src/script.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/src/script.sh b/src/script.sh
index 24c3be16..bb458b48 100644
--- a/src/script.sh
+++ b/src/script.sh
@@ -173,6 +173,12 @@ sort -u > "top-1m-tranco.txt"
 # ## Append new line https://unix.stackexchange.com/a/31955
 # sed '$a\' > "oisd-exclude.txt"
 
+# # html-xml-utils
+# cat "oisd-exclude.html" | \
+# hxwls | \
+# grep -F '?w=' | \
+# sed 's/^?w=//g' > "oisd-exclude.txt"
+
 # Merge Umbrella, Tranco, Radar and self-maintained top domains
 cat "top-1m-umbrella.txt" "top-1m-tranco.txt" "exclude.txt" | \
 sort -u > "top-1m-well-known.txt"