chore: remove unused oisd exclusion

.github/workflows/pages.yml

@@ -14,7 +14,7 @@ jobs:
       - name: Install Dependencies
         run: |
           apk update
-          apk add brotli curl git grep jq xmlstarlet zstd
+          apk add brotli curl git grep jq zstd
       - name: Build
         env:
           PHISHTANK_API: ${{ secrets.PHISHTANK_API }}

.gitlab-ci.yml

@@ -12,7 +12,7 @@ build_job:
   stage: build
 
   before_script:
-    - apk update && apk add brotli curl grep jq xmlstarlet zstd
+    - apk update && apk add brotli curl grep jq zstd
 
   script:
     - sh src/script.sh

src/script.sh

@@ -160,20 +160,6 @@ grep -F "." | \
 sed "s/^www\.//g" | \
 sort -u > "top-1m-tranco.txt"
 
-# ## Parse oisd exclusion list
-# cat "oisd-exclude.html" | \
-# # https://stackoverflow.com/a/47600828
-# xmlstarlet format --recover --html 2>/dev/null | \
-# xmlstarlet select --html --template --value-of '//a' | \
-# ## 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"