From e47195b096ea813b310b73f8b174ded7f1e0c208 Mon Sep 17 00:00:00 2001
From: Austin Burk <apburk@gmail.com>
Date: Wed, 24 Aug 2022 17:32:05 -0400
Subject: [PATCH] gh workflow

---
 .github/workflows/update.yml | 28 ++++++++++++++++++++++++++++
 README.md                    |  2 +-
 2 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100644 .github/workflows/update.yml

diff --git a/.github/workflows/update.yml b/.github/workflows/update.yml
new file mode 100644
index 0000000..2e9e47a
--- /dev/null
+++ b/.github/workflows/update.yml
@@ -0,0 +1,28 @@
+name: Pull latest data from Mojang API
+
+on:
+  push:
+  workflow_dispatch:
+  schedule:
+    - cron:  '25 */6 * * *'
+
+jobs:
+  scheduled:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Check out this repo
+      uses: actions/checkout@v2
+    - name: Fetch latest data
+      run: |-
+        node update_blocklist.js
+    - name: Generate todo.txt
+      run: |-
+        comm -23 <(sort -u data/current.txt) <(awk -F= '{print $1}' data/identified.txt |sort -u) | sort -u > data/todo.txt
+    - name: Commit and push if it changed
+      run: |-
+        git config user.name "Automated"
+        git config user.email "actions@users.noreply.github.com"
+        git add -A
+        timestamp=$(date -u)
+        git commit -m "Blocklist updated: ${timestamp}" || exit 0
+        git push
diff --git a/README.md b/README.md
index 2bf45ee..79f20bb 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@ I figured I'd try to get a more comprehensive list of the domains blocked by Moj
 Get a list of TLDs (idk if this is super up to date)
 
 ```
-curl -s https://raw.githubusercontent.com/umpirsky/tld-list/master/data/en/tld.txt|awk '{print $1}' > tld.txt
+curl -s https://raw.githubusercontent.com/umpirsky/tld-list/master/data/en/tld.txt|grep -Po "\(\K.+?(?=\))" > tld.txt
 ```
 
 Get the middle segment (part before the TLD) of all entries, excluding ddns.net, spit it out as *.string