From e32a4039fde59eda1f04807ad078ece66e0ceb9e Mon Sep 17 00:00:00 2001
From: Dnomd343 <i@343.re>
Date: Wed, 28 Sep 2022 17:53:34 +0800
Subject: [PATCH] feat: gfwlist fetch

---
 assets/gfwlist.py | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100755 assets/gfwlist.py

diff --git a/assets/gfwlist.py b/assets/gfwlist.py
new file mode 100755
index 0000000..a089c39
--- /dev/null
+++ b/assets/gfwlist.py
@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import os
+import re
+
+source = [
+    'curl -sL https://github.com/Loukky/gfwlist-by-loukky/raw/master/gfwlist.txt | base64 -d | '
+    'sed \'/^$\\|@@/d\' | sed \'s#!.\\+##;s#|##g;s#@##g;s#http:\\/\\/##;s#https:\\/\\/##;\' | '
+    'sed \'/^[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+$/d\' | grep \'^[0-9a-zA-Z\\.-]\\+$\' | '
+    'grep "\\." | sed \'s#^\\.\\+##\'',
+    'curl -sL https://github.com/gfwlist/gfwlist/raw/master/gfwlist.txt | base64 -d | '
+    'sed \'/^$\\|@@/d\' | sed \'s#!.\\+##;s#|##g;s#@##g;s#http:\\/\\/##;s#https:\\/\\/##;\' | '
+    'sed \'/^[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+$/d\' | grep \'^[0-9a-zA-Z\\.-]\\+$\' | '
+    'grep "\\." | sed \'s#^\\.\\+##\'',
+    'curl -sL https://github.com/hq450/fancyss/raw/master/rules/gfwlist.conf | '
+    'sed \'s/ipset=\\/\\.//g;s/\\/gfwlist//g;/^server/d\'',
+    'curl -sL https://github.com/Loyalsoldier/v2ray-rules-dat/releases/latest/download/gfw.txt',
+]
+
+domains = set()
+for script in source:
+    raw = os.popen(script).read().split('\n')
+    domains.update(filter(None, raw))
+regex = r'^(?=^.{3,255}$)[a-zA-Z0-9][a-zA-Z0-9\-]{0,62}(.[a-zA-Z0-9][a-zA-Z0-9\-]{0,62})+$'
+domains = {x for x in domains if re.search(regex, str(x)) is not None}
+print('\n'.join(sorted(domains)))