Use regex for extracting hosts

.env.example

@@ -1,2 +1,2 @@
-export CLOUDFLARE_ACCOUNT_ID=
+CLOUDFLARE_ACCOUNT_ID=
-export CLOUDFLARE_TOKEN=
+CLOUDFLARE_TOKEN=

.gitignore

@@ -8,3 +8,4 @@ tmp.py
 .venv
 dist/
 .ruff_cache/
+hosts.txt

.vscode/settings.json

@@ -1,4 +1,10 @@
 {
-    "python.languageServer": "Pylance",
+    "python.languageServer": "Pylance", // Ruff is used for linting but Pylance still is useful for intellisense
-    "python.analysis.ignore": [ "*" ] // Ruff is used for linting but Pylance still is useful
+    "python.analysis.ignore": [
+        "*"
+    ],
+    "python.analysis.exclude": [
+        "."
+    ],
+    "python.linting.enabled": false 
 }

src/__main__.py

@@ -102,8 +102,9 @@ def main():
     try:
         args.func(args)
     except AttributeError as e:
-        logger.debug(e)
+        logger.error("No subcommand specified")
         argparser.print_help()
+        exit(1)
 
 
 def upload_to_cloudflare(args):

src/utils/utils.py

@@ -1,5 +1,5 @@
 import pathlib
-
+import re
 import requests
 
 
@@ -53,23 +53,34 @@ class Config:
 # Convert a hosts file to a simple hostname list
 def convert_to_list(file: pathlib.Path) -> list:
     with open(file, "r") as f:
-        # Don't read commented lines; strip whitespace;
+        # Loop through the file and using regex, only get the domain names
-        #  remove 127.0.0.1 from beginning of line;
+        # Remove the prefixed loopback domain and suffixed comments
-        # ignore lines with "localhost"; ignore lines with "::1";
+        # Remove any empty strings
-        # ignore newlines
+        loopback = [
-        hosts = [
+            "localhost",
-            i[10:].strip()
+            "::1",
-            for i in f.readlines()
+            "localhost.localdomain",
-            if not i.startswith("#") and "localhost" not in i and "::1" not in i
+            "broadcasthost",
+            "local",
+            "ip6-localhost",
+            "ip6-loopback",
+            "ip6-localnet",
+            "ip6-mcastprefix",
+            "ip6-allnodes",
+            "ip6-allrouters",
+            "ip6-allhosts",
+            "0.0.0.0",
         ]
-        # Equivalent to:
+        matches = [
-        # for x in f.readlines():
+            re.search(r"^(?:127\.0\.0\.1|0\.0\.0\.0|::1)\s+(.+?)(?:\s+#.+)?$", line)
-        #     if not x.startswith('#') and 'localhost' not in x and '::1' not in x:
+            for line in f
-        #         hosts.append(x[10:].strip())
+        ]
-
+        hosts = [
-        # If there are any empty strings in the list, remove them
+            match.group(1)
-        # For some reason, whitelist seems to still be present
+            for match in matches
-        hosts = [i for i in hosts if i != ""]
+            if match and match.group(1) not in loopback
+        ]
+        print(f"First 5 hosts: {hosts[:5]}")
         return hosts