From dbe8a5d8693ad0af662970e80c15dc2a5c1ace98 Mon Sep 17 00:00:00 2001 From: Ana Custura Date: Mon, 1 Apr 2024 15:46:55 +0100 Subject: [PATCH] Extract normalised domain names with tldextract --- app/models/mirrors.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/app/models/mirrors.py b/app/models/mirrors.py index db79513..fd1462b 100644 --- a/app/models/mirrors.py +++ b/app/models/mirrors.py @@ -1,4 +1,5 @@ import json +import tldextract from datetime import datetime, timedelta from typing import Optional, List, Union, Any, Dict @@ -55,7 +56,8 @@ class Origin(AbstractConfiguration): @property def normalised_domain_name(self): - return self.domain_name.replace("www.", "") + extracted_domain = tldextract.extract(self.domain_name) + return extracted_domain.registered_domain def onion(self) -> Optional[str]: tld = extract(self.domain_name).registered_domain