From 7316f73e80276846c455f0b81ef6a4571168dfb2 Mon Sep 17 00:00:00 2001 From: Jon Barker Date: Tue, 11 Jul 2023 14:59:54 -0700 Subject: [PATCH] Blacklist malicious url in openwebtext --- tools/openwebtext/blacklist_urls.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/openwebtext/blacklist_urls.py b/tools/openwebtext/blacklist_urls.py index bf68840b6d..f54f6617a9 100644 --- a/tools/openwebtext/blacklist_urls.py +++ b/tools/openwebtext/blacklist_urls.py @@ -1,4 +1,6 @@ -# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved. +# Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved. + +# WARNING! This file contains a blacklist of known malicious sites and thus contains some NSFW language. import glob @@ -47,6 +49,7 @@ 'google', 'gunprime', 'gyazo', + 'horsefucker', 'hotdealstar', 'imagefap', 'imageshack',