From e5d502a253b2d59025be9075528127f1172bb14e Mon Sep 17 00:00:00 2001 From: arkiver Date: Thu, 31 Mar 2022 02:03:08 +0200 Subject: [PATCH] Also block www.archive.org URLs and web.archive.org --- db/ignore_patterns/global.json | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/db/ignore_patterns/global.json b/db/ignore_patterns/global.json index 5a53abf8..25742938 100644 --- a/db/ignore_patterns/global.json +++ b/db/ignore_patterns/global.json @@ -54,8 +54,9 @@ "^https?://geo\\.yahoo\\.com/b\\?", "^https?://((s-)?static\\.ak\\.fbcdn\\.net|(connect\\.|www\\.)?facebook\\.com)/connect\\.php/js/.*rsrc\\.php", "^https?://www\\.flickr\\.com/change_language\\.gne", - "^https?://archive\\.org/details/", - "^https?://archive\\.org/download/", + "^https?://(www\\.)?archive\\.org/details/", + "^https?://(www\\.)?archive\\.org/download/", + "^https?://web\\.archive\\.org/", "^https?://[^\\.]+\\.us\\.archive\\.org/", "^https?://([^/]+\\.)?archive-it\\.org/", "^https?://archive\\.is/",