From 2e44a10dbfafd5528a3b0319eb6ddeb856e3803b Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Tue, 13 May 2025 09:19:15 +0200 Subject: [PATCH] [fix] engine archlinux: avoid Anubis challenge by User-Agent "SearXNG" Of the archlinux wikis only wiki.archlinux.org has a has Anubis challenge. About Anubis[1]: > Anubis decides to present a challenge using this logic: > > - User-Agent contains "Mozilla" > ... > This should ensure that git clients, RSS readers, and other low-harm clients > can get through without issue .. [1] https://github.com/TecharoHQ/anubis/blob/6c0ff3f4d5e7a66ea85e5873e6ee4c28692091d7/docs/docs/design/how-anubis-works.mdx#challenge-presentation Signed-off-by: Markus Heiser Suggested-by: @unixfox https://github.com/searxng/searxng/issues/4646#issuecomment-2855322406 Closes: https://github.com/searxng/searxng/issues/4646 --- searx/engines/archlinux.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/searx/engines/archlinux.py b/searx/engines/archlinux.py index 820b31799..63de157dc 100644 --- a/searx/engines/archlinux.py +++ b/searx/engines/archlinux.py @@ -51,6 +51,9 @@ def request(query, params): if netloc == main_wiki: eng_lang: str = traits.get_language(sxng_lang, 'English') # type: ignore query += ' (' + eng_lang + ')' + # wiki.archlinux.org is protected by anubis + # - https://github.com/searxng/searxng/issues/4646#issuecomment-2817848019 + params['headers']['User-Agent'] = "SearXNG" elif netloc == 'wiki.archlinuxcn.org': base_url = 'https://' + netloc + '/wzh/index.php?'