From 626f9cd886e898c8a624d5a7ef8829ac28f88340 Mon Sep 17 00:00:00 2001 From: Rohan Kumar Date: Sun, 19 Jun 2022 13:44:51 -0700 Subject: [PATCH] Don't test dead wayback machine links --- linter-configs/htmltest.yml | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/linter-configs/htmltest.yml b/linter-configs/htmltest.yml index 03786e9..8bb5828 100644 --- a/linter-configs/htmltest.yml +++ b/linter-configs/htmltest.yml @@ -1,11 +1,12 @@ DirectoryPath: "public" IgnoreDirs: - "search" -CacheExpires: "48h" +CacheExpires: "72h" # three days CheckFavicon: true EnforceHTML5: true IgnoreAltMissing: true # an empty alt makes presentation-role explicit, it's not a defect. EnforceHTTPS: true +ExternalTimeout: 30 IgnoreHTTPS: - "http://192.168.1" - "http://localhost:" @@ -25,22 +26,23 @@ IgnoreHTTPS: CheckExternal: true IgnoreURLs: - "../music.txt" - - "^gemini://.*" - - "mailto:.*" - - "git@git.*" - - "http://[^/]*.onion.*" - - "https://archive.is.*" - - "https://ogp.me/ns.*" - - "https://seirdy.one/webmentions/.*" - - "http://creativecommons.org/ns.*" - - "https://seirdy.one/search/.*" - - "https://jacky.wtf/.*" # site is down i think + - "^gemini://" + - "mailto:" + - "git@git" + - "http://[^/]*.onion" + - "https://archive.is" + - "https://ogp.me/ns" + - "https://seirdy.one/webmentions/" + - "http://creativecommons.org/ns" + - "https://seirdy.one/search/" + - "https://jacky.wtf/" # site is down i think - "https://fediring.net/(previous|next)" # redir - - "https://forum.palemoon.org/.*" # manual check: blocks crawlers - - "https://queue.acm.org/detail.*" # manual check: blocks crawlers + - "https://forum.palemoon.org/" # manual check: blocks crawlers + - "https://queue.acm.org/detail" # manual check: blocks crawlers - "https://www.geocities.ws/jaup/jaup.htm" # manual check: blocks crawlers - "https://plausible.io/blog/google-floc#" # manual check: I block this domain - "https://twitter.com/" # manual check: 404 for some reason, using curl works fine. - "https://bugs.debian.org/cgi-bin/bugreport.cgi" # manual check: 400 for some reason, using curl works fine. - "https://forum.kuketz-blog.de/" # manual check: blocks crawlers + - "https://web.archive.org/web/0/http" # the wayback machine. OutputDir: "linter-configs/htmltest"