seirdy.one/linter-configs/htmltest.yml

DirectoryPath: "public"
IgnoreDirs:
  - "search"
CacheExpires: "168h" # seven days
CheckFavicon: true
EnforceHTML5: true
IgnoreAltMissing: true # an empty alt makes presentation-role explicit, it's not a defect.
EnforceHTTPS: true
ExternalTimeout: 180
HTTPConcurrencyLimit: 96
IgnoreHTTPS:
  - "http://192.168.1"
  - "http://localhost:"
  - "http://wgq3bd2kqoybhstp77i3wrzbfnsyd27wt34psaja4grqiezqircorkyd.onion"
  - "http://bettermotherfuckingwebsite.com/"
  - "http://dtrace.org/"
  - "http://emacspeak.sourceforge.net/"
  - "http://herpolhode.com/"
  - "http://io.netgarage.org/me/"
  - "http://linter.structured-data.org/"
  - "http://optipng.sourceforge.net/"
  - "http://renaissancechambara.jp/"
  - "http://techrights.org/"
  - "http://www.nathanmyhrvold.com/"
  - "http://www.tuxmachines.org/"
  - "http://xmlns.com/"
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
  - "https://fediring.net/(previous|next)" # redir
  - "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"