mirror of
https://git.sr.ht/~seirdy/seirdy.one
synced 2024-12-26 02:22:09 +00:00
61 lines
2.7 KiB
YAML
61 lines
2.7 KiB
YAML
DirectoryPath: "public"
|
|
IgnoreDirs:
|
|
- "search"
|
|
CacheExpires: "48h" # 2 days
|
|
CheckFavicon: true
|
|
EnforceHTML5: true
|
|
IgnoreAltMissing: false
|
|
IgnoreAltEmpty: true # an empty alt makes presentation-role explicit, it's not a defect.
|
|
EnforceHTTPS: true
|
|
ExternalTimeout: 20
|
|
HTTPConcurrencyLimit: 128
|
|
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/"
|
|
- "http://nerdlistings.info/"
|
|
CheckExternal: true
|
|
IgnoreURLs:
|
|
- "../music.txt"
|
|
- "^gemini://"
|
|
- "mailto:"
|
|
- "git@git"
|
|
- "http://[^/]*\\.onion"
|
|
- "https://archive.is"
|
|
- "https://archive.ph"
|
|
- "https://archive.today"
|
|
- "https://ogp.me/ns"
|
|
- "https://seirdy.one/webmentions/"
|
|
- "http://creativecommons.org/ns"
|
|
- "https://seirdy.one/search/"
|
|
- "https://fediring.net/(previous|next)" # redir
|
|
# - "https://forum.palemoon.org/viewtopic.php?f=1&t=25473" # manual check: blocks crawlers
|
|
- "https://forum.palemoon.org/viewtopic.php"
|
|
- "https://queue.acm.org/detail" # manual check: blocks crawlers
|
|
- "https://plausible.io/blog/google-floc#" # manual check: I block this domain
|
|
# - "https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=830173" # manual check: 400 for some reason, using curl works fine.
|
|
- "https://bugs.debian.org/cgi-bin/bugreport.cgi"
|
|
# - "https://forum.kuketz-blog.de/viewtopic.php?p=78202" # manual check: blocks crawlers
|
|
- "https://forum.kuketz-blog.de/viewtopic.php"
|
|
- "https://web.archive.org/" # the wayback machine itself.
|
|
- "https://gitweb.torproject.org/tor-browser.git/tree/browser/components/securitylevel/SecurityLevel.jsm.id=ffdf" # Seems to block htmltest; check manually
|
|
- "https://lnk.dk" # blocks htmltest
|
|
- "https://www.fastcompany.com/90759792/with-google-dominating-search-the-internet-needs-crawl-neutrality" # blocks htmltest
|
|
- "https://faq.whatsapp.com/general/security-and-privacy/answering-your-questions-about-whatsapps-privacy-policy" # my DNS filters block this domain, cbf to work around it just for htmltest
|
|
- "https://doi.org/10.1515/popets-2017-0023" # redirects to a different domain which tends to block requests. DOI is generally good about keeping links alive; it's kinda the point of the service.
|
|
- "https://docs.graycot.dev/s/MFowZsw_F" # DNSSEC issue
|
|
# user has opted out of archiving
|
|
- "https://herd.bovid.space/@garbados"
|
|
OutputDir: "linter-configs/htmltest"
|