1
0
Fork 0
mirror of https://git.sr.ht/~seirdy/seirdy.one synced 2024-11-23 21:02:09 +00:00

Don't test dead wayback machine links

This commit is contained in:
Rohan Kumar 2022-06-19 13:44:51 -07:00
parent 93451cfe84
commit 626f9cd886
No known key found for this signature in database
GPG key ID: 1E892DB2A5F84479

View file

@ -1,11 +1,12 @@
DirectoryPath: "public" DirectoryPath: "public"
IgnoreDirs: IgnoreDirs:
- "search" - "search"
CacheExpires: "48h" CacheExpires: "72h" # three days
CheckFavicon: true CheckFavicon: true
EnforceHTML5: true EnforceHTML5: true
IgnoreAltMissing: true # an empty alt makes presentation-role explicit, it's not a defect. IgnoreAltMissing: true # an empty alt makes presentation-role explicit, it's not a defect.
EnforceHTTPS: true EnforceHTTPS: true
ExternalTimeout: 30
IgnoreHTTPS: IgnoreHTTPS:
- "http://192.168.1" - "http://192.168.1"
- "http://localhost:" - "http://localhost:"
@ -25,22 +26,23 @@ IgnoreHTTPS:
CheckExternal: true CheckExternal: true
IgnoreURLs: IgnoreURLs:
- "../music.txt" - "../music.txt"
- "^gemini://.*" - "^gemini://"
- "mailto:.*" - "mailto:"
- "git@git.*" - "git@git"
- "http://[^/]*.onion.*" - "http://[^/]*.onion"
- "https://archive.is.*" - "https://archive.is"
- "https://ogp.me/ns.*" - "https://ogp.me/ns"
- "https://seirdy.one/webmentions/.*" - "https://seirdy.one/webmentions/"
- "http://creativecommons.org/ns.*" - "http://creativecommons.org/ns"
- "https://seirdy.one/search/.*" - "https://seirdy.one/search/"
- "https://jacky.wtf/.*" # site is down i think - "https://jacky.wtf/" # site is down i think
- "https://fediring.net/(previous|next)" # redir - "https://fediring.net/(previous|next)" # redir
- "https://forum.palemoon.org/.*" # manual check: blocks crawlers - "https://forum.palemoon.org/" # manual check: blocks crawlers
- "https://queue.acm.org/detail.*" # 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://www.geocities.ws/jaup/jaup.htm" # manual check: blocks crawlers
- "https://plausible.io/blog/google-floc#" # manual check: I block this domain - "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://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://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://forum.kuketz-blog.de/" # manual check: blocks crawlers
- "https://web.archive.org/web/0/http" # the wayback machine.
OutputDir: "linter-configs/htmltest" OutputDir: "linter-configs/htmltest"