robots.txt was 404ing

This commit is contained in:
chimchooree
2023-05-11 09:13:51 -05:00
parent 7dbbf80e72
commit 2f3a2ecfc1
2 changed files with 80 additions and 0 deletions
+74
View File
@@ -0,0 +1,74 @@
# default
User-agent: *
Allow: /
Disallow: /box/
Disallow: /diary/entries/raw/
# advertising
User-agent: AdsBot-Google*
User-agent: Mediapartners-Google*
Disallow: /
# trouble, referencing https://aardling.com/robots.txt and others
User-agent: AhrefsBot
Disallow: /
User-agent: DOC
Disallow: /
User-agent: Download Ninja
Disallow: /
User-agent: EasouSpider
Disallow: /
User-agent: Exabot
Disallow: /
User-agent: Fetch
Disallow: /
User-agent: grub-client
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: larbin
Disallow: /
User-agent: libwww
Disallow: /
User-agent: linko
Disallow: /
User-agent: Microsoft.URL.Control
Disallow: /
User-agent: MSIECrawler
Disallow: /
User-agent: NPBot
Disallow: /
User-agent: Offline Explorer
Disallow: /
User-agent: sitecheck.internetseer.com
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: Teleport
Disallow: /
User-agent: TeleportPro
Disallow: /
User-agent: UbiCrawler
Disallow: /
User-agent: Vagabondo
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: WebReaper
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebZIP
Disallow: /
User-agent: wget
Disallow: /
User-agent: Xenu
Disallow: /
User-agent: Zao
Disallow: /
User-agent: Zealbot
Disallow: /
User-agent: ZyBORG
Disallow: /
Sitemap: http://www.blessfrey.me/sitemap.xml