INIT (I swear I will never re-init this repo again)
This commit is contained in:
commit
3db85006cc
105 changed files with 16927 additions and 0 deletions
194
static/robots.txt
Normal file
194
static/robots.txt
Normal file
|
@ -0,0 +1,194 @@
|
|||
User-agent: *
|
||||
Disallow: /index.xml
|
||||
Disallow: /feed.atom
|
||||
Disallow: /categories/
|
||||
Disallow: /categories/*
|
||||
Disallow: /tags/
|
||||
Disallow: /tags/*
|
||||
Disallow: /posts/
|
||||
Disallow: /series/
|
||||
Disallow: /series/*
|
||||
Disallow: /annoucement
|
||||
|
||||
Sitemap: /sitemap.xml
|
||||
|
||||
# Explicitly allow Algolia
|
||||
User-agent: Algolia Crawler
|
||||
Allow: /
|
||||
Disallow: /index.xml
|
||||
Disallow: /feed.atom
|
||||
Disallow: /categories/
|
||||
Disallow: /tags/
|
||||
Disallow: /posts/
|
||||
Disallow: /series/
|
||||
|
||||
User-agent: MJ12bot
|
||||
Disallow: /
|
||||
|
||||
User-agent: AhrefsBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: BLEXBot
|
||||
Disallow: /
|
||||
|
||||
# Block SISTRIX
|
||||
User-agent: SISTRIX Crawler
|
||||
Disallow: /
|
||||
User-agent: sistrix
|
||||
Disallow: /
|
||||
User-agent: 007ac9
|
||||
Disallow: /
|
||||
User-agent: 007ac9 Crawler
|
||||
Disallow: /
|
||||
|
||||
# Block Uptime robot
|
||||
User-agent: UptimeRobot/2.0
|
||||
Disallow: /
|
||||
|
||||
# Block Ezooms Robot
|
||||
User-agent: Ezooms Robot
|
||||
Disallow: /
|
||||
|
||||
# Block Perl LWP
|
||||
User-agent: Perl LWP
|
||||
Disallow: /
|
||||
|
||||
# Block netEstate NE Crawler (+http://www.website-datenbank.de/)
|
||||
User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/)
|
||||
Disallow: /
|
||||
|
||||
# Block WiseGuys Robot
|
||||
User-agent: WiseGuys Robot
|
||||
Disallow: /
|
||||
|
||||
# Block Turnitin Robot
|
||||
User-agent: Turnitin Robot
|
||||
Disallow: /
|
||||
|
||||
# Block Heritrix
|
||||
User-agent: Heritrix
|
||||
Disallow: /
|
||||
|
||||
# Block pricepi
|
||||
User-agent: pimonster
|
||||
Disallow: /
|
||||
|
||||
User-agent: SurdotlyBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: ZoominfoBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: AI2Bot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Ai2Bot-Dolma
|
||||
Disallow: /
|
||||
|
||||
User-agent: Amazonbot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Applebot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Applebot-Extended
|
||||
Disallow: /
|
||||
|
||||
User-agent: Bytespider
|
||||
Disallow: /
|
||||
|
||||
User-agent: CCBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: ChatGPT-User
|
||||
Disallow: /
|
||||
|
||||
User-agent: Claude-Web
|
||||
Disallow: /
|
||||
|
||||
User-agent: ClaudeBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Diffbot
|
||||
Disallow: /
|
||||
|
||||
User-agent: FacebookBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: FriendlyCrawler
|
||||
Disallow: /
|
||||
|
||||
User-agent: GPTBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Google-Extended
|
||||
Disallow: /
|
||||
|
||||
User-agent: GoogleOther
|
||||
Disallow: /
|
||||
|
||||
User-agent: GoogleOther-Image
|
||||
Disallow: /
|
||||
|
||||
User-agent: GoogleOther-Video
|
||||
Disallow: /
|
||||
|
||||
User-agent: ICC-Crawler
|
||||
Disallow: /
|
||||
|
||||
User-agent: ImagesiftBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Meta-ExternalAgent
|
||||
Disallow: /
|
||||
|
||||
User-agent: Meta-ExternalFetcher
|
||||
Disallow: /
|
||||
|
||||
User-agent: OAI-SearchBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: PerplexityBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: PetalBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: Scrapy
|
||||
Disallow: /
|
||||
|
||||
User-agent: Timpibot
|
||||
Disallow: /
|
||||
|
||||
User-agent: VelenPublicWebCrawler
|
||||
Disallow: /
|
||||
|
||||
User-agent: Webzio-Extended
|
||||
Disallow: /
|
||||
|
||||
User-agent: YouBot
|
||||
Disallow: /
|
||||
|
||||
User-agent: anthropic-ai
|
||||
Disallow: /
|
||||
|
||||
User-agent: cohere-ai
|
||||
Disallow: /
|
||||
|
||||
User-agent: facebookexternalhit
|
||||
Disallow: /
|
||||
|
||||
User-agent: iaskspider/2.0
|
||||
Disallow: /
|
||||
|
||||
User-agent: img2dataset
|
||||
Disallow: /
|
||||
|
||||
User-agent: ia_archiver
|
||||
Disallow: /
|
||||
|
||||
User-agent: omgili
|
||||
Disallow: /
|
||||
|
||||
User-agent: omgilibot
|
||||
Disallow: /
|
Loading…
Add table
Add a link
Reference in a new issue