Stop all crawlers.
This commit is contained in:
parent
0a8293f86b
commit
eb7df19d1d
1 changed files with 2 additions and 109 deletions
111
docs/robots.txt
111
docs/robots.txt
|
|
@ -1,111 +1,4 @@
|
||||||
User-agent: Googlebot-Image
|
User-agent: *
|
||||||
User-agent: msnbot-media
|
Disallow: /
|
||||||
User-agent: GPTBot
|
|
||||||
User-agent: CCBot
|
|
||||||
User-agent: ChatGPT-User
|
|
||||||
User-agent: ia-archiver
|
|
||||||
User-agent: omgili
|
|
||||||
User-agent: omgili-bot
|
|
||||||
User-agent: Omgilibot
|
|
||||||
User-agent: img2dataset
|
|
||||||
User-agent: Twitterbot
|
|
||||||
User-agent: Google-Extended
|
|
||||||
User-agent: Applebot-Extended
|
|
||||||
User-agent: anthropic-ai
|
|
||||||
User-agent: Claude-Web
|
|
||||||
User-agent: FacebookBot
|
|
||||||
User-agent: Bytespider
|
|
||||||
User-agent: magpie-crawler
|
|
||||||
User-agent: AI2Bot
|
|
||||||
User-agent: Ai2Bot-Dolma
|
|
||||||
User-agent: Amazonbot
|
|
||||||
User-agent: anthropic-ai
|
|
||||||
User-agent: Applebot
|
|
||||||
User-agent: Applebot-Extended
|
|
||||||
User-agent: Bytespider
|
|
||||||
User-agent: Claude-Web
|
|
||||||
User-agent: ClaudeBot
|
|
||||||
User-agent: cohere-ai
|
|
||||||
User-agent: Diffbot
|
|
||||||
User-agent: DuckAssistBot
|
|
||||||
User-agent: FacebookBot
|
|
||||||
User-agent: FriendlyCrawler
|
|
||||||
User-agent: Google-Extended
|
|
||||||
User-agent: iaskspider/2.0
|
|
||||||
User-agent: ICC-Crawler
|
|
||||||
User-agent: ImagesiftBot
|
|
||||||
User-agent: img2dataset
|
|
||||||
User-agent: ISSCyberRiskCrawler
|
|
||||||
User-agent: Kangaroo Bot
|
|
||||||
User-agent: Meta-ExternalAgent
|
|
||||||
User-agent: Meta-ExternalFetcher
|
|
||||||
User-agent: OAI-SearchBot
|
|
||||||
User-agent: omgili
|
|
||||||
User-agent: omgilibot
|
|
||||||
User-agent: PanguBot
|
|
||||||
User-agent: PerplexityBot
|
|
||||||
User-agent: PetalBot
|
|
||||||
User-agent: Scrapy
|
|
||||||
User-agent: Sidetrade indexer bot
|
|
||||||
User-agent: Timpibot
|
|
||||||
User-agent: VelenPublicWebCrawler
|
|
||||||
User-agent: Webzio-Extended
|
|
||||||
User-agent: YouBot
|
|
||||||
Disallow: /
|
|
||||||
User-Agent: *
|
|
||||||
Disallow: *.txt
|
|
||||||
Disallow: *.pdf
|
|
||||||
Disallow: *.doc
|
|
||||||
Disallow: *.docx
|
|
||||||
Disallow: *.odt
|
|
||||||
Disallow: *.rtf
|
|
||||||
Disallow: *.tex
|
|
||||||
Disallow: *.wks
|
|
||||||
Disallow: *.wpd
|
|
||||||
Disallow: *.wps
|
|
||||||
Disallow: *.html
|
|
||||||
Disallow: *.bmp
|
|
||||||
Disallow: *.gif
|
|
||||||
Disallow: *.ico
|
|
||||||
Disallow: *.jpeg
|
|
||||||
Disallow: *.jpg
|
|
||||||
Disallow: *.png
|
|
||||||
Disallow: *.svg
|
|
||||||
Disallow: *.tif
|
|
||||||
Disallow: *.tiff
|
|
||||||
Disallow: *.webp
|
|
||||||
Disallow: *.aac
|
|
||||||
Disallow: *.aiff
|
|
||||||
Disallow: *.amr
|
|
||||||
Disallow: *.flac
|
|
||||||
Disallow: *.m4a
|
|
||||||
Disallow: *.mp3
|
|
||||||
Disallow: *.oga
|
|
||||||
Disallow: *.opus
|
|
||||||
Disallow: *.wav
|
|
||||||
Disallow: *.wma
|
|
||||||
Disallow: *.mp4
|
|
||||||
Disallow: *.webm
|
|
||||||
Disallow: *.ogg
|
|
||||||
Disallow: *.avi
|
|
||||||
Disallow: *.mov
|
|
||||||
Disallow: *.wmv
|
|
||||||
Disallow: *.flv
|
|
||||||
Disallow: *.mkv
|
|
||||||
Disallow: *.py
|
|
||||||
Disallow: *.js
|
|
||||||
Disallow: *.java
|
|
||||||
Disallow: *.c
|
|
||||||
Disallow: *.cpp
|
|
||||||
Disallow: *.cs
|
|
||||||
Disallow: *.h
|
|
||||||
Disallow: *.css
|
|
||||||
Disallow: *.php
|
|
||||||
Disallow: *.swift
|
|
||||||
Disallow: *.go
|
|
||||||
Disallow: *.rb
|
|
||||||
Disallow: *.pl
|
|
||||||
Disallow: *.sh
|
|
||||||
Disallow: *.sql
|
|
||||||
|
|
||||||
Host: https://gugulet.hu
|
Host: https://gugulet.hu
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue