# robots.txt automatically generated by PrestaShop e-commerce open-source solution
# https://www.prestashop.com - https://www.prestashop.com/forums
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/robotstxt.html
User-agent: *
# Allow Directives
Allow: */modules/*.css
Allow: */modules/*.js
Allow: */modules/*.png
Allow: */modules/*.jpg
Allow: /js/jquery/*
# Private pages
Disallow: /*?order=
Disallow: /*?tag=
Disallow: /*?id_currency=
Disallow: /*?search_query=
Disallow: /*?back=
Disallow: /*?n=
Disallow: /*&order=
Disallow: /*&tag=
Disallow: /*&id_currency=
Disallow: /*&search_query=
Disallow: /*&back=
Disallow: /*&n=
Disallow: /*controller=addresses
Disallow: /*controller=address
Disallow: /*controller=authentication
Disallow: /*controller=cart
Disallow: /*controller=discount
Disallow: /*controller=footer
Disallow: /*controller=get-file
Disallow: /*controller=header
Disallow: /*controller=history
Disallow: /*controller=identity
Disallow: /*controller=images.inc
Disallow: /*controller=init
Disallow: /*controller=my-account
Disallow: /*controller=order
Disallow: /*controller=order-slip
Disallow: /*controller=order-detail
Disallow: /*controller=order-follow
Disallow: /*controller=order-return
Disallow: /*controller=order-confirmation
Disallow: /*controller=pagination
Disallow: /*controller=password
Disallow: /*controller=pdf-invoice
Disallow: /*controller=pdf-order-return
Disallow: /*controller=pdf-order-slip
Disallow: /*controller=product-sort
Disallow: /*controller=search
Disallow: /*controller=statistics
Disallow: /*controller=attachment
Disallow: /*controller=guest-tracking
# Directories for www.lilweasel.com
Disallow: /app/
Disallow: /cache/
Disallow: /classes/
Disallow: /config/
Disallow: /controllers/
Disallow: /download/
Disallow: /js/
Disallow: /localization/
Disallow: /log/
Disallow: /mails/
Disallow: /modules/
Disallow: /override/
Disallow: /pdf/
Disallow: /src/
Disallow: /tools/
Disallow: /translations/
Disallow: /upload/
Disallow: /var/
Disallow: /vendor/
Disallow: /webservice/
Disallow: /fr/app/
Disallow: /fr/cache/
Disallow: /fr/classes/
Disallow: /fr/config/
Disallow: /fr/controllers/
Disallow: /fr/download/
Disallow: /fr/js/
Disallow: /fr/localization/
Disallow: /fr/log/
Disallow: /fr/mails/
Disallow: /fr/modules/
Disallow: /fr/override/
Disallow: /fr/pdf/
Disallow: /fr/src/
Disallow: /fr/tools/
Disallow: /fr/translations/
Disallow: /fr/upload/
Disallow: /fr/var/
Disallow: /fr/vendor/
Disallow: /fr/webservice/
# Files
Disallow: /*fr/adresse
Disallow: /*fr/adresses
Disallow: /*fr/connexion
Disallow: /*fr/panier
Disallow: /*fr/reduction
Disallow: /*fr/suivi-commande-invite
Disallow: /*fr/historique-commandes
Disallow: /*fr/identite
Disallow: /*fr/mon-compte
Disallow: /*fr/commande
Disallow: /*fr/confirmation-commande
Disallow: /*fr/suivi-commande
Disallow: /*fr/avoirs
Disallow: /*fr/recuperation-mot-de-passe
Disallow: /*fr/recherche
# Various fuckers
User-Agent: peer39_crawler/1.0
Disallow: /
User-agent: barkrowler
Disallow: /
## Microsoft annoyances
User-Agent: AdIdxBot
Disallow: /
User-Agent: BingPreview
Disallow: /
User-Agent: MicrosoftPreview
Disallow: /
## Yandex annoyances
User-Agent: YandexAdNet
Disallow: /
User-Agent: YandexBlogs
Disallow: /
User-Agent: YandexBot
Disallow: /
User-Agent: YandexForDomain
Disallow: /
User-Agent: YandexImages
Disallow: /
User-Agent: YandexResizer
Disallow: /
User-Agent: YandexMarket
Disallow: /
User-Agent: YandexMedia
Disallow: /
User-Agent: YandexNews
Disallow: /
User-Agent: YandexOntoDB
Disallow: /
User-Agent: YandexPagechecker
Disallow: /
User-Agent: YandexSitelinks
Disallow: /
User-Agent: YandexSpravBot
Disallow: /
User-Agent: YandexTurbo
Disallow: /
User-Agent: YandexVertis
Disallow: /
User-Agent: YandexVideo
Disallow: /
User-Agent: YandexWebmaster
Disallow: /
## Random marketing bullshit
User-Agent: AhrefsBot
Disallow: /
User-Agent: AhrefsSiteAudit
Disallow: /
## IP-violation scanners ##
User-Agent: TurnitinBot
Disallow: /
User-Agent: SlySearch
Disallow: /
User-Agent: BLEXBot
Disallow: /
User-agent: CheckMarkNetwork/1.0 (+https://www.checkmarknetwork.com/spider.html)
Disallow: /
User-agent: BrandVerity/1.0
Disallow: /
## Misc. icky stuff ##
User-agent: PiplBot
Disallow: /
# Well-known overly-aggressive bot that claims to respect robots.txt: http://mj12bot.com/
User-agent: MJ12bot
Crawl-Delay: 10
## Gen-AI data scrapers ##
User-agent: Cotoyogi
Disallow: /
User-Agent: GenAI
Disallow: /
User-Agent: SemrushBot-OCOB
Disallow: /
User-Agent: SemrushBot-FT
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Ai2Bot-Dolma
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: anthropic-ai
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: cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: DuckAssistBot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: FriendlyCrawler
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: GoogleOther-Image
Disallow: /
User-agent: GoogleOther-Video
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: iaskspider/2.0
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: ISSCyberRiskCrawler
Disallow: /
User-agent: Kangaroo Bot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: omgili
Disallow: /
User-agent: omgilibot
Disallow: /
User-agent: PanguBot
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: Sidetrade indexer bot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: Webzio-Extended
Disallow: /
User-agent: YouBot
Disallow: /

## Sitemap
Sitemap: https://www.lilweasel.com/1_index_sitemap.xml