# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Areas privadas exigem login e nao expoem conteudo indexavel.
User-agent: *
Allow: /

# ---------------------------------------------------------------------------
# A VARIANTE DO TESTE A/B — card wdqp10qbwv.
#
# /para-empresas-varejo e a mesma landing comecando no capitulo dos cinco
# passos. Ela nao pode ser achada por buscador nenhum: nao esta linkada em
# lugar nenhum do site, nao entra no sitemap, e a propria pagina manda
# `noindex, nofollow` na meta.
#
# O Disallow abaixo e a trava que os rastreadores leem ANTES de baixar a
# pagina — e e a unica que vale para os rastreadores de treinamento de IA,
# que nao leem a meta `noai`.
# ---------------------------------------------------------------------------
Disallow: /para-empresas-varejo

# Rastreadores de treinamento e de resposta de IA.
#
# Cada um le o proprio nome; `User-agent: *` acima NAO cobre os que exigem
# bloco proprio (o Google-Extended e o caso classico: ele so obedece a um
# bloco com o nome dele).
User-agent: GPTBot
Disallow: /para-empresas-varejo

User-agent: OAI-SearchBot
Disallow: /para-empresas-varejo

User-agent: ChatGPT-User
Disallow: /para-empresas-varejo

User-agent: ClaudeBot
Disallow: /para-empresas-varejo

User-agent: Claude-Web
Disallow: /para-empresas-varejo

User-agent: anthropic-ai
Disallow: /para-empresas-varejo

User-agent: Google-Extended
Disallow: /para-empresas-varejo

User-agent: CCBot
Disallow: /para-empresas-varejo

User-agent: PerplexityBot
Disallow: /para-empresas-varejo

User-agent: Perplexity-User
Disallow: /para-empresas-varejo

User-agent: Applebot-Extended
Disallow: /para-empresas-varejo

User-agent: Bytespider
Disallow: /para-empresas-varejo

User-agent: Amazonbot
Disallow: /para-empresas-varejo

User-agent: meta-externalagent
Disallow: /para-empresas-varejo

User-agent: FacebookBot
Disallow: /para-empresas-varejo

User-agent: cohere-ai
Disallow: /para-empresas-varejo

User-agent: Diffbot
Disallow: /para-empresas-varejo

User-agent: omgili
Disallow: /para-empresas-varejo

Sitemap: https://yojob.com.br/sitemap.xml