Top Sites>BR104 - Notícias de Alagoas, Maceió e Interior em tempo real

# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

########################################
# BLOQUEIO ESPECÍFICO DE BOTS/IA/SCRAPERS
# Estes não devem acessar NENHUMA parte do site
########################################

User-agent: anthropic-ai
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

#User-agent: ChatGPT-User
#Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Diffbot
Disallow: /

# IMPORTANTE:
# NÃO vamos bloquear FacebookBot para permitir geração de preview/social

# IMPORTANTE:
# NÃO vamos bloquear nada do Google aqui.
# (Googlebot, Googlebot-News, Google-Extended, etc.)
# Bloquear Google-Extended no robots.txt não deveria matar Discover,
# mas, como seu WAF pode usar essa lista pra dar 403,
# o mais seguro é NÃO colocar o Google-Extended no bloco proibido.
# Assim você evita bloquear sem querer o render do Discover.

#User-agent: GPTBot
#Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: NewsNow
Disallow: /

User-agent: news-please
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: PiplBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: TurnitinBot
Disallow: /


########################################
# REGRAS GERAIS (Google, Bing, etc.)
########################################

User-agent: *
# Bloquear arquivos técnicos e rotas que não devem aparecer no Google
Disallow: /*.jsx$
Disallow: *.jsx$
Disallow: /*.jsx/
Disallow: *.jsx?
Disallow: /ads/
Disallow: /api/
Disallow: /search
Disallow: /busca
Disallow: /?queryId=
Disallow: /*/0

# WordPress internos / rotas sensíveis
Disallow: /wp-admin/
Disallow: /readme.html
Disallow: /license.txt
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-register.php

# Bloqueia as versões /amp/ (se você não quer indexar AMP separado)
Disallow: /*/amp/

# Permitir recursos necessários
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/

########################################
# SITEMAP
########################################
Sitemap: https://www.br104.com.br/sitemap_index.xml
Sitemap: https://www.br104.com.br/sitemap-news.xml/

Not stored for this site.