# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ============================================
# robots.txt for jmaie.com
# Temporary Email Service - SEO Optimized
# Last Updated: 2025
# ============================================

# Default rules for all crawlers
User-agent: *
Allow: /
Allow: /blog.php
Allow: /bulk.php
Allow: /pages/
Allow: /blog_images_animated/

# Allow language versions
Allow: /*?lang=en
Allow: /*?lang=ar
Allow: /*?lang=hi
Allow: /*?lang=es
Allow: /*?lang=fr
Allow: /*?lang=de
Allow: /*?lang=pt
Allow: /*?lang=ru
Allow: /*?lang=tr
Allow: /*?lang=id
Allow: /*?lang=zh

# Disallow sensitive areas
Disallow: /admin/
Disallow: /api/
Disallow: /api.php
Disallow: /includes/
Disallow: /config.php
Disallow: /install.php
Disallow: /upload.php
Disallow: /tracker.php
Disallow: /blog_track.php
Disallow: /blog_admin.php
Disallow: /cron_publish.php
Disallow: /generate_images.php
Disallow: /db-diagnostic.php
Disallow: /backups/
Disallow: /*.sql$
Disallow: /*.log$
Disallow: /*.zip$

# Block query parameters that create duplicate content
Disallow: /*?demo=*
Disallow: /*?action=*

# ============================================
# Google Bots
# ============================================

# Google AdSense Bot - Full Access
User-agent: Mediapartners-Google
Allow: /

# Google Image Bot
User-agent: Googlebot-Image
Allow: /uploads/
Allow: /blog_images_animated/
Allow: /*.svg$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.webp$

# Google Mobile Bot
User-agent: Googlebot-Mobile
Allow: /

# Google News Bot
User-agent: Googlebot-News
Allow: /blog.php

# ============================================
# Bing Bots
# ============================================

User-agent: Bingbot
Allow: /

User-agent: MSNBot
Allow: /

User-agent: MSNBot-Media
Allow: /uploads/
Allow: /blog_images_animated/

# ============================================
# Other Search Engines
# ============================================

# Yandex
User-agent: Yandex
Allow: /
Crawl-delay: 2

# Baidu
User-agent: Baiduspider
Allow: /
Crawl-delay: 2

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Yahoo
User-agent: Slurp
Allow: /

# ============================================
# Social Media Bots
# ============================================

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterest
Allow: /

User-agent: TelegramBot
Allow: /

# ============================================
# Block Bad Bots & Scrapers
# ============================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SearchmetricsBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# ============================================
# Sitemaps
# ============================================

Sitemap: https://jmaie.com/sitemap.xml
Sitemap: https://jmaie.com/sitemap.php

# ============================================
# Host (for Yandex)
# ============================================

Host: https://jmaie.com