# Robots.txt file for globalsourceksa.com

#       .__________________________.
#       | .___________________. |  |
#       | | ................. | |  |
#       | | ::[ Dear Robot ]: | |  |
#       | | ::::[ Be Nice ]:: | |  |
#       | | ::::::::::::::::: | |  |
#       | | ::::::::::::::::: | |  |
#       | | ::::::::::::::::: | |  |
#       | | ::::::::::::::::: | |  |
#       | !___________________! |  |
#       !_______________________!__!
#      /                            \
#     /  [][][][][][][][][][][][][]  \
#    /  [][][][][][][][][][][][][][]  \
#   (  [][][][][____________][][][][]  )
#    \ ------------------------------ /
#     \______________________________/

# General
# -------
User-agent: *
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-includes/
Disallow: /author/
Disallow: /*?author=*
Disallow: /search/
Disallow: /?s=
Disallow: /*?replytocom=
Disallow: /feed/
Disallow: */feed/
Disallow: /comments/feed/
Disallow: /trackback/

# Block WP utility files
# ----------------------
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /readme.html

# Allow access to specific files in wp-admin
# ------------------------------------------
Allow: /wp-admin/admin-ajax.php

# Allow media uploads to be crawled
# ---------------------------------
Allow: /wp-content/uploads/

# Disallow specific file types
# ----------------------------
Disallow: /*.pdf$
Disallow: /*.eot$
Disallow: /*.ttf$
Disallow: /*.woff$
Disallow: /*.woff2$
Disallow: /*.zip$
Disallow: /*.rar$
Disallow: /*.exe$
Disallow: /*.tmp$
Disallow: /*.bak$
Disallow: /*.log$

# Prevent crawling CF challenge URLs
# ----------------------------------
Disallow: /cdn-cgi/bm/cv/
Disallow: /cdn-cgi/challenge-platform/

# Sitemap
# -------
Sitemap: https://www.globalsourceksa.com/sitemap_index.xml

# Allow Known Bots
# -------------
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
User-agent: GPTBot
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Googlebot
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: AI2Bot
User-agent: CCBot
User-agent: Diffbot
User-agent: omgili
User-agent: BingBot
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: LinkedInBot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: cohere-ai
User-agent: TimpiBot
User-agent: ProRataInc
User-agent: YouBot
User-agent: archive.org_bot
User-agent: MistralAI-User
User-agent: PetalBot
Allow: /

# Ban Useless Bots
# ----------------
User-agent: Nuclei
User-agent: WikiDo
User-agent: Riddler
User-agent: PetalBot
User-agent: Zoominfobot
User-agent: Go-http-client
User-agent: Node/simplecrawler
User-agent: CazoodleBot
User-agent: dotbot/1.0
User-agent: Gigabot
User-agent: Barkrowler
User-agent: BLEXBot
User-agent: magpie-crawler
Disallow: /

# Crafted with Care by Hype Funda
# -------------------------------
# At Hype Funda, we take pride in designing and developing websites that 
# truly resonate with our clients' visions. Our latest project showcases 
# our expertise in website design, development, digital marketing, SEO, 
# SMM, PPC, and robust security measures. We are dedicated to creating 
# engaging and effective online experiences that connect businesses with 
# their audiences while ensuring their data is protected. 
#
# To learn more about our services and how we can help elevate your digital 
# presence, visit us at 
#
# https://www.hypefunda.com/
#
# Partner with us to achieve your goals with confidence!
# ------------------------------------------------------
#
#      /$$   /$$                                     /$$$$$$$$                        /$$
#     | $$  | $$                                    | $$_____/                       | $$
#     | $$  | $$ /$$   /$$  /$$$$$$   /$$$$$$       | $$    /$$   /$$ /$$$$$$$   /$$$$$$$  /$$$$$$
#     | $$$$$$$$| $$  | $$ /$$__  $$ /$$__  $$      | $$$$$| $$  | $$| $$__  $$ /$$__  $$ |____  $$
#     | $$__  $$| $$  | $$| $$  \ $$| $$$$$$$$      | $$__/| $$  | $$| $$  \ $$| $$  | $$  /$$$$$$$
#     | $$  | $$| $$  | $$| $$  | $$| $$_____/      | $$   | $$  | $$| $$  | $$| $$  | $$ /$$__  $$
#     | $$  | $$|  $$$$$$$| $$$$$$$/|  $$$$$$$      | $$   |  $$$$$$/| $$  | $$|  $$$$$$$|  $$$$$$$
#     |__/  |__/ \____  $$| $$____/  \_______/      |__/    \______/ |__/  |__/ \_______/ \_______/
#                /$$  | $$| $$                                                                                                         
#               |  $$$$$$/| $$                                                                                                         
#                \______/ |__/
#