#
# robots.txt
#
# 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.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html
#
# For syntax checking, see:
# http://www.frobee.com/robots-txt-check

User-agent: *
Crawl-delay: 10
User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg

#Disallow Sogou spider crawling
User-agent: Sogou web spider
Disallow: /
User-agent: sogou spider
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: *
Disallow:

# Directories
Disallow: /core/
Disallow: /profiles/
Disallow: /modules/
Disallow: /themes/
Disallow: /libraries/
# Files
Disallow: /README.txt
Disallow: /web.config
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
Disallow: /5908/ZB_SG/
Disallow: /5908/ZB_CN/
Disallow: /content/
Disallow: /taxonomy/
Disallow: /tags/
Disallow: /api/
Disallow: /story/next_prev/
Disallow: /mysph/
Disallow: /wanbao/
Disallow: /shinmin/
Disallow: /horse-racing/
Disallow: /embed/
Disallow: /media/oembed/
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password/
Disallow: /index.php/user/register/
Disallow: /index.php/user/login/
Disallow: /index.php/user/logout/
# disallow all files ending in specific extension
Disallow: /*.php$
Disallow: /*.pl$
# Disallow mobile app banners.
Disallow: /mobileapp/web-banners

# Allow specific AI crawlers
User-agent: Google-Extended
Allow: /
User-agent: Google-CloudVertexBot
Allow: /
User-agent: Google-Read-Aloud
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: ChatGPT-OpenAI
Allow: /
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: claude-web
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Bingbot
Allow: /
# Optional for Zaobao exploration
User-agent: DeepseekBot
Allow: /
User-agent: Deepseek
Allow: /