# Robots.txt for Password Generator Website
# Optimized configuration for search engine crawling and security
# Last updated: 2025-10-25
# Website: https://dgyy.github.io/Password-Generator/

# ===================================================================
# GLOBAL RULES - Apply to all crawlers
# ===================================================================

User-agent: *
# Allow access to main content areas
Allow: /
Allow: /categories/
Allow: /pages/

# Block sensitive and private areas
Disallow: /clear-history.html
Disallow: /src/
Disallow: /*.draft.html
Disallow: /*.tmp.html
Disallow: /temp/
Disallow: /backup/
Disallow: /_drafts/
Disallow: /_private/
Disallow: /admin/
Disallow: /private/
Disallow: /logs/
Disallow: /cache/

# Block files that shouldn't be indexed
Disallow: /*.json$
Disallow: /*.xml$
Disallow: /*.txt$
Disallow: /sitemap.xml
Disallow: /robots.txt

# Block parameter-based URLs to prevent duplicate content
Disallow: /*?*
Disallow: /*?utm_*
Disallow: /*?source=*
Disallow: /*?ref=*
Disallow: /*?page=*
Disallow: /*?sort=*
Disallow: /*?filter=*

# Block search and utility pages
Disallow: /pages/search.html
Disallow: /pages/404.html
Disallow: /index-optimized.html

# Crawl delay to prevent server overload
Crawl-delay: 1

# ===================================================================
# GOOGLE SPECIFIC CONFIGURATION
# ===================================================================

User-agent: Googlebot
# Allow Googlebot full access to content pages
Allow: /
Allow: /categories/
Allow: /pages/generators/
Allow: /pages/validators/
Allow: /pages/categories/

# Block only sensitive files and directories
Disallow: /src/
Disallow: /clear-history.html
Disallow: /*.draft.html
Disallow: /temp/
Disallow: /backup/

# No crawl delay for Googlebot (it handles rate limiting automatically)
# Crawl-delay: 0

# ===================================================================
# GOOGLE IMAGES CONFIGURATION
# ===================================================================

User-agent: Googlebot-Image
# Allow access to images for image search
Allow: /assets/
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.gif
Allow: /*.svg
Allow: /*.webp

# Block sensitive images
Disallow: /assets/admin/
Disallow: /assets/private/

# ===================================================================
# BING SPECIFIC CONFIGURATION
# ===================================================================

User-agent: Bingbot
# Allow access to main content
Allow: /
Allow: /categories/
Allow: /pages/

# Block sensitive areas
Disallow: /src/
Disallow: /clear-history.html
Disallow: /temp/
Disallow: /backup/
Disallow: /*.draft.html

# Moderate crawl delay for Bing
Crawl-delay: 2

# ===================================================================
# BAIDU SPECIFIC CONFIGURATION
# ===================================================================

User-agent: Baiduspider
# Allow access to main pages
Allow: /
Allow: /categories/
Allow: /pages/generators/
Allow: /pages/validators/

# Block non-Chinese specific content if needed
Disallow: /pages/categories/english-only/

# Longer crawl delay for Baidu
Crawl-delay: 3

# ===================================================================
# YANDEX SPECIFIC CONFIGURATION
# ===================================================================

User-agent: Yandexbot
# Allow access to main content
Allow: /
Allow: /categories/
Allow: /pages/

# Block sensitive areas
Disallow: /src/
Disallow: /clear-history.html
Disallow: /temp/

# Moderate crawl delay
Crawl-delay: 2

# ===================================================================
# SOCIAL MEDIA CRAWLERS
# ===================================================================

User-agent: facebookexternalhit
Allow: /
Allow: /categories/
Allow: /pages/
# Allow social media crawlers to generate rich previews

User-agent: Twitterbot
Allow: /
Allow: /categories/
Allow: /pages/
# Allow Twitter crawler for card generation

# ===================================================================
# PERFORMANCE MONITORING CRAWLERS
# ===================================================================

User-agent: SemrushBot
# Allow limited access for SEO monitoring
Allow: /categories/
Allow: /pages/
Crawl-delay: 5

User-agent: AhrefsBot
# Allow limited access
Allow: /
Crawl-delay: 5

User-agent: MJ12bot
# Block aggressive crawlers
Disallow: /

# ===================================================================
# UNWANTED CRAWLERS - Block completely
# ===================================================================

User-agent: ia_archiver
Disallow: /

User-agent: BacklinkCrawler
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: BUbiNG
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: GrapeshotCrawler
Disallow: /

User-agent: MassDownloader
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: Shopwiki
Disallow: /

User-agent: XenuBot
Disallow: /

# ===================================================================
# SPECIAL DIRECTIVES
# ===================================================================

# Host directive for Russian search engines
Host: https://dgyy.github.io/Password-Generator/

# ===================================================================
# SITEMAP CONFIGURATION
# ===================================================================

# Main sitemap
Sitemap: https://dgyy.github.io/Password-Generator/sitemap.xml

# Additional sitemaps if available (commented out for future use)
# Sitemap: https://dgyy.github.io/Password-Generator/sitemap-generators.xml
# Sitemap: https://dgyy.github.io/Password-Generator/sitemap-validators.xml
# Sitemap: https://dgyy.github.io/Password-Generator/sitemap-categories.xml

# ===================================================================
# END OF ROBOTS.TXT
# ===================================================================

# Notes:
# - This robots.txt is optimized for password generator website
# - Search engines are guided to focus on valuable content
# - Sensitive and duplicate content is protected
# - Crawl delays prevent server overload
# - Social media crawlers can generate rich previews
# - Unwanted crawlers are completely blocked
# - Sitemap location helps search engine discovery
#
# For questions about this configuration, contact: wkrealmadrid@hotmail.com
# Last review: 2025-10-25