# =====================================================================
#  robots.txt — sklepy tulup.*  (na bazie realnego pliku tulup.pl)
#  POPRAWKI vs oryginał:
#   - naprawiony bug: /*$sort -> /*&sort (blokada filtrów jako kolejny param)
#   - AliyunSecBot/Aliyun -> AliyunSecBot ; OI-Crawler/Nutch -> OI-Crawler
#   - usunięte duplikaty (Nicecrawler, Scrapy)
#   - dodany Crawl-delay (spowolnienie "wielorybów": Amazon/meta/Pinterest)
#  Zasada: bot czyta TYLKO swoją grupę User-agent, nie dziedziczy z '*'.
# =====================================================================


# ---------------------------------------------------------------------
# 1) WSZYSCY (w tym Amazon, AmazonProductDiscovery, meta-external*,
#    Pinterest, Google, Bing...) — nie blokujemy, ale spowalniamy
#    i odcinamy ciężkie URL-e (filtry, wyszukiwarka, ajax, uploads).
#    Crawl-delay: 10 -> podnieś do 30 dla ostrzejszego limitu.
# ---------------------------------------------------------------------
User-agent: *
Crawl-delay: 10
Disallow: /order
Disallow: /favourites
Disallow: /ajax
Disallow: /uploads
Disallow: /*search?q
Disallow: /*?sort
Disallow: /*&sort
Disallow: /*?sub
Disallow: /*&sub
Disallow: /*?size
Disallow: /*&size
Disallow: /*?hash
Disallow: /*&hash


# ---------------------------------------------------------------------
# 2) BOTY DO PEŁNEJ BLOKADY (Disallow: /)
#    Wszystkie pod jedną regułą — wiele linii User-agent + jeden Disallow.
# ---------------------------------------------------------------------
User-agent: AI2Bot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: AwarioBot
User-agent: bigsur.ai
User-agent: Bytespider
User-agent: Diffbot
User-agent: FriendlyCrawler
User-agent: ICC-Crawler
User-agent: img2dataset
User-agent: Kangaroo Bot
User-agent: MachineLearningForPeaceBot
User-agent: Meltwater
User-agent: Nicecrawler
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: PiplBot
User-agent: QualifiedBot
User-agent: Scoop.it
User-agent: Seekr
User-agent: Sidetrade indexer bot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: SEOkicks
User-agent: AliyunSecBot
User-agent: OI-Crawler
User-agent: Pandalytics
User-agent: DomainStatsBot
User-agent: BitSightBot
User-agent: Scrapy
User-agent: MJ12bot
User-agent: Barkrowler
User-agent: DotBot
User-agent: BLEXBot
User-agent: serpstatbot
User-agent: XoviOnpageCrawler
User-agent: Screaming Frog SEO Spider
User-agent: Gulper Web Bot
User-agent: WebZIP
User-agent: TurnitinBot
User-agent: SuperBot
User-agent: ScannerBot
Disallow: /