# robots.txt for CoDzisObejrzec.pl
# Optimized for SEO - Updated 2026-07-13

# AI Content Signals (contentsignals.org)
Content-Signal: ai-train=no, search=yes, ai-input=yes

User-agent: *
# Allow everything by default
Allow: /

# ==========================================
# BLOCK WORDPRESS INTERNALS (Critical Fix!)
# ==========================================

# Block WordPress admin and login
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-register.php

# Block WordPress core files
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/wpcf7_uploads/

# Block WordPress utilities
Disallow: /wp-cron.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt

# Block affiliate redirect pages (302 redirects — GSC "strona zawiera przekierowanie")
# X-Robots-Tag: noindex już jest ustawiony w PHP, ale robots.txt zapobiega crawlowaniu
Disallow: /go/

# ==========================================
# BLOCK FEEDS (Critical Fix - Duplicate Content!)
# ==========================================

Disallow: /feed/
Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /*/feed/$
Disallow: /feed/$
Disallow: /*.rss$
Disallow: /rss/

# ==========================================
# BLOCK DUPLICATE CONTENT
# ==========================================

# Block search results
Disallow: /?s=
Disallow: /search/
Disallow: /*/search/

# Archiwa autorow: SKANOWANIE DOZWOLONE, indeksowanie steruje meta robots.
#
# Bylo tu wykluczenie /author/ w trzech blokach (*, Googlebot, Bingbot).
# Search Console raportowal „Strona zindeksowana, ale zablokowana przez plik
# robots.txt" — 15 stron, status walidacji NIEPOWODZENIE (2026-09-09).
#
# To klasyczna sprzecznosc: strony autorow sa linkowane ze stopki kazdego
# wpisu, wiec Google je znajduje i indeksuje z samych linkow — ale przez
# blokade NIE MOZE wejsc i zobaczyc `noindex`. Efekt: zostaja w indeksie bez
# tresci, na zawsze. Wykluczenie w robots.txt nie usuwa z indeksu; usuwa go
# dopiero `noindex`, ktory trzeba Google POKAZAC.
#
# Sterowanie indeksowaniem jest w author.php + filtrze
# rank_math/frontend/robots (zob. coob_is_blog_writer_account()):
#   /author/{seansoholik,kadrowicz,nocnyseans,adminCO}/  index   (68-111 wpisow)
#   pozostale ~40 kont zarejestrowanych userow           noindex (0 wpisow)
# Sprawdzone na zywo 2026-09-09: /author/nocnyseans/ ma `index` i 10 kafli,
# /author/anna/ ma `noindex`.
#
# Koszt: Googlebot przeskanuje raz te ~40 pustych archiwow. Jednorazowo, bo
# potem widzi `noindex`. Zysk: 4 wartosciowe strony autorow moga rankowac,
# a puste wypadaja z indeksu.

# Block date archives
Disallow: /2025/
Disallow: /2026/

# Block tag archives
Disallow: /tag/

# Block attachment pages (single images)
Disallow: /attachment/
Disallow: /*attachment*/

# Block embed pages
Disallow: /embed/
Disallow: /*/embed/

# Block trackback
Disallow: /trackback/
Disallow: /*/trackback/

# ==========================================
# BLOCK URL PARAMETERS (Duplicate Content)
# ==========================================

# Block preview pages
Disallow: /*?preview=
Disallow: /*&preview=

# Block specific post IDs
Disallow: /*?p=*
Disallow: /*&p=*

# Block replytocom (comment replies)
Disallow: /*?replytocom=
Disallow: /*&replytocom=

# Login redirects - NIE blokuj przez robots.txt!
# Google musi móc wejść na te URL-e żeby zobaczyć X-Robots-Tag: noindex
# i usunąć je z indeksu. Blokowanie robots.txt tworzy catch-22.
# Zamiast tego: X-Robots-Tag: noindex serwowany przez PHP (functions.php)
# Disallow: /*?loginSocial=  <-- CELOWO wyłączone
# Disallow: /wp-login.php?*  <-- CELOWO wyłączone

# Block pagination parameters
Disallow: /*?paged=
Disallow: /*&paged=

# Block filter/facet URL parameters (crawl budget — wszystkie kombinacje filtrów)
Disallow: /*?platform=
Disallow: /*&platform=
Disallow: /*?genre=
Disallow: /*&genre=
Disallow: /*?type=
Disallow: /*&type=
Disallow: /*?mood=
Disallow: /*&mood=
Disallow: /*?sort=
Disallow: /*&sort=
Disallow: /*?filter=
Disallow: /*&filter=
Disallow: /*?media_type=
Disallow: /*&media_type=
Disallow: /*?orderby=
Disallow: /*&orderby=
Disallow: /*?wynik=
Disallow: /*&wynik=
Disallow: /*?random=
Disallow: /*&random=

# ==========================================
# BLOCK WRONG URL STRUCTURES (Fix from GSC)
# ==========================================

# Block /movies/ (should be /filmy/ for PL or /en/movies/ for EN)
Disallow: /movies/

# Block best-movies auto-landing pages — 337 stron z noindex, waste crawl budget
# Mają rank_math_robots=noindex ale Google i tak crawluje. robots.txt = hard stop.
# ⚠ WYJATKI DODANE 2026-09-08 — NIE USUWAC BEZ SPRAWDZENIA GSC.
# Blankietowe `Disallow: /best-movies` bylo SLUSZNE dla 330 z 337 stron
# (auto-landing z rank_math_robots=noindex, marnowaly crawl budget), ale
# zabieralo tez 7 stron, ktore noindexa NIE MAJA i realnie rankuja:
# lacznie 1 056 klikniec i 30 444 wyswietlen w GSC (92 dni), w tym
# /best-movies-horror-na-netflix-do-myslenia-2026/ z 867 klikniecami —
# TRZECIA najpopularniejsza strona serwisu. Byly blokowane w robots.txt,
# jednoczesnie zglaszane w page-sitemap.xml i deklarowaly `index, follow`.
# Sprzecznosc potrojna. Allow z dluzszym dopasowaniem wygrywa u Google.
Allow: /best-movies-horror-na-netflix-do-myslenia-2026/
Allow: /best-movies-komedii-na-netflix-2026/
Allow: /best-movies-dokumentalne-na-netflix-do-myslenia-2026/
Allow: /best-movies-horror-na-netflix-2026/
Allow: /best-movies-komedii-na-hbo-max-2026/
Allow: /best-movies-komedii-na-prime-video-2026/
Allow: /best-movies-komedii-na-prime-video-do-myslenia-2026/
Disallow: /best-movies-
Disallow: /best-movies

# /en/main-page/ — valid EN landing page, allowed

# Allow English movie pages (singular /en/movie/ used by some old links)
Allow: /en/movie/
# Block /movie/ without /en/ prefix (redirects to /en/movie/)
Disallow: /movie/

# Block /review/ without /en/ prefix (redirects to /recenzje/)
Disallow: /review/

# Block /reviews/ (non-canonical plural)
Disallow: /reviews/

# ==========================================
# ALLOW IMPORTANT CONTENT
# ==========================================

# Allow main content types
Allow: /filmy/
Allow: /en/movies/
Allow: /recenzje/
Allow: /en/reviews/
Allow: /podobne-do/
Allow: /en/similar-to/
Allow: /trendy/
Allow: /premiery/
Allow: /teraz-w-kinach/
Allow: /nowe-odcinki/
Allow: /filmy-na-wieczor/
Allow: /rankingi/
Allow: /aktualnosci/
Allow: /en/news/
Allow: /blog/
Allow: /swipe/

# Allow English versions
Allow: /en/
Allow: /en/best-movies-*/

# Allow static assets
Allow: /wp-content/themes/*/assets/
Allow: /wp-content/themes/*/assets/css/
Allow: /wp-content/themes/*/assets/js/
Allow: /wp-content/themes/*/assets/images/
Allow: /wp-content/uploads/*.jpg$
Allow: /wp-content/uploads/*.jpeg$
Allow: /wp-content/uploads/*.png$
Allow: /wp-content/uploads/*.gif$
Allow: /wp-content/uploads/*.webp$
Allow: /wp-content/uploads/*.svg$

# ==========================================
# SITEMAP
# ==========================================

Sitemap: https://codzisobejrzec.pl/sitemap_index.xml
Sitemap: https://codzisobejrzec.pl/sitemap.xml

# ==========================================
# SPECIFIC BOT INSTRUCTIONS
# ==========================================

User-agent: Googlebot
Allow: /
# Block affiliate redirects — każdy klik tworzy nowy ?ref=N URL, crawl budget waste
Disallow: /go/
# Block best-movies auto-landing pages (337 stron, noindex, waste crawl budget)
# ⚠ WYJATKI DODANE 2026-09-08 — NIE USUWAC BEZ SPRAWDZENIA GSC.
# Blankietowe `Disallow: /best-movies` bylo SLUSZNE dla 330 z 337 stron
# (auto-landing z rank_math_robots=noindex, marnowaly crawl budget), ale
# zabieralo tez 7 stron, ktore noindexa NIE MAJA i realnie rankuja:
# lacznie 1 056 klikniec i 30 444 wyswietlen w GSC (92 dni), w tym
# /best-movies-horror-na-netflix-do-myslenia-2026/ z 867 klikniecami —
# TRZECIA najpopularniejsza strona serwisu. Byly blokowane w robots.txt,
# jednoczesnie zglaszane w page-sitemap.xml i deklarowaly `index, follow`.
# Sprzecznosc potrojna. Allow z dluzszym dopasowaniem wygrywa u Google.
Allow: /best-movies-horror-na-netflix-do-myslenia-2026/
Allow: /best-movies-komedii-na-netflix-2026/
Allow: /best-movies-dokumentalne-na-netflix-do-myslenia-2026/
Allow: /best-movies-horror-na-netflix-2026/
Allow: /best-movies-komedii-na-hbo-max-2026/
Allow: /best-movies-komedii-na-prime-video-2026/
Allow: /best-movies-komedii-na-prime-video-do-myslenia-2026/
Disallow: /best-movies-
Disallow: /best-movies
# Block thin taxonomy archives
Disallow: /recenzje/gatunek/
Disallow: /recenzje/rok/
# /filmy-na-wieczor/{filter}/ — combo slugs redirect 301 to main page, no block needed.
# Single-genre pages (mystery, horror, komedia) are valid content — allow all.
# Block admin/internals
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
# Block feeds
Disallow: /feed/
Disallow: /*/feed/
# Block duplicate content
Disallow: /?s=
# (/author/ celowo bez wykluczenia — patrz komentarz wyzej)
Disallow: /2025/
Disallow: /2026/
Disallow: /2027/
Disallow: /tag/
Disallow: /*?preview=
Disallow: /*?p=*
# Block filter parameters (1000+ noindexed crawled pages)
Disallow: /*?platform=
Disallow: /*&platform=
Disallow: /*?genre=
Disallow: /*&genre=
Disallow: /*?type=
Disallow: /*&type=
Disallow: /*?media_type=
Disallow: /*&media_type=
Disallow: /*?orderby=
Disallow: /*&orderby=
Disallow: /*?mood=
Disallow: /*&mood=
Disallow: /*?sort=
Disallow: /*&sort=
Disallow: /*?wynik=
Disallow: /*&wynik=
Disallow: /*?random=
Disallow: /*&random=
# Block wrong URL structures
Disallow: /movies/
Disallow: /movie/
Disallow: /review/
Disallow: /reviews/

User-agent: Googlebot-Image
Allow: /wp-content/uploads/

User-agent: Bingbot
Allow: /
# Block best-movies auto-landing pages
# ⚠ WYJATKI DODANE 2026-09-08 — NIE USUWAC BEZ SPRAWDZENIA GSC.
# Blankietowe `Disallow: /best-movies` bylo SLUSZNE dla 330 z 337 stron
# (auto-landing z rank_math_robots=noindex, marnowaly crawl budget), ale
# zabieralo tez 7 stron, ktore noindexa NIE MAJA i realnie rankuja:
# lacznie 1 056 klikniec i 30 444 wyswietlen w GSC (92 dni), w tym
# /best-movies-horror-na-netflix-do-myslenia-2026/ z 867 klikniecami —
# TRZECIA najpopularniejsza strona serwisu. Byly blokowane w robots.txt,
# jednoczesnie zglaszane w page-sitemap.xml i deklarowaly `index, follow`.
# Sprzecznosc potrojna. Allow z dluzszym dopasowaniem wygrywa u Google.
Allow: /best-movies-horror-na-netflix-do-myslenia-2026/
Allow: /best-movies-komedii-na-netflix-2026/
Allow: /best-movies-dokumentalne-na-netflix-do-myslenia-2026/
Allow: /best-movies-horror-na-netflix-2026/
Allow: /best-movies-komedii-na-hbo-max-2026/
Allow: /best-movies-komedii-na-prime-video-2026/
Allow: /best-movies-komedii-na-prime-video-do-myslenia-2026/
Disallow: /best-movies-
Disallow: /best-movies
# Block admin/internals
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
# Block feeds
Disallow: /feed/
Disallow: /*/feed/
# Block duplicate content
Disallow: /?s=
# (/author/ celowo bez wykluczenia — patrz komentarz wyzej)
Disallow: /2025/
Disallow: /2026/
Disallow: /2027/
Disallow: /tag/
Disallow: /*?preview=
Disallow: /*?p=*
# Block filter parameters
Disallow: /*?platform=
Disallow: /*&platform=
Disallow: /*?genre=
Disallow: /*&genre=
Disallow: /*?type=
Disallow: /*&type=
Disallow: /*?media_type=
Disallow: /*&media_type=
Disallow: /*?orderby=
Disallow: /*&orderby=
Disallow: /*?mood=
Disallow: /*&mood=
Disallow: /*?sort=
Disallow: /*&sort=
Disallow: /*?wynik=
Disallow: /*&wynik=
Disallow: /*?random=
Disallow: /*&random=
Disallow: /*?paged=
Disallow: /*&paged=
# Block wrong URL structures
Disallow: /movies/
Disallow: /movie/
Disallow: /review/
Disallow: /reviews/

# ==========================================
# BLOCK BAD BOTS & AI CRAWLERS
# ==========================================

# SEO tool bots (waste bandwidth)
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

# ==========================================
# AI SEARCH BOTS (ALLOW - citations & AI Overviews)
# ==========================================

# ChatGPT-User = bot cytowania w ChatGPT (NIE training) - ALLOW dla widoczności w AI search
User-agent: ChatGPT-User
Allow: /

# OAI-SearchBot = OpenAI search indexer - ALLOW
User-agent: OAI-SearchBot
Allow: /

# Google-Extended = Gemini + AI Overviews - ALLOW dla AI Overviews w Google
User-agent: Google-Extended
Allow: /

# Applebot-Extended = Apple Intelligence - ALLOW
User-agent: Applebot-Extended
Allow: /

# ==========================================
# AI TRAINING BOTS (BLOCK - nie chcemy treningu bez wynagrodzenia)
# ==========================================

User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

# Spam bots
User-agent: spbot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: AhrefsSiteAudit
Disallow: /