Top Sites>AYOJAKARTA.COM | Menggambarkan Wajah Jakarta Secara Utuh

User-agent: *
Allow: /
Allow: *?page=all
Allow: *?page=1
Allow: *?page=2
Allow: *?page=3

Disallow: *?utm_medium=*
Disallow: *?fbclid=*
Disallow: *?q=*
Disallow: *?page=*
Disallow: */comment
Disallow: /_server-islands/*
Disallow: */topik-khusus.html
Disallow: */topik-khusus-detail.html


Sitemap: https://www.ayojakarta.com/sitemap.xml

    # llms.txt for https://www.ayojakarta.com
    # Last updated: 2025-11-07
    site: https://www.ayojakarta.com
    brand: AyoJakarta.com
    owner: AyoJakarta.com
    contact: alphastackburn@gmail.com
    language: id
    country: ID
    content_focus: Metropolitan, Bodetabek, News, Gaya Hidup, Persija, Bisnis, Khazanah, Sport, Viral, Pendidikan

    policy:
    ai_crawling: allowed
    ai_training: allowed_with_attribution
    ai_derivative_use: allowed_noncommercial
    citation_required: yes
    personal_data_protection: strict
    exclude_user_generated_comments: true

    attribution:
    required_fields:
        - source_title
        - source_url
        - publication_date
        - author_or_editor
    examples:
        - "Sumber: AyoJakarta.com — 'Judul Artikel' ([https://www.ayojakarta.com/slug-artikel](https://www.ayojakarta.com/slug-artikel)), dipublikasikan YYYY-MM-DD."

    rate_limits:
    requests_per_minute: 30
    burst_limit: 60
    concurrent_connections: 4
    respect_robots_txt: true
    cache_min_seconds: 600

    allow:
    - /                    # Homepage
    - /metropolitan/
- /bodetabek/
- /news/
- /gaya-hidup/
- /persija/
- /bisnis/
- /khazanah/
- /sport/
- /viral/
- /pendidikan/
    - /tag/
    - /author/
    - /sitemap.xml
    - /sitemap-web.xml
    - /sitemap-news.xml

    disallow:
    - /_server-islands/
    - /comments/

    structured_data:
    prefer: schema_org
    types:
        - Article
        - NewsArticle
        - Review
    fields_required:
        - headline
        - datePublished
        - dateModified
        - author.name
        - publisher.name
        - mainEntityOfPage
        - image
        - articleSection
        - keywords
    faq: include
    breadcrumbs: include

    feeds:
    - type: sitemap
        url: https://www.ayojakarta.com/sitemap.xml
        update_interval_minutes: 120
    - type: sitemap
        url: https://www.ayojakarta.com/sitemap-web.xml
        update_interval_minutes: 120
    - type: sitemap
        url: https://www.ayojakarta.com/sitemap-news.xml
        update_interval_minutes: 120

    dedupe:
    prefer_canonical_url: true
    canonical_header_hint: true
    ignore_query_params:
        - utm_source
        - utm_medium
        - utm_campaign
        - gclid
        - fbclid

    license:
    content_license: CC BY-NC 4.0
    media_assets: copyrighted
    terms_url: https://www.ayojakarta.com/pedoman
    privacy_url: https://www.ayojakarta.com/privacy
    notes:
        - Teks artikel dapat digunakan non-komersial dengan atribusi.
        - Gambar, video, logo, dan brand assets tidak diizinkan untuk pelatihan/redistribusi.
        - Kutipan harus mematuhi fair use dan tidak menyalin penuh isi artikel.

    rag:
    chunking:
        max_chars_per_chunk: 1800
        overlap_chars: 200
    prioritization:
        - prefer_summary_paragraphs
        - include_tables_specs
        - include_captions_but_do_not_train_images
    include_sections:
        - "Ringkasan"
        - "Inti Berita"
        - "Spesifikasi"
        - "Kesimpulan"
        - "Poin Penting"
    exclude_sections:
        - "Disclaimer"
        - "Hak Cipta"
        - "Penafian"
        - "Tautan Sponsor"

    freshness:
    consider_stale_after_hours: 72
    recheck_on_status_codes:
        - 404
        - 410
        - 301
        - 302
    prefer_lastmod_from_sitemaps: true

    takedown:
    email: alphastackburn@gmail.com
    process:
        - "Sertakan URL dan cuplikan konten yang dipermasalahkan."
        - "Cantumkan alasan hukum atau kebijakan."
        - "Respons maksimal 3 hari kerja."

    security:
    polite_crawl: true
    bot_identification_required: true
    no_auth_bypass: true
    disallow_pi_collection: true
    accept_headers:
        - "User-Agent"
        - "From"
        - "X-Request-Intent"

    # Metadata
    Crawl-delay: 1
    Last-modified: 2025-11-07T04:39:50.071Z
    Version: 1.0

    # Training Guidelines
    Training-Data: allowed
    Commercial-Use: allowed
    Attribution: required
    Modification: allowed
    Distribution: allowed
    Data-Collection-Consent: explicit

    changelog:
    - date: 2025-11-07
        changes:
        - "Initial publication of llms.txt aligned to AyoJakarta.com channels: Metropolitan, Bodetabek, News, Gaya Hidup, Persija, Bisnis, Khazanah, Sport, Viral, Pendidikan."