# config/sources.d/20-transport-logistics-aviation-space.yaml — aviation regulators & bodies, airports, airlines,
# aerospace manufacturers, space agencies & companies, rail & transit, maritime & logistics, road & border agencies.
# Written 2026-09-08. Every sensor below was fetched and parsed with apps/engine/src/validate.ts (OK only).
# Blocked sites (Akamai/Cloudflare/Imperva/Radware 403, client-rendered shells) are recorded in `notes:` rather than
# pretending. Categories: aviation · space · transport · logistics (+ government / industry where relevant).
sources:
  # ───────────────────────── A · Aviation regulators, safety boards & industry bodies ─────────────────────────
  - id: faa
    name: FAA
    domain: faa.gov
    homepage: https://www.faa.gov
    categories: [aviation, government]
    tier: A
    weight: 1.4
    aliases: [federal aviation administration]
    discover: { rss: false }
    notes: "www.faa.gov (newsroom, RSS, robots.txt) is Akamai-protected → 403 for bots. The NAS Status API (nasstatus.faa.gov) is open: ground stops, ground delay programs, airport closures."
    sensors:
      - { name: nas airport status, url: "https://nasstatus.faa.gov/api/airport-status-information", type: XML, connector: http, tier: A }
  - id: easa
    name: EASA
    domain: easa.europa.eu
    homepage: https://www.easa.europa.eu
    categories: [aviation, government]
    tier: B
    weight: 1.3
    aliases: [european union aviation safety agency]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.easa.europa.eu/en/newsroom-and-events/news", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.easa.europa.eu/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxChildren: 12 } }
  - id: icao
    name: ICAO
    domain: icao.int
    homepage: https://www.icao.int
    categories: [aviation, international]
    tier: B
    weight: 1.3
    aliases: [international civil aviation organization]
    discover: { rss: true, sitemap: true }
    notes: "icao.int/news is a client-rendered shell (thin); the Drupal sitemap index is the usable signal."
    sensors:
      - { name: sitemap, url: "https://www.icao.int/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxChildren: 15 } }
  - id: eurocontrol
    name: EUROCONTROL
    domain: eurocontrol.int
    homepage: https://www.eurocontrol.int
    categories: [aviation, international]
    tier: B
    weight: 1.2
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.eurocontrol.int/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }
  - id: uk-caa
    name: UK Civil Aviation Authority
    domain: caa.co.uk
    homepage: https://www.caa.co.uk
    categories: [aviation, government]
    tier: B
    aliases: [uk caa, civil aviation authority]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: gov.uk publications feed, url: "https://www.gov.uk/government/organisations/civil-aviation-authority.atom", type: ATOM, connector: rss, tier: B }
      - { name: newsroom, url: "https://www.caa.co.uk/newsroom/", type: HTML, connector: http, tier: B }
  - id: aaib
    name: Air Accidents Investigation Branch
    domain: gov.uk
    homepage: https://www.gov.uk/government/organisations/air-accidents-investigation-branch
    categories: [aviation, government]
    tier: B
    aliases: [aaib]
    discover: { rss: false }
    sensors:
      - { name: gov.uk feed, url: "https://www.gov.uk/government/organisations/air-accidents-investigation-branch.atom", type: ATOM, connector: rss, tier: B }
  - id: uk-dft
    name: UK Department for Transport
    domain: gov.uk
    homepage: https://www.gov.uk/government/organisations/department-for-transport
    categories: [transport, government]
    tier: B
    aliases: [dft, department for transport]
    discover: { rss: false }
    sensors:
      - { name: gov.uk feed, url: "https://www.gov.uk/government/organisations/department-for-transport.atom", type: ATOM, connector: rss, tier: B }
      - { name: office of rail and road feed, url: "https://www.gov.uk/government/organisations/office-of-rail-and-road.atom", type: ATOM, connector: rss, tier: C }
  - id: ntsb
    name: NTSB
    domain: ntsb.gov
    homepage: https://www.ntsb.gov
    categories: [aviation, transport, government]
    tier: B
    weight: 1.3
    aliases: [national transportation safety board]
    discover: { rss: true }
    sensors:
      - { name: press releases, url: "https://www.ntsb.gov/news/press-releases/Pages/default.aspx", type: HTML, connector: http, tier: B }
      - { name: news and events, url: "https://www.ntsb.gov/news/Pages/default.aspx", type: HTML, connector: http, tier: B }
  - id: bea-aero
    name: BEA (Bureau d'Enquêtes et d'Analyses)
    domain: bea.aero
    homepage: https://bea.aero
    categories: [aviation, government]
    tier: B
    aliases: [bea aero, bureau d'enquêtes et d'analyses]
    discover: { rss: true }
    sensors:
      - { name: notified events, url: "https://bea.aero/en/investigation-reports/notified-events/", type: HTML, connector: http, tier: B }
  - id: tsb-canada
    name: Transportation Safety Board of Canada
    domain: tsb.gc.ca
    homepage: https://www.tsb.gc.ca
    categories: [aviation, transport, government]
    tier: B
    aliases: [tsb, bst, bureau de la sécurité des transports]
    discover: { rss: false }
    notes: "tsb.gc.ca sits behind Azure Application Gateway → 403 for bots (RSS and news pages); no Canada News Centre department id worked (2026-09-08)."
  - id: nav-canada
    name: NAV CANADA
    domain: navcanada.ca
    homepage: https://www.navcanada.ca
    categories: [aviation]
    tier: B
    aliases: [navcanada]
    discover: { rss: false }
    notes: "navcanada.ca returns 403 to bots (Imperva); no feed found (2026-09-08)."
  - id: jcab
    name: Japan Civil Aviation Bureau (MLIT)
    domain: mlit.go.jp
    homepage: https://www.mlit.go.jp/koku/
    categories: [aviation, government]
    tier: C
    aliases: [jcab, mlit koku]
    discover: { rss: true }
    sensors:
      - { name: koku index, url: "https://www.mlit.go.jp/koku/index.html", type: HTML, connector: http, tier: C }
  - id: lba
    name: Luftfahrt-Bundesamt
    domain: lba.de
    homepage: https://www.lba.de
    categories: [aviation, government]
    tier: C
    aliases: [lba]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.lba.de/Sitemap_Index.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: iata
    name: IATA
    domain: iata.org
    homepage: https://www.iata.org
    categories: [aviation, industry]
    tier: B
    weight: 1.3
    aliases: [international air transport association]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: pressroom, url: "https://www.iata.org/en/pressroom/", type: HTML, connector: http, tier: B }
  - id: aci-world
    name: ACI World
    domain: aci.aero
    homepage: https://aci.aero
    categories: [aviation, industry]
    tier: B
    aliases: [airports council international, aci]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://aci.aero/feed/", type: RSS, connector: rss, tier: B }
  - id: airlines-for-america
    name: Airlines for America
    domain: airlines.org
    homepage: https://airlines.org
    categories: [aviation, industry]
    tier: B
    aliases: [a4a]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://airlines.org/feed/", type: RSS, connector: rss, tier: B }
  - id: nbaa
    name: NBAA
    domain: nbaa.org
    homepage: https://nbaa.org
    categories: [aviation, industry]
    tier: C
    aliases: [national business aviation association]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://nbaa.org/feed/", type: RSS, connector: rss, tier: C }
  # ───────────────────────── B · Airports ─────────────────────────
  - id: toronto-pearson
    name: Toronto Pearson (GTAA)
    domain: torontopearson.com
    homepage: https://www.torontopearson.com
    categories: [aviation, transport]
    tier: B
    aliases: [gtaa, yyz, greater toronto airports authority]
    discover: { sitemap: true }
    notes: "News pages are behind a Radware bot captcha; the sitemap is open."
    sensors:
      - { name: sitemap (en), url: "https://www.torontopearson.com/sitemap_yyz_en.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: yyc-calgary
    name: Calgary Airport Authority (YYC)
    domain: yyc.com
    homepage: https://www.yyc.com
    categories: [aviation, transport]
    tier: C
    aliases: [yyc, calgary international airport]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.yyc.com/en-us/SiteMap.aspx", type: SITEMAP, connector: sitemap, tier: C }
  - id: aeroports-de-montreal
    name: Aéroports de Montréal (YUL)
    domain: admtl.com
    homepage: https://www.admtl.com
    categories: [aviation, transport]
    tier: C
    aliases: [adm, yul, montréal-trudeau]
    discover: { sitemap: true }
    notes: "admtl.com (news pages and sitemap) returns 403 (Imperva) to bots (2026-09-08)."
  - id: vancouver-airport
    name: Vancouver Airport Authority (YVR)
    domain: yvr.ca
    homepage: https://www.yvr.ca
    categories: [aviation, transport]
    tier: C
    aliases: [yvr]
    discover: { rss: false }
    notes: "yvr.ca returns 403 (Imperva) to bots (2026-09-08)."
  - id: panynj
    name: Port Authority of New York and New Jersey
    domain: panynj.gov
    homepage: https://www.panynj.gov
    categories: [aviation, transport, logistics]
    tier: B
    aliases: [port authority ny nj, jfk, ewr, lga]
    discover: { sitemap: true }
    notes: "Press-release archive is client-rendered; sitemap is open."
    sensors:
      - { name: sitemap, url: "https://www.panynj.gov/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: lax
    name: Los Angeles World Airports (LAX)
    domain: flylax.com
    homepage: https://www.flylax.com
    categories: [aviation, transport]
    tier: C
    aliases: [lawa, los angeles international airport]
    discover: { rss: false }
    notes: "flylax.com is behind a Cloudflare challenge (2026-09-08)."
  - id: heathrow
    name: Heathrow Airport
    domain: heathrow.com
    homepage: https://www.heathrow.com
    categories: [aviation, transport]
    tier: B
    weight: 1.1
    aliases: [lhr, heathrow airport holdings]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases, url: "https://mediacentre.heathrow.com/pressrelease", type: HTML, connector: http, tier: B }
      - { name: sitemap index, url: "https://www.heathrow.com/sitemap-index.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxChildren: 8, maxUrls: 4000 } }
  - id: groupe-adp
    name: Groupe ADP (Paris Aéroport)
    domain: parisaeroport.fr
    homepage: https://www.parisaeroport.fr
    categories: [aviation, transport]
    tier: C
    aliases: [aéroports de paris, adp, cdg, orly]
    discover: { sitemap: true }
    notes: "presse.groupeadp.fr is bot-blocked (403); the parisaeroport.fr sitemap is open."
    sensors:
      - { name: sitemap, url: "https://www.parisaeroport.fr/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: schiphol
    name: Royal Schiphol Group
    domain: schiphol.nl
    homepage: https://www.schiphol.nl
    categories: [aviation, transport]
    tier: B
    aliases: [amsterdam airport schiphol, ams]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://news.schiphol.com/", type: HTML, connector: http, tier: B }
  - id: fraport
    name: Fraport
    domain: fraport.com
    homepage: https://www.fraport.com
    categories: [aviation, transport]
    tier: B
    aliases: [frankfurt airport, fra]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases, url: "https://www.fraport.com/en/newsroom/pressreleases.html", type: HTML, connector: http, tier: B }
  - id: changi-airport
    name: Changi Airport Group
    domain: changiairport.com
    homepage: https://www.changiairport.com
    categories: [aviation, transport]
    tier: C
    aliases: [sin, singapore changi]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.changiairport.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxUrls: 3000 } }
  - id: hong-kong-airport
    name: Hong Kong International Airport
    domain: hongkongairport.com
    homepage: https://www.hongkongairport.com
    categories: [aviation, transport]
    tier: B
    aliases: [hkia, airport authority hong kong, hkg]
    discover: { rss: true }
    sensors:
      - { name: press releases, url: "https://www.hongkongairport.com/en/media-centre/press-release/", type: HTML, connector: http, tier: B }
  - id: narita-airport
    name: Narita International Airport
    domain: narita-airport.jp
    homepage: https://www.narita-airport.jp
    categories: [aviation, transport]
    tier: C
    aliases: [nrt, naa]
    discover: { rss: true }
    sensors:
      - { name: news, url: "https://www.narita-airport.jp/en/news/", type: HTML, connector: http, tier: C }
  # ───────────────────────── C · Airlines ─────────────────────────
  - id: air-canada
    name: Air Canada
    domain: aircanada.com
    homepage: https://www.aircanada.com
    categories: [aviation, travel]
    tier: B
    weight: 1.2
    aliases: [air canada rouge, aeroplan]
    discover: { rss: true }
    sensors:
      - { name: media newsroom, url: "https://www.aircanada.com/media/", type: HTML, connector: http, tier: B }
      - { name: travel news and updates, url: "https://www.aircanada.com/ca/en/aco/home/book/travel-news-and-updates.html", type: HTML, connector: http, tier: B }
  - id: westjet
    name: WestJet
    domain: westjet.com
    homepage: https://www.westjet.com
    categories: [aviation, travel]
    tier: B
    aliases: [westjet airlines, swoop]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://www.westjet.com/en-ca/news", type: HTML, connector: http, tier: B }
  - id: porter-airlines
    name: Porter Airlines
    domain: flyporter.com
    homepage: https://www.flyporter.com
    categories: [aviation, travel]
    tier: C
    aliases: [porter]
    discover: { rss: false }
    notes: "flyporter.com is behind a Cloudflare challenge (2026-09-08)."
  - id: air-transat
    name: Air Transat
    domain: airtransat.com
    homepage: https://www.airtransat.com
    categories: [aviation, travel]
    tier: C
    aliases: [transat, transat a.t.]
    discover: { sitemap: true }
    notes: "News page is a client-rendered shell; transat.com media room returned 404. Sitemap index is open."
    sensors:
      - { name: sitemap index, url: "https://www.airtransat.com/sitemaps", type: SITEMAP, connector: sitemap, tier: C, config: { maxChildren: 4 } }
  - id: flair-airlines
    name: Flair Airlines
    domain: flyflair.com
    homepage: https://flyflair.com
    categories: [aviation, travel]
    tier: C
    aliases: [flair]
    discover: { rss: false }
    notes: "flyflair.com returns 403 (Imperva) to bots (2026-09-08)."
  - id: delta
    name: Delta Air Lines
    domain: delta.com
    homepage: https://www.delta.com
    categories: [aviation, travel]
    tier: B
    weight: 1.3
    aliases: [delta air lines, delta airlines]
    discover: { rss: true }
    sensors:
      - { name: news hub feed, url: "https://news.delta.com/rss.xml", type: RSS, connector: rss, tier: B }
  - id: united-airlines
    name: United Airlines
    domain: united.com
    homepage: https://www.united.com
    categories: [aviation, travel]
    tier: B
    weight: 1.3
    aliases: [united]
    discover: { rss: false }
    notes: "united.com and hub.united.com (newsroom) time out / block non-browser clients (Akamai); no open feed (2026-09-08)."
  - id: american-airlines
    name: American Airlines
    domain: aa.com
    homepage: https://www.aa.com
    categories: [aviation, travel]
    tier: B
    weight: 1.3
    aliases: [american, american airlines group]
    discover: { rss: false }
    notes: "aa.com and news.aa.com (Q4 newsroom incl. RSS) sit behind a Cloudflare challenge (2026-09-08)."
  - id: southwest
    name: Southwest Airlines
    domain: southwest.com
    homepage: https://www.southwest.com
    categories: [aviation, travel]
    tier: B
    weight: 1.2
    aliases: [southwest airlines]
    discover: { sitemap: true }
    notes: "swamedia.com newsroom is a Salesforce client-rendered app; the investor-relations sitemap is open."
    sensors:
      - { name: investors sitemap, url: "https://investors.southwest.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: jetblue
    name: JetBlue
    domain: jetblue.com
    homepage: https://www.jetblue.com
    categories: [aviation, travel]
    tier: C
    aliases: [jetblue airways]
    discover: { sitemap: true }
    notes: "news.jetblue.com (Q4 newsroom + RSS) is behind a Cloudflare challenge; the CMS sitemap is open."
    sensors:
      - { name: sitemap, url: "https://legacycms.jetblue.com/public/.rest/sitemap/v1/seo/home/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: alaska-airlines
    name: Alaska Airlines
    domain: alaskaair.com
    homepage: https://www.alaskaair.com
    categories: [aviation, travel]
    tier: B
    aliases: [alaska air group, hawaiian airlines]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom feed, url: "https://news.alaskaair.com/feed/", type: RSS, connector: rss, tier: B }
  - id: spirit-airlines
    name: Spirit Airlines
    domain: spirit.com
    homepage: https://www.spirit.com
    categories: [aviation, travel]
    tier: C
    aliases: [spirit]
    discover: { rss: false }
    notes: "spirit.com blocks bots; ir.spirit.com redirects to spiritrestructuring.com (404 on feeds) — 2026-09-08."
  - id: frontier-airlines
    name: Frontier Airlines
    domain: flyfrontier.com
    homepage: https://www.flyfrontier.com
    categories: [aviation, travel]
    tier: C
    aliases: [frontier, frontier group holdings]
    discover: { rss: false }
    notes: "flyfrontier.com serves an 'Unauthorized Activity' interstitial and ir.flyfrontier.com a Cloudflare challenge (2026-09-08)."
  - id: lufthansa-group
    name: Lufthansa Group
    domain: lufthansagroup.com
    homepage: https://www.lufthansagroup.com
    categories: [aviation, travel]
    tier: B
    weight: 1.3
    aliases: [lufthansa, swiss, austrian airlines, brussels airlines, eurowings]
    discover: { rss: true }
    notes: "lufthansagroup.com returns 403 to bots; the Presspage newsroom (newsroom.lufthansagroup.com) is open."
    sensors:
      - { name: newsroom, url: "https://newsroom.lufthansagroup.com/en/", type: HTML, connector: http, tier: B }
  - id: air-france-klm
    name: Air France-KLM
    domain: airfranceklm.com
    homepage: https://www.airfranceklm.com
    categories: [aviation, travel]
    tier: B
    weight: 1.3
    aliases: [air france, klm, afklm, transavia]
    discover: { rss: true }
    notes: "airfranceklm.com and corporate.airfrance.com are behind a Cloudflare challenge; KLM's Presspage newsroom is open."
    sensors:
      - { name: klm newsroom, url: "https://news.klm.com/", type: HTML, connector: http, tier: B }
  - id: iag
    name: International Airlines Group
    domain: iairgroup.com
    homepage: https://www.iairgroup.com
    categories: [aviation, travel]
    tier: C
    weight: 1.2
    aliases: [iag, british airways, iberia, vueling, aer lingus]
    discover: { sitemap: true }
    notes: "iberia.com and ba.com block bots; the IAG corporate sitemap is open."
    sensors:
      - { name: sitemap, url: "https://www.iairgroup.com/xmlsitemap", type: SITEMAP, connector: sitemap, tier: C }
  - id: ryanair
    name: Ryanair
    domain: ryanair.com
    homepage: https://www.ryanair.com
    categories: [aviation, travel]
    tier: B
    weight: 1.2
    aliases: [ryanair holdings]
    discover: { rss: true }
    sensors:
      - { name: corporate news (wp api), url: "https://corporate.ryanair.com/wp-json/wp/v2/posts?per_page=20&_fields=id,date,link,title,excerpt", type: REST_API, connector: jsonlist, tier: B, config: { keyField: id, titleField: title.rendered, urlField: link, dateField: date, summaryField: excerpt.rendered, compareFields: [title.rendered] } }
  - id: easyjet
    name: easyJet
    domain: easyjet.com
    homepage: https://www.easyjet.com
    categories: [aviation, travel]
    tier: C
    weight: 1.1
    discover: { rss: false }
    notes: "easyjet.com and mediacentre.easyjet.com are Akamai-protected (403) — 2026-09-08."
  - id: wizz-air
    name: Wizz Air
    domain: wizzair.com
    homepage: https://wizzair.com
    categories: [aviation, travel]
    tier: C
    aliases: [wizz]
    discover: { sitemap: true }
    notes: "wizzair.com press pages are client-rendered and the sitemap index resolves to empty child maps for bots (2026-09-08)."
  - id: norwegian
    name: Norwegian Air Shuttle
    domain: norwegian.com
    homepage: https://www.norwegian.com
    categories: [aviation, travel]
    tier: C
    aliases: [norwegian air]
    discover: { sitemap: true }
    notes: "media.norwegian.com (Mynewsdesk) shows an 'Are you human?' wall and norwegian.com/sitemap.xml returns 403 on repeat fetches (2026-09-08)."
  - id: sas
    name: SAS Scandinavian Airlines
    domain: sasgroup.net
    homepage: https://www.sasgroup.net
    categories: [aviation, travel]
    tier: C
    aliases: [sas, scandinavian airlines]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases, url: "https://www.sasgroup.net/newsroom/press-releases/", type: HTML, connector: http, tier: C }
  - id: cathay-pacific
    name: Cathay Pacific
    domain: cathaypacific.com
    homepage: https://www.cathaypacific.com
    categories: [aviation, travel]
    tier: B
    aliases: [cathay]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://news.cathaypacific.com/", type: HTML, connector: http, tier: B }
  - id: air-new-zealand
    name: Air New Zealand
    domain: airnewzealand.co.nz
    homepage: https://www.airnewzealand.co.nz
    categories: [aviation, travel]
    tier: C
    aliases: [air nz]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.airnewzealand.com/sitemap/en-nz.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: korean-air
    name: Korean Air
    domain: koreanair.com
    homepage: https://www.koreanair.com
    categories: [aviation, travel]
    tier: B
    aliases: [대한항공, asiana]
    discover: { rss: true }
    sensors:
      - { name: newsroom feed, url: "https://news.koreanair.com/feed/", type: RSS, connector: rss, tier: B }
  - id: ethiopian-airlines
    name: Ethiopian Airlines
    domain: ethiopianairlines.com
    homepage: https://www.ethiopianairlines.com
    categories: [aviation, travel]
    tier: C
    aliases: [ethiopian]
    discover: { rss: true }
    sensors:
      - { name: press releases, url: "https://corporate.ethiopianairlines.com/media/press-release", type: HTML, connector: http, tier: C }
  - id: kenya-airways
    name: Kenya Airways
    domain: kenya-airways.com
    homepage: https://www.kenya-airways.com
    categories: [aviation, travel]
    tier: C
    aliases: [kq]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.kenya-airways.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: airasia
    name: AirAsia (Capital A)
    domain: airasia.com
    homepage: https://www.airasia.com
    categories: [aviation, travel]
    tier: C
    aliases: [capital a, airasia move]
    discover: { rss: true }
    notes: "airasia.com rate-limits bots (Cloudflare 429) and newsroom.airasia.com is a client-rendered shell (thin) — 2026-09-08."
  - id: cebu-pacific
    name: Cebu Pacific
    domain: cebupacificair.com
    homepage: https://www.cebupacificair.com
    categories: [aviation, travel]
    tier: C
    aliases: [cebu pacific air, 5j]
    discover: { rss: true }
    notes: "cebupacificair.com newsroom is a client-rendered shell (thin) — 2026-09-08."
  # ───────────────────────── D · Aerospace & defence manufacturers, eVTOL ─────────────────────────
  - id: boeing
    name: Boeing
    domain: boeing.com
    homepage: https://www.boeing.com
    categories: [aviation, space, industry]
    tier: A
    weight: 1.5
    aliases: [the boeing company]
    products:
      - { name: 737 MAX, type: product, aliases: ["737 max", "737-8", "737-9"] }
      - { name: 787 Dreamliner, type: product, aliases: ["787 dreamliner"] }
      - { name: 777X, type: product }
      - { name: Starliner, type: product }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news releases feed, url: "https://boeing.mediaroom.com/news-releases-statements?pagetemplate=rss", type: RSS, connector: rss, tier: A }
      - { name: news sitemap, url: "https://www.boeing.com/news-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: airbus
    name: Airbus
    domain: airbus.com
    homepage: https://www.airbus.com
    categories: [aviation, space, industry]
    tier: A
    weight: 1.5
    aliases: [airbus se, airbus group]
    products:
      - { name: A320neo, type: product, aliases: [a320neo, a321neo, a321xlr] }
      - { name: A350, type: product }
      - { name: A220, type: product }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.airbus.com/en/rss.xml", type: RSS, connector: rss, tier: A }
  - id: embraer
    name: Embraer
    domain: embraer.com
    homepage: https://embraer.com
    categories: [aviation, industry]
    tier: B
    weight: 1.1
    aliases: [embraer s.a., eve air mobility]
    products:
      - { name: E2 family, type: product, aliases: [e195-e2, e190-e2] }
    discover: { rss: true, sitemap: true }
    notes: "eveairmobility.com (Eve) is Imperva-protected (403); Embraer's own sitemap is open."
    sensors:
      - { name: sitemap, url: "https://embraer.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: bombardier
    name: Bombardier
    domain: bombardier.com
    homepage: https://bombardier.com
    categories: [aviation, industry]
    tier: B
    aliases: [bombardier inc., global 7500, challenger]
    discover: { rss: false }
    notes: "bombardier.com (and Héroux-Devtek) serve an Imperva bot-wall shell (NOINDEX, ~1 KB) to non-browser clients (2026-09-08)."
  - id: heroux-devtek
    name: Héroux-Devtek
    domain: herouxdevtek.com
    homepage: https://www.herouxdevtek.com
    categories: [aviation, industry]
    tier: C
    aliases: [heroux devtek]
    discover: { rss: false }
    notes: "herouxdevtek.com serves an Imperva bot-wall shell to non-browser clients (2026-09-08)."
  - id: general-dynamics
    name: General Dynamics
    domain: gd.com
    homepage: https://www.gd.com
    categories: [aviation, industry]
    tier: B
    weight: 1.1
    aliases: [gulfstream, gulfstream aerospace, gd]
    discover: { rss: true }
    notes: "gulfstreamnews.com returns 403; General Dynamics' corporate press feed covers Gulfstream announcements."
    sensors:
      - { name: press releases feed, url: "https://www.gd.com/feed.xml", type: RSS, connector: rss, tier: B }
  - id: dassault-aviation
    name: Dassault Aviation
    domain: dassault-aviation.com
    homepage: https://www.dassault-aviation.com
    categories: [aviation, industry]
    tier: B
    aliases: [dassault, falcon, rafale]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed (en), url: "https://www.dassault-aviation.com/en/feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 30 } }
  - id: textron-aviation
    name: Textron Aviation
    domain: txtav.com
    homepage: https://txtav.com
    categories: [aviation, industry]
    tier: B
    aliases: [cessna, beechcraft, textron]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://media.txtav.com/", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://txtav.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: rtx
    name: RTX (Pratt & Whitney, Collins Aerospace, Raytheon)
    domain: rtx.com
    homepage: https://www.rtx.com
    categories: [aviation, industry]
    tier: B
    weight: 1.3
    aliases: [raytheon technologies, pratt & whitney, pratt and whitney, collins aerospace, raytheon]
    products:
      - { name: PW1100G GTF, type: product, aliases: [gtf, geared turbofan, pw1100g] }
    discover: { rss: true, sitemap: true }
    notes: "prattwhitney.com and collinsaerospace.com newsrooms are behind a Cloudflare challenge; rtx.com is open."
    sensors:
      - { name: news, url: "https://www.rtx.com/news", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.rtx.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: ge-aerospace
    name: GE Aerospace
    domain: geaerospace.com
    homepage: https://www.geaerospace.com
    categories: [aviation, industry]
    tier: B
    weight: 1.3
    aliases: [ge aviation, cfm international, leap engine]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.geaerospace.com/news/rss.xml", type: RSS, connector: rss, tier: B }
  - id: rolls-royce
    name: Rolls-Royce Holdings
    domain: rolls-royce.com
    homepage: https://www.rolls-royce.com
    categories: [aviation, industry]
    tier: B
    weight: 1.2
    aliases: [rolls royce, trent xwb]
    discover: { rss: false }
    notes: "rolls-royce.com is Imperva-protected (403 for bots) — 2026-09-08."
  - id: safran
    name: Safran
    domain: safran-group.com
    homepage: https://www.safran-group.com
    categories: [aviation, industry]
    tier: B
    weight: 1.2
    discover: { rss: true }
    sensors:
      - { name: pressroom, url: "https://www.safran-group.com/pressroom", type: HTML, connector: http, tier: B }
  - id: cae
    name: CAE
    domain: cae.com
    homepage: https://www.cae.com
    categories: [aviation, industry]
    tier: B
    aliases: [cae inc.]
    discover: { rss: true, sitemap: true }
    notes: "cae.com sitemaps (news.xml, sitemap.xml) answer 200 once then 403 on repeat fetches (bot management) — 2026-09-08."
  - id: honeywell-aerospace
    name: Honeywell Aerospace
    domain: honeywellaerospace.com
    homepage: https://aerospace.honeywell.com
    categories: [aviation, industry]
    tier: C
    aliases: [honeywell]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://www.honeywellaerospace.com/us/en/company/newsroom", type: HTML, connector: http, tier: C }
  - id: thales
    name: Thales
    domain: thalesgroup.com
    homepage: https://www.thalesgroup.com
    categories: [aviation, space, industry]
    tier: B
    weight: 1.2
    aliases: [thales group, thales alenia space]
    discover: { rss: true, sitemap: true }
    notes: "thalesgroup.com (rss.xml, sitemap) answers once then switches to a 403/302 bot challenge on repeat fetches (2026-09-08); no stable sensor kept."
  - id: leonardo
    name: Leonardo
    domain: leonardo.com
    homepage: https://www.leonardo.com
    categories: [aviation, space, industry]
    tier: C
    aliases: [leonardo s.p.a., agustawestland, telespazio]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap (en), url: "https://www.leonardo.com/sitemap_EN.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: saab
    name: Saab
    domain: saab.com
    homepage: https://www.saab.com
    categories: [aviation, industry]
    tier: B
    aliases: [saab ab, gripen]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases, url: "https://www.saab.com/newsroom/press-releases", type: HTML, connector: http, tier: B }
  - id: lockheed-martin
    name: Lockheed Martin
    domain: lockheedmartin.com
    homepage: https://www.lockheedmartin.com
    categories: [aviation, space, industry]
    tier: B
    weight: 1.3
    aliases: [lockheed, f-35, skunk works]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news releases feed, url: "https://news.lockheedmartin.com/news-releases?pagetemplate=rss", type: RSS, connector: rss, tier: B }
      - { name: sitemap (en-us), url: "https://www.lockheedmartin.com/sitemap-en-us.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: northrop-grumman
    name: Northrop Grumman
    domain: northropgrumman.com
    homepage: https://www.northropgrumman.com
    categories: [aviation, space, industry]
    tier: B
    weight: 1.2
    aliases: [northrop, b-21 raider]
    discover: { rss: true, sitemap: true }
    notes: "news.northropgrumman.com is a Next.js shell (RSS endpoints 403 on Vercel, HTML nearly empty); the corporate sitemap is open."
    sensors:
      - { name: sitemap, url: "https://www.northropgrumman.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: l3harris
    name: L3Harris Technologies
    domain: l3harris.com
    homepage: https://www.l3harris.com
    categories: [aviation, space, industry]
    tier: B
    aliases: [l3harris, aerojet rocketdyne]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom feed, url: "https://www.l3harris.com/feeds/newsroom/rss.xml?rid=12281", type: RSS, connector: rss, tier: B, config: { maxItems: 60 } }
  - id: bae-systems
    name: BAE Systems
    domain: baesystems.com
    homepage: https://www.baesystems.com
    categories: [aviation, industry]
    tier: B
    weight: 1.1
    aliases: [bae]
    discover: { rss: false }
    notes: "baesystems.com serves an Imperva bot-wall (403) to non-browser clients (2026-09-08)."
  - id: joby-aviation
    name: Joby Aviation
    domain: jobyaviation.com
    homepage: https://www.jobyaviation.com
    categories: [aviation, technology]
    tier: B
    aliases: [joby, evtol]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.jobyaviation.com/news", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.jobyaviation.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: archer-aviation
    name: Archer Aviation
    domain: archer.com
    homepage: https://archer.com
    categories: [aviation, technology]
    tier: C
    aliases: [archer, midnight evtol]
    discover: { sitemap: true }
    notes: "archer.com/news is a client-rendered app and investors.archer.com (Q4 RSS) is behind a Cloudflare challenge; sitemap index is open."
    sensors:
      - { name: sitemap index, url: "https://archer.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: wisk-aero
    name: Wisk Aero
    domain: wisk.aero
    homepage: https://wisk.aero
    categories: [aviation, technology]
    tier: C
    aliases: [wisk]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://wisk.aero/newsroom", type: HTML, connector: http, tier: C }
  - id: beta-technologies
    name: BETA Technologies
    domain: beta.team
    homepage: https://beta.team
    categories: [aviation, technology]
    tier: C
    aliases: [beta, alia]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news stories, url: "https://beta.team/stories", type: HTML, connector: http, tier: C }
  - id: vertical-aerospace
    name: Vertical Aerospace
    domain: vertical-aerospace.com
    homepage: https://vertical-aerospace.com
    categories: [aviation, technology]
    tier: C
    aliases: [vx4]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://vertical-aerospace.com/news/feed/", type: RSS, connector: rss, tier: C }
  # ───────────────────────── E · Space agencies, launch & satellite companies ─────────────────────────
  - id: the-space-devs
    name: The Space Devs (Launch Library 2)
    domain: thespacedevs.com
    homepage: https://thespacedevs.com
    categories: [space, open-data]
    tier: B
    weight: 1.2
    aliases: [launch library, launch library 2, ll2]
    products:
      - { name: Launch Library 2 API, type: API, aliases: [ll2 api] }
    discover: { rss: false }
    llm: false
    notes: "Community-maintained launch manifest (net = no-earlier-than); free tier ~15 req/h, so tier B only, never S/A."
    sensors:
      - { name: upcoming launches, url: "https://ll.thespacedevs.com/2.2.0/launch/upcoming/?limit=30&mode=list", type: REST_API, connector: jsonlist, tier: B, config: { itemsPath: results, keyField: id, titleField: name, dateField: net, summaryField: status.name, compareFields: [net, status.name], urlTemplate: "https://ll.thespacedevs.com/2.2.0/launch/{key}/" } }
  - id: spacex
    name: SpaceX
    domain: spacex.com
    homepage: https://www.spacex.com
    categories: [space, technology]
    tier: A
    weight: 1.5
    aliases: [space exploration technologies, starship, falcon 9, starlink]
    products:
      - { name: Starship, type: product }
      - { name: Falcon 9, type: product, aliases: [falcon heavy] }
      - { name: Starlink, type: service }
    discover: { rss: false }
    notes: "spacex.com (updates, launches) is a ~3 KB client-rendered shell with no feed or API; launches are covered by the Launch Library sensor (the-space-devs)."
  - id: blue-origin
    name: Blue Origin
    domain: blueorigin.com
    homepage: https://www.blueorigin.com
    categories: [space, technology]
    tier: B
    weight: 1.2
    aliases: [new glenn, new shepard, blue moon]
    discover: { rss: false }
    notes: "blueorigin.com/news answers 429 (Vercel rate-limit) to non-browser clients — 2026-09-08."
  - id: rocket-lab
    name: Rocket Lab
    domain: rocketlabcorp.com
    homepage: https://rocketlabcorp.com
    categories: [space, technology]
    tier: B
    weight: 1.2
    aliases: [rocket lab usa, electron, neutron]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: updates, url: "https://rocketlabcorp.com/updates/", type: HTML, connector: http, tier: B }
  - id: ula
    name: United Launch Alliance
    domain: ulalaunch.com
    homepage: https://www.ulalaunch.com
    categories: [space, industry]
    tier: B
    aliases: [ula, vulcan centaur, atlas v]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.ulalaunch.com/about/news", type: HTML, connector: http, tier: B }
  - id: arianespace
    name: Arianespace
    domain: arianespace.com
    homepage: https://www.arianespace.com
    categories: [space, industry]
    tier: B
    weight: 1.1
    aliases: [ariane 6, vega c, arianegroup]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news sitemap, url: "https://www.arianespace.com/news-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: firefly-aerospace
    name: Firefly Aerospace
    domain: fireflyspace.com
    homepage: https://fireflyspace.com
    categories: [space, technology]
    tier: B
    aliases: [firefly, alpha rocket, blue ghost]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://fireflyspace.com/news/feed/", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }
  - id: relativity-space
    name: Relativity Space
    domain: relativityspace.com
    homepage: https://www.relativityspace.com
    categories: [space, technology]
    tier: C
    aliases: [terran r]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.relativityspace.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: stoke-space
    name: Stoke Space
    domain: stokespace.com
    homepage: https://www.stokespace.com
    categories: [space, technology]
    tier: C
    aliases: [nova rocket]
    discover: { rss: true }
    sensors:
      - { name: news, url: "https://www.stokespace.com/news", type: HTML, connector: http, tier: C }
  - id: sierra-space
    name: Sierra Space
    domain: sierraspace.com
    homepage: https://www.sierraspace.com
    categories: [space, technology]
    tier: B
    aliases: [dream chaser, life habitat]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.sierraspace.com/feed/", type: RSS, connector: rss, tier: B }
  - id: axiom-space
    name: Axiom Space
    domain: axiomspace.com
    homepage: https://axiomspace.com
    categories: [space, technology]
    tier: B
    aliases: [axiom station, axiom mission]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://axiomspace.com/news/rss.xml", type: RSS, connector: rss, tier: B }
  - id: vast
    name: Vast
    domain: vastspace.com
    homepage: https://www.vastspace.com
    categories: [space, technology]
    tier: C
    aliases: [vast space, haven-1]
    discover: { rss: true }
    sensors:
      - { name: updates, url: "https://www.vastspace.com/updates", type: HTML, connector: http, tier: C }
  - id: planet-labs
    name: Planet Labs
    domain: planet.com
    homepage: https://www.planet.com
    categories: [space, technology]
    tier: B
    aliases: [planet, planetscope, skysat]
    discover: { rss: true, sitemap: true }
    notes: "investors.planet.com (Q4 RSS) is behind a Cloudflare challenge; the Pulse blog and sitemap are open."
    sensors:
      - { name: pulse blog, url: "https://www.planet.com/pulse/", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.planet.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: maxar
    name: Maxar (Vantor)
    domain: maxar.com
    homepage: https://vantor.com
    categories: [space, technology]
    tier: C
    aliases: [vantor, maxar intelligence, maxar technologies, worldview legion]
    discover: { rss: false }
    notes: "maxar.com now redirects to vantor.com (rebrand); the Nuxt site ships 2+ MB pages with no feed and /news is 404 — no sensor kept (2026-09-08)."
  - id: blacksky
    name: BlackSky
    domain: blacksky.com
    homepage: https://blacksky.com
    categories: [space, technology]
    tier: C
    discover: { sitemap: true }
    sensors:
      - { name: sitemap index, url: "https://blacksky.com/sitemap_index.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: iridium
    name: Iridium Communications
    domain: iridium.com
    homepage: https://www.iridium.com
    categories: [space, telecom]
    tier: C
    aliases: [iridium]
    discover: { rss: false }
    notes: "iridium.com returns 403 to bots and investor.iridium.com has no RSS (2026-09-08)."
  - id: viasat
    name: Viasat
    domain: viasat.com
    homepage: https://www.viasat.com
    categories: [space, telecom]
    tier: B
    aliases: [inmarsat]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: latest news, url: "https://www.viasat.com/news/latest-news/", type: HTML, connector: http, tier: B }
  - id: telesat
    name: Telesat
    domain: telesat.com
    homepage: https://www.telesat.com
    categories: [space, telecom]
    tier: B
    aliases: [telesat lightspeed]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press, url: "https://www.telesat.com/press/", type: HTML, connector: http, tier: B }
  - id: mda-space
    name: MDA Space
    domain: mda.space
    homepage: https://mda.space
    categories: [space, technology]
    tier: B
    weight: 1.1
    aliases: [mda, canadarm3, mda ltd]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news releases, url: "https://mda.space/news", type: HTML, connector: http, tier: B }
  - id: ghgsat
    name: GHGSat
    domain: ghgsat.com
    homepage: https://www.ghgsat.com
    categories: [space, climate]
    tier: C
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: resources and news, url: "https://www.ghgsat.com/resources/", type: HTML, connector: http, tier: C }
  - id: northstar
    name: NorthStar Earth & Space
    domain: northstar-data.com
    homepage: https://northstar-data.com
    categories: [space, technology]
    tier: C
    aliases: [northstar earth and space]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://northstar-data.com/feed/", type: RSS, connector: rss, tier: C }
  - id: isro
    name: ISRO
    domain: isro.gov.in
    homepage: https://www.isro.gov.in
    categories: [space, government]
    tier: B
    weight: 1.3
    aliases: [indian space research organisation, gaganyaan, chandrayaan]
    discover: { rss: true }
    sensors:
      - { name: press, url: "https://www.isro.gov.in/Press.html", type: HTML, connector: http, tier: B }
  - id: jaxa
    name: JAXA
    domain: jaxa.jp
    homepage: https://global.jaxa.jp
    categories: [space, government]
    tier: B
    weight: 1.3
    aliases: [japan aerospace exploration agency, h3 rocket]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://global.jaxa.jp/rss/press.rdf", type: RSS, connector: rss, tier: B }
      - { name: what's new, url: "https://global.jaxa.jp/news/", type: HTML, connector: http, tier: B }
  - id: cnes
    name: CNES
    domain: cnes.fr
    homepage: https://cnes.fr
    categories: [space, government]
    tier: B
    weight: 1.2
    aliases: [centre national d'études spatiales]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://cnes.fr/rss/news", type: RSS, connector: rss, tier: B, config: { maxItems: 60 } }
  - id: dlr
    name: DLR
    domain: dlr.de
    homepage: https://www.dlr.de
    categories: [space, aviation, research]
    tier: B
    weight: 1.1
    aliases: [deutsches zentrum für luft- und raumfahrt, german aerospace center]
    discover: { rss: true, sitemap: true }
    notes: "dlr.de/en/latest/news is a React app (the /rss path returns the same HTML); the sitemap index is open."
    sensors:
      - { name: sitemap index, url: "https://www.dlr.de/sitemap-index.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxChildren: 12, maxUrls: 4000 } }
  - id: asi
    name: ASI (Agenzia Spaziale Italiana)
    domain: asi.it
    homepage: https://www.asi.it
    categories: [space, government]
    tier: C
    aliases: [italian space agency, agenzia spaziale italiana]
    discover: { rss: true }
    sensors:
      - { name: news feed (en), url: "https://www.asi.it/en/feed/", type: RSS, connector: rss, tier: C }
  - id: uk-space-agency
    name: UK Space Agency
    domain: gov.uk
    homepage: https://www.gov.uk/government/organisations/uk-space-agency
    categories: [space, government]
    tier: B
    aliases: [uksa]
    discover: { rss: false }
    sensors:
      - { name: gov.uk feed, url: "https://www.gov.uk/government/organisations/uk-space-agency.atom", type: ATOM, connector: rss, tier: B }
  - id: canadian-space-agency
    name: Canadian Space Agency
    domain: asc-csa.gc.ca
    homepage: https://www.asc-csa.gc.ca
    categories: [space, government]
    tier: B
    weight: 1.1
    aliases: [csa, asc, agence spatiale canadienne]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.asc-csa.gc.ca/eng/news/", type: HTML, connector: http, tier: B }
      - { name: sitemap (pages), url: "https://www.asc-csa.gc.ca/sitemaps/sitemap-pages.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: kasa
    name: Korea AeroSpace Administration
    domain: kasa.go.kr
    homepage: https://www.kasa.go.kr
    categories: [space, government]
    tier: C
    aliases: [kasa, kari, korea aerospace research institute]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.kasa.go.kr/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: roscosmos
    name: Roscosmos
    domain: roscosmos.ru
    homepage: https://www.roscosmos.ru
    categories: [space, government]
    tier: C
    aliases: [роскосмос]
    discover: { rss: false }
    notes: "No feed, sitemap or server-rendered index found on roscosmos.ru (2026-09-08)."
  - id: eumetsat
    name: EUMETSAT
    domain: eumetsat.int
    homepage: https://www.eumetsat.int
    categories: [space, weather, international]
    tier: B
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.eumetsat.int/news/feed", type: RSS, connector: rss, tier: B, config: { maxItems: 60 } }
  - id: euspa
    name: EUSPA
    domain: euspa.europa.eu
    homepage: https://www.euspa.europa.eu
    categories: [space, government]
    tier: B
    aliases: [eu agency for the space programme, galileo, copernicus, egnos]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.euspa.europa.eu/rss.xml", type: RSS, connector: rss, tier: B }
  - id: space-foundation
    name: Space Foundation
    domain: spacefoundation.org
    homepage: https://www.spacefoundation.org
    categories: [space, ngo]
    tier: C
    aliases: [space symposium]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.spacefoundation.org/feed/", type: RSS, connector: rss, tier: C }
  - id: secure-world-foundation
    name: Secure World Foundation
    domain: swfound.org
    homepage: https://www.swfound.org
    categories: [space, ngo]
    tier: C
    aliases: [swf]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.swfound.org/news", type: HTML, connector: http, tier: C }
  - id: planetary-society
    name: The Planetary Society
    domain: planetary.org
    homepage: https://www.planetary.org
    categories: [space, ngo]
    tier: C
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: articles, url: "https://www.planetary.org/articles", type: HTML, connector: http, tier: C }
  # ───────────────────────── F · Rail & transit ─────────────────────────
  - id: amtrak
    name: Amtrak
    domain: amtrak.com
    homepage: https://www.amtrak.com
    categories: [transport]
    tier: B
    weight: 1.1
    aliases: [national railroad passenger corporation, acela]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: media feed, url: "https://media.amtrak.com/feed/", type: RSS, connector: rss, tier: B }
  - id: via-rail
    name: VIA Rail Canada
    domain: viarail.ca
    homepage: https://www.viarail.ca
    categories: [transport]
    tier: B
    aliases: [via rail, via]
    discover: { rss: true }
    sensors:
      - { name: press releases, url: "https://media.viarail.ca/en/press-releases", type: HTML, connector: http, tier: B }
  - id: cn-rail
    name: CN (Canadian National Railway)
    domain: cn.ca
    homepage: https://www.cn.ca
    categories: [transport, logistics]
    tier: B
    weight: 1.2
    aliases: [cn, canadian national]
    discover: { rss: true }
    sensors:
      - { name: media, url: "https://www.cn.ca/en/media/", type: HTML, connector: http, tier: B }
  - id: cpkc
    name: CPKC
    domain: cpkcr.com
    homepage: https://www.cpkcr.com
    categories: [transport, logistics]
    tier: B
    weight: 1.1
    aliases: [canadian pacific kansas city, canadian pacific, cp rail]
    discover: { rss: false }
    notes: "cpkcr.com times out for non-browser clients and investor.cpkcr.com (Q4 RSS) is behind a Cloudflare challenge (2026-09-08)."
  - id: union-pacific
    name: Union Pacific
    domain: up.com
    homepage: https://www.up.com
    categories: [transport, logistics]
    tier: B
    weight: 1.1
    aliases: [up, union pacific railroad]
    discover: { rss: true }
    sensors:
      - { name: press releases, url: "https://www.up.com/press-releases", type: HTML, connector: http, tier: B }
  - id: bnsf
    name: BNSF Railway
    domain: bnsf.com
    homepage: https://www.bnsf.com
    categories: [transport, logistics]
    tier: B
    aliases: [bnsf, burlington northern santa fe]
    discover: { rss: true }
    sensors:
      - { name: news and media, url: "https://www.bnsf.com/news-media/index.page", type: HTML, connector: http, tier: B }
  - id: csx
    name: CSX
    domain: csx.com
    homepage: https://www.csx.com
    categories: [transport, logistics]
    tier: C
    aliases: [csx transportation]
    discover: { rss: false }
    notes: "csx.com is Imperva-protected (403) and investors.csx.com sits behind a Cloudflare challenge (2026-09-08)."
  - id: norfolk-southern
    name: Norfolk Southern
    domain: norfolksouthern.com
    homepage: https://www.norfolksouthern.com
    categories: [transport, logistics]
    tier: B
    aliases: [ns, norfolk southern railway]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://www.norfolksouthern.com/en/newsroom", type: HTML, connector: http, tier: B }
  - id: deutsche-bahn
    name: Deutsche Bahn
    domain: deutschebahn.com
    homepage: https://www.deutschebahn.com
    categories: [transport]
    tier: B
    weight: 1.2
    aliases: [db, db ag]
    discover: { rss: true }
    sensors:
      - { name: presse, url: "https://www.deutschebahn.com/de/presse", type: HTML, connector: http, tier: B }
  - id: sncf
    name: SNCF
    domain: sncf.com
    homepage: https://www.groupe-sncf.com
    categories: [transport]
    tier: B
    weight: 1.2
    aliases: [groupe sncf, sncf voyageurs, tgv inoui]
    discover: { rss: false }
    notes: "groupe-sncf.com and sncf.com are behind a DataDome challenge (403 'Please wait') — 2026-09-08."
  - id: eurostar
    name: Eurostar
    domain: eurostar.com
    homepage: https://www.eurostar.com
    categories: [transport, travel]
    tier: C
    aliases: [eurostar group, thalys]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap index (uk-en), url: "https://www.eurostar.com/uk-en/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxChildren: 10 } }
  - id: jr-east
    name: JR East
    domain: jreast.co.jp
    homepage: https://www.jreast.co.jp
    categories: [transport]
    tier: C
    aliases: [east japan railway company]
    discover: { rss: false }
    notes: "jreast.co.jp press pages are Akamai-protected (403) — 2026-09-08."
  - id: alstom
    name: Alstom
    domain: alstom.com
    homepage: https://www.alstom.com
    categories: [transport, industry]
    tier: B
    weight: 1.1
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://www.alstom.com/newsroom", type: HTML, connector: http, tier: B }
  - id: siemens-mobility
    name: Siemens Mobility
    domain: mobility.siemens.com
    homepage: https://www.mobility.siemens.com
    categories: [transport, industry]
    tier: C
    aliases: [siemens mobility gmbh, velaro]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap index, url: "https://www.mobility.siemens.com/sitemap_index.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxChildren: 10, maxUrls: 3000 } }
  - id: stadler
    name: Stadler Rail
    domain: stadlerrail.com
    homepage: https://www.stadlerrail.com
    categories: [transport, industry]
    tier: C
    aliases: [stadler]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.stadlerrail.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: wabtec
    name: Wabtec
    domain: wabteccorp.com
    homepage: https://www.wabteccorp.com
    categories: [transport, industry]
    tier: C
    aliases: [westinghouse air brake technologies]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://www.wabteccorp.com/newsroom", type: HTML, connector: http, tier: C }
  - id: hitachi-rail
    name: Hitachi Rail
    domain: hitachirail.com
    homepage: https://www.hitachirail.com
    categories: [transport, industry]
    tier: C
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.hitachirail.com/xmlsitemap", type: SITEMAP, connector: sitemap, tier: C }
  - id: stm
    name: STM (Société de transport de Montréal)
    domain: stm.info
    homepage: https://www.stm.info
    categories: [transport]
    tier: B
    weight: 1.1
    aliases: [société de transport de montréal, métro de montréal]
    discover: { rss: true }
    sensors:
      - { name: news feed (en), url: "https://www.stm.info/en/rss.xml", type: RSS, connector: rss, tier: B }
  - id: exo
    name: exo (Réseau de transport métropolitain)
    domain: exo.quebec
    homepage: https://exo.quebec
    categories: [transport]
    tier: C
    aliases: [réseau de transport métropolitain, trains de banlieue]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://exo.quebec/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: rem
    name: REM (CDPQ Infra)
    domain: rem.info
    homepage: https://rem.info
    categories: [transport]
    tier: B
    aliases: [réseau express métropolitain, cdpq infra]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://rem.info/en/news", type: HTML, connector: http, tier: B }
  - id: artm
    name: ARTM
    domain: artm.quebec
    homepage: https://www.artm.quebec
    categories: [transport, government]
    tier: C
    aliases: [autorité régionale de transport métropolitain]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.artm.quebec/feed/", type: RSS, connector: rss, tier: C }
  - id: ttc
    name: TTC (Toronto Transit Commission)
    domain: ttc.ca
    homepage: https://www.ttc.ca
    categories: [transport]
    tier: C
    aliases: [toronto transit commission]
    discover: { rss: false }
    notes: "ttc.ca news and service alerts are client-rendered (Sitecore JSS); sitemap index only lists route schedules (2026-09-08)."
  - id: metrolinx
    name: Metrolinx
    domain: metrolinx.com
    homepage: https://www.metrolinx.com
    categories: [transport, government]
    tier: B
    aliases: [go transit, up express, presto]
    discover: { rss: true }
    sensors:
      - { name: press room, url: "https://www.metrolinx.com/en/news", type: HTML, connector: http, tier: B }
  - id: translink
    name: TransLink
    domain: translink.ca
    homepage: https://www.translink.ca
    categories: [transport]
    tier: C
    aliases: [translink vancouver, skytrain]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.translink.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: oc-transpo
    name: OC Transpo
    domain: octranspo.com
    homepage: https://www.octranspo.com
    categories: [transport]
    tier: C
    aliases: [o-train]
    discover: { rss: true }
    sensors:
      - { name: news, url: "https://www.octranspo.com/news", type: HTML, connector: http, tier: C }
  - id: mta
    name: MTA (New York)
    domain: mta.info
    homepage: https://www.mta.info
    categories: [transport]
    tier: B
    weight: 1.2
    aliases: [metropolitan transportation authority, nyc subway, lirr, metro-north]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.mta.info/rss.xml", type: RSS, connector: rss, tier: B }
  - id: wmata
    name: WMATA
    domain: wmata.com
    homepage: https://www.wmata.com
    categories: [transport]
    tier: B
    aliases: [metro washington, washington metropolitan area transit authority]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.wmata.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: tfl
    name: Transport for London
    domain: tfl.gov.uk
    homepage: https://tfl.gov.uk
    categories: [transport, government]
    tier: A
    weight: 1.3
    aliases: [tfl, london underground, elizabeth line]
    products:
      - { name: TfL Unified API, type: API, aliases: [tfl api] }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: line status (tube/dlr/overground/elizabeth), url: "https://api.tfl.gov.uk/Line/Mode/tube,dlr,overground,elizabeth-line/Status", type: REST_API, connector: jsonlist, tier: A, config: { keyField: id, titleField: name, summaryField: "lineStatuses[0].statusSeverityDescription", dateField: modified, compareFields: ["lineStatuses[0].statusSeverityDescription", "lineStatuses[0].reason"], urlTemplate: "https://tfl.gov.uk/tube-dlr-overground/status/" } }
      - { name: press releases, url: "https://tfl.gov.uk/info-for/media/press-releases", type: HTML, connector: http, tier: B }
  - id: ratp
    name: RATP
    domain: ratp.fr
    homepage: https://www.ratp.fr
    categories: [transport]
    tier: C
    aliases: [ratp group, métro de paris]
    discover: { rss: false }
    notes: "ratp.fr is behind a Cloudflare challenge (2026-09-08)."
  - id: mbta
    name: MBTA
    domain: mbta.com
    homepage: https://www.mbta.com
    categories: [transport]
    tier: A
    weight: 1.1
    aliases: [massachusetts bay transportation authority, the t]
    products:
      - { name: MBTA V3 API, type: API }
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://cdn.mbta.com/news/rss.xml", type: RSS, connector: rss, tier: B }
      - { name: subway alerts (v3 api), url: "https://api-v3.mbta.com/alerts?filter%5Broute_type%5D=0,1&sort=-updated_at&page%5Blimit%5D=50", type: REST_API, connector: jsonlist, tier: A, config: { itemsPath: data, keyField: id, titleField: attributes.header, summaryField: attributes.description, dateField: attributes.updated_at, compareFields: [attributes.header, attributes.effect, attributes.severity], urlTemplate: "https://www.mbta.com/alerts/subway" } }
  - id: bart
    name: BART
    domain: bart.gov
    homepage: https://www.bart.gov
    categories: [transport]
    tier: A
    aliases: [bay area rapid transit]
    products:
      - { name: BART Legacy API, type: API }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: service advisories (bsa api), url: "https://api.bart.gov/api/bsa.aspx?cmd=bsa&key=MW9S-E7SL-26DU-VV8V&json=y", type: REST_API, connector: jsonlist, tier: A, config: { itemsPath: root.bsa, keyField: "@id", titleField: "description.#cdata-section", summaryField: "sms_text.#cdata-section", dateField: posted, compareFields: ["description.#cdata-section", expires], urlTemplate: "https://www.bart.gov/schedules/advisories" } }
  - id: septa
    name: SEPTA
    domain: septa.org
    homepage: https://www.septa.org
    categories: [transport]
    tier: A
    aliases: [southeastern pennsylvania transportation authority]
    discover: { rss: false }
    llm: false
    sensors:
      - { name: system alerts (api), url: "https://www3.septa.org/api/Alerts/index.php?req1=all", type: REST_API, connector: jsonlist, tier: A, config: { keyField: route_id, titleTemplate: "{mode} {route_name}", summaryField: description, dateField: last_updated, compareFields: [isalert, isdetour, issuspended, isdelays, alert, advisory], maxItems: 300, urlTemplate: "https://www.septa.org/alerts/" } }
  - id: cta
    name: CTA (Chicago Transit Authority)
    domain: transitchicago.com
    homepage: https://www.transitchicago.com
    categories: [transport]
    tier: A
    aliases: [chicago transit authority, chicago l]
    products:
      - { name: CTA Customer Alerts API, type: API }
    discover: { rss: true, sitemap: true }
    llm: false
    sensors:
      - { name: customer alerts (api), url: "https://www.transitchicago.com/api/1.0/alerts.aspx?outputType=JSON&activeonly=true", type: REST_API, connector: jsonlist, tier: A, config: { itemsPath: CTAAlerts.Alert, keyField: AlertId, titleField: Headline, summaryField: ShortDescription, dateField: EventStart, urlField: "AlertURL.#cdata-section", compareFields: [Headline, SeverityScore, EventEnd], maxItems: 200 } }
  - id: brightline
    name: Brightline
    domain: gobrightline.com
    homepage: https://www.gobrightline.com
    categories: [transport]
    tier: C
    aliases: [brightline west, brightline florida]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press room, url: "https://www.gobrightline.com/press-room", type: HTML, connector: http, tier: C }
  - id: california-hsr
    name: California High-Speed Rail Authority
    domain: hsr.ca.gov
    homepage: https://hsr.ca.gov
    categories: [transport, government]
    tier: C
    aliases: [cahsr, california high speed rail]
    discover: { sitemap: true }
    notes: "hsr.ca.gov newsroom serves an Imperva bot-wall shell to non-browser clients; the WordPress sitemap index is open."
    sensors:
      - { name: sitemap index, url: "https://hsr.ca.gov/sitemap_index.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: alto
    name: Alto (Canada high-speed rail)
    domain: altotrain.ca
    homepage: https://www.altotrain.ca
    categories: [transport, government]
    tier: B
    aliases: [alto train, tgv canada, vía hfr, high frequency rail]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.altotrain.ca/en/news/feed", type: RSS, connector: rss, tier: B, config: { maxItems: 60 } }
  # ───────────────────────── H · Road, security & border agencies ─────────────────────────
  - id: tsa
    name: TSA
    domain: tsa.gov
    homepage: https://www.tsa.gov
    categories: [aviation, transport, government]
    tier: B
    weight: 1.2
    aliases: [transportation security administration, tsa precheck]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.tsa.gov/rss.xml", type: RSS, connector: rss, tier: B }
  - id: cbsa
    name: Canada Border Services Agency
    domain: cbsa-asfc.gc.ca
    homepage: https://www.cbsa-asfc.gc.ca
    categories: [transport, government]
    tier: B
    weight: 1.1
    aliases: [cbsa, asfc, agence des services frontaliers du canada]
    discover: { rss: false }
    sensors:
      - { name: news feed, url: "https://api.io.canada.ca/io-server/gc/news/en/v2?dept=canadaborderservicesagency&sort=publishedDate&orderBy=desc&pick=50&format=atom&atomtitle=CBSA", type: ATOM, connector: rss, tier: B }
  - id: us-cbp
    name: U.S. Customs and Border Protection
    domain: cbp.gov
    homepage: https://www.cbp.gov
    categories: [transport, government]
    tier: B
    weight: 1.1
    aliases: [cbp, customs and border protection]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.cbp.gov/rss.xml", type: RSS, connector: rss, tier: B, config: { maxItems: 60 } }
  - id: us-dot
    name: U.S. Department of Transportation
    domain: transportation.gov
    homepage: https://www.transportation.gov
    categories: [transport, government]
    tier: B
    weight: 1.2
    aliases: [usdot, dot, fmcsa, federal motor carrier safety administration]
    discover: { rss: false }
    notes: "transportation.gov and fmcsa.dot.gov (newsroom, RSS) are Akamai-protected → 403 for bots (2026-09-08); FAA is a separate source."
  - id: transport-for-nsw
    name: Transport for NSW
    domain: transport.nsw.gov.au
    homepage: https://www.transport.nsw.gov.au
    categories: [transport, government]
    tier: C
    aliases: [tfnsw]
    discover: { rss: false }
    notes: "transport.nsw.gov.au media releases return 403 to non-browser clients (2026-09-08)."
  - id: saaq
    name: SAAQ
    domain: saaq.gouv.qc.ca
    homepage: https://saaq.gouv.qc.ca
    categories: [transport, government]
    tier: C
    aliases: [société de l'assurance automobile du québec]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap index, url: "https://saaq.gouv.qc.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: quebec-511
    name: Québec 511 (MTMD)
    domain: quebec511.info
    homepage: https://www.quebec511.info
    categories: [transport, government]
    tier: C
    aliases: [québec 511, quebec 511, ministère des transports du québec, mtq, mtmd]
    discover: { rss: false }
    notes: "quebec511.info is Imperva-protected (403) and quebec.ca has no per-ministry news RSS; nothing open found (2026-09-08)."
  - id: ontario-511
    name: Ontario 511 (MTO)
    domain: 511on.ca
    homepage: https://511on.ca
    categories: [transport, government, open-data]
    tier: A
    aliases: [ontario 511, ministry of transportation ontario, mto]
    products:
      - { name: Ontario 511 API, type: API }
    discover: { rss: false }
    llm: false
    sensors:
      - { name: road events (api), url: "https://511on.ca/api/v2/get/event", type: REST_API, connector: jsonlist, tier: A, config: { keyField: ID, titleTemplate: "{RoadwayName} {DirectionOfTravel}: {EventType}", summaryField: Description, dateField: LastUpdated, compareFields: [Description, IsFullClosure, LanesAffected], maxItems: 300, urlTemplate: "https://511on.ca/list/events" } }
      - { name: newsroom, url: "https://511on.ca/newsroom", type: HTML, connector: http, tier: C }
  - id: icbc
    name: ICBC
    domain: icbc.com
    homepage: https://www.icbc.com
    categories: [transport, government]
    tier: C
    aliases: [insurance corporation of british columbia]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://icbc.com/about-icbc/newsroom", type: HTML, connector: http, tier: C }
  # ───────────────────────── G · Maritime, ports, postal & logistics ─────────────────────────
  - id: maersk
    name: A.P. Moller - Maersk
    domain: maersk.com
    homepage: https://www.maersk.com
    categories: [logistics, transport]
    tier: B
    weight: 1.3
    aliases: [maersk, maersk line, apm terminals]
    discover: { sitemap: true }
    notes: "maersk.com news pages are client-rendered (press-releases path 404 for bots); the main sitemap is open."
    sensors:
      - { name: sitemap, url: "https://www.maersk.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxUrls: 4000 } }
  - id: msc
    name: MSC Mediterranean Shipping Company
    domain: msc.com
    homepage: https://www.msc.com
    categories: [logistics, transport]
    tier: B
    weight: 1.2
    aliases: [msc, mediterranean shipping company]
    discover: { rss: false }
    notes: "msc.com is Akamai-protected (403 for bots) — 2026-09-08."
  - id: cma-cgm
    name: CMA CGM
    domain: cma-cgm.com
    homepage: https://www.cma-cgm.com
    categories: [logistics, transport]
    tier: B
    weight: 1.1
    aliases: [cma cgm group, ceva logistics]
    discover: { rss: false }
    notes: "cma-cgm.com and cmacgm-group.com are Next.js shells behind Dynatrace/bot management; no open feed found (2026-09-08)."
  - id: hapag-lloyd
    name: Hapag-Lloyd
    domain: hapag-lloyd.com
    homepage: https://www.hapag-lloyd.com
    categories: [logistics, transport]
    tier: B
    weight: 1.1
    aliases: [hapag lloyd]
    discover: { rss: false }
    notes: "hapag-lloyd.com serves a 'Security Check' interstitial (403) to non-browser clients (2026-09-08)."
  - id: zim
    name: ZIM Integrated Shipping Services
    domain: zim.com
    homepage: https://www.zim.com
    categories: [logistics, transport]
    tier: C
    aliases: [zim]
    discover: { rss: false }
    notes: "zim.com is Akamai-protected (403) — 2026-09-08."
  - id: port-of-montreal
    name: Port of Montreal
    domain: port-montreal.com
    homepage: https://www.port-montreal.com
    categories: [logistics, transport]
    tier: B
    aliases: [montreal port authority, administration portuaire de montréal, apm]
    discover: { rss: false }
    notes: "port-montreal.com is behind a Cloudflare challenge (2026-09-08)."
  - id: port-of-vancouver
    name: Vancouver Fraser Port Authority
    domain: portvancouver.com
    homepage: https://www.portvancouver.com
    categories: [logistics, transport]
    tier: B
    aliases: [port of vancouver]
    discover: { rss: false }
    notes: "portvancouver.com is behind a Cloudflare challenge (2026-09-08)."
  - id: port-of-halifax
    name: Halifax Port Authority
    domain: portofhalifax.ca
    homepage: https://www.portofhalifax.ca
    categories: [logistics, transport]
    tier: C
    aliases: [port of halifax]
    discover: { rss: false }
    notes: "portofhalifax.ca is behind a Cloudflare challenge (2026-09-08)."
  - id: port-of-prince-rupert
    name: Prince Rupert Port Authority
    domain: rupertport.com
    homepage: https://www.rupertport.com
    categories: [logistics, transport]
    tier: C
    aliases: [port of prince rupert]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.rupertport.com/feed/", type: RSS, connector: rss, tier: C }
  - id: port-of-los-angeles
    name: Port of Los Angeles
    domain: portoflosangeles.org
    homepage: https://www.portoflosangeles.org
    categories: [logistics, transport]
    tier: B
    weight: 1.1
    aliases: [pola, port of la]
    discover: { rss: true }
    sensors:
      - { name: news, url: "https://portoflosangeles.org/news", type: HTML, connector: http, tier: B }
  - id: port-of-long-beach
    name: Port of Long Beach
    domain: polb.com
    homepage: https://polb.com
    categories: [logistics, transport]
    tier: C
    aliases: [polb]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap index, url: "https://polb.com/sitemap-index.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: port-of-rotterdam
    name: Port of Rotterdam
    domain: portofrotterdam.com
    homepage: https://www.portofrotterdam.com
    categories: [logistics, transport]
    tier: B
    weight: 1.1
    aliases: [havenbedrijf rotterdam]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news and press releases, url: "https://www.portofrotterdam.com/en/news-and-press-releases", type: HTML, connector: http, tier: B }
  - id: port-of-antwerp-bruges
    name: Port of Antwerp-Bruges
    domain: portofantwerpbruges.com
    homepage: https://www.portofantwerpbruges.com
    categories: [logistics, transport]
    tier: C
    aliases: [port of antwerp, port of zeebrugge]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.portofantwerpbruges.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: port-of-hamburg
    name: Port of Hamburg
    domain: hafen-hamburg.de
    homepage: https://www.hafen-hamburg.de
    categories: [logistics, transport]
    tier: C
    aliases: [hafen hamburg, hamburg port authority]
    discover: { rss: true }
    sensors:
      - { name: press news, url: "https://www.hafen-hamburg.de/en/press/news/", type: HTML, connector: http, tier: C }
  - id: mpa-singapore
    name: Maritime and Port Authority of Singapore
    domain: mpa.gov.sg
    homepage: https://www.mpa.gov.sg
    categories: [logistics, transport, government]
    tier: C
    aliases: [mpa, mpa singapore]
    discover: { rss: true }
    notes: "mpa.gov.sg media centre is a client-rendered Next.js shell (thin) — 2026-09-08."
  - id: panama-canal
    name: Panama Canal Authority
    domain: pancanal.com
    homepage: https://pancanal.com
    categories: [logistics, transport]
    tier: B
    weight: 1.2
    aliases: [autoridad del canal de panamá, acp, canal de panamá]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed (en), url: "https://pancanal.com/en/feed/", type: RSS, connector: rss, tier: B }
  - id: suez-canal-authority
    name: Suez Canal Authority
    domain: suezcanal.gov.eg
    homepage: https://www.suezcanal.gov.eg
    categories: [logistics, transport, government]
    tier: B
    weight: 1.1
    aliases: [sca, suez canal]
    discover: { rss: false }
    sensors:
      - { name: news, url: "https://www.suezcanal.gov.eg/English/MediaCenter/News/Pages/default.aspx", type: HTML, connector: http, tier: C }
  - id: st-lawrence-seaway
    name: Great Lakes St. Lawrence Seaway
    domain: greatlakes-seaway.com
    homepage: https://greatlakes-seaway.com
    categories: [logistics, transport]
    tier: B
    aliases: [st. lawrence seaway, seaway, voie maritime du saint-laurent]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://greatlakes-seaway.com/en/news/feed/", type: RSS, connector: rss, tier: B }
  - id: imo
    name: International Maritime Organization
    domain: imo.org
    homepage: https://www.imo.org
    categories: [logistics, transport, international]
    tier: B
    weight: 1.2
    aliases: [imo]
    discover: { rss: true }
    sensors:
      - { name: press briefings, url: "https://www.imo.org/en/MediaCentre/PressBriefings/Pages/Default.aspx", type: HTML, connector: http, tier: B }
  - id: bimco
    name: BIMCO
    domain: bimco.org
    homepage: https://www.bimco.org
    categories: [logistics, industry]
    tier: C
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news, url: "https://www.bimco.org/news-insights/bimco-news/", type: HTML, connector: http, tier: C }
  - id: ics-shipping
    name: International Chamber of Shipping
    domain: ics-shipping.org
    homepage: https://www.ics-shipping.org
    categories: [logistics, industry]
    tier: C
    aliases: [ics]
    discover: { rss: true }
    notes: "ics-shipping.org news returns 403 to bots and its WordPress feed is empty (2026-09-08)."
  - id: lloyds-register
    name: Lloyd's Register
    domain: lr.org
    homepage: https://www.lr.org
    categories: [logistics, industry]
    tier: C
    aliases: [lr, lloyd's register group]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press room, url: "https://www.lr.org/en/knowledge/press-room/", type: HTML, connector: http, tier: C }
  - id: dnv
    name: DNV
    domain: dnv.com
    homepage: https://www.dnv.com
    categories: [logistics, energy, industry]
    tier: B
    aliases: [det norske veritas, dnv gl]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.dnv.com/news/rss/", type: RSS, connector: rss, tier: B }
  - id: abs-shipping
    name: ABS (American Bureau of Shipping)
    domain: eagle.org
    homepage: https://ww2.eagle.org
    categories: [logistics, industry]
    tier: C
    aliases: [american bureau of shipping, abs]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://ww2.eagle.org/en/news/newsroom.html", type: HTML, connector: http, tier: C }
  - id: dhl
    name: DHL Group
    domain: dhl.com
    homepage: https://group.dhl.com
    categories: [logistics]
    tier: B
    weight: 1.3
    aliases: [deutsche post dhl, dhl express]
    discover: { rss: false }
    notes: "group.dhl.com and dhl.com time out / reset for non-browser clients (Akamai) — no open feed (2026-09-08)."
  - id: fedex
    name: FedEx
    domain: fedex.com
    homepage: https://www.fedex.com
    categories: [logistics]
    tier: A
    weight: 1.4
    aliases: [federal express, fedex express, fedex freight]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: service alerts, url: "https://www.fedex.com/en-us/service-alerts.html", type: HTML, connector: http, tier: A }
      - { name: newsroom, url: "https://newsroom.fedex.com/", type: HTML, connector: http, tier: B }
  - id: ups
    name: UPS
    domain: ups.com
    homepage: https://www.ups.com
    categories: [logistics]
    tier: A
    weight: 1.4
    aliases: [united parcel service]
    discover: { rss: false }
    notes: "ups.com (service alerts) and about.ups.com (newsroom) are Akamai-protected → timeout/403 for bots (2026-09-08)."
  - id: usps
    name: USPS
    domain: usps.com
    homepage: https://about.usps.com
    categories: [logistics, government]
    tier: A
    weight: 1.3
    aliases: [united states postal service, us postal service]
    discover: { rss: true }
    sensors:
      - { name: service alerts, url: "https://about.usps.com/newsroom/service-alerts/", type: HTML, connector: http, tier: A }
      - { name: news feed, url: "https://about.usps.com/news/latestnews.rss", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }
  - id: canada-post
    name: Canada Post
    domain: canadapost-postescanada.ca
    homepage: https://www.canadapost-postescanada.ca
    categories: [logistics, government]
    tier: A
    weight: 1.3
    aliases: [postes canada, canada post corporation]
    discover: { rss: false, sitemap: true }
    sensors:
      - { name: service alerts, url: "https://www.canadapost-postescanada.ca/cpc/en/our-company/news-and-media/service-alerts.page", type: HTML, connector: http, tier: A }
      - { name: corporate news, url: "https://www.canadapost-postescanada.ca/cpc/en/our-company/news-and-media/corporate-news.page", type: HTML, connector: http, tier: B }
  - id: purolator
    name: Purolator
    domain: purolator.com
    homepage: https://www.purolator.com
    categories: [logistics]
    tier: C
    discover: { rss: false }
    notes: "purolator.com (incl. service alerts) is behind a Cloudflare challenge (2026-09-08)."
  - id: kuehne-nagel
    name: Kuehne+Nagel
    domain: kuehne-nagel.com
    homepage: https://www.kuehne-nagel.com
    categories: [logistics]
    tier: B
    aliases: [kuehne nagel, kühne + nagel, k+n]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom, url: "https://newsroom.kuehne-nagel.com/", type: HTML, connector: http, tier: B }
  - id: dsv
    name: DSV
    domain: dsv.com
    homepage: https://www.dsv.com
    categories: [logistics]
    tier: B
    aliases: [dsv a/s, db schenker]
    discover: { rss: true, sitemap: true }
    notes: "dbschenker.com now redirects to dsv.com (DB Schenker acquired by DSV)."
    sensors:
      - { name: press, url: "https://www.dsv.com/en/about-dsv/press", type: HTML, connector: http, tier: B }
  - id: ch-robinson
    name: C.H. Robinson
    domain: chrobinson.com
    homepage: https://www.chrobinson.com
    categories: [logistics]
    tier: C
    aliases: [chrw]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap (en-us), url: "https://www.chrobinson.com/chrobinson-en-us-sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: xpo
    name: XPO
    domain: xpo.com
    homepage: https://www.xpo.com
    categories: [logistics]
    tier: C
    aliases: [xpo logistics]
    discover: { sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.xpo.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C }
  - id: jb-hunt
    name: J.B. Hunt
    domain: jbhunt.com
    homepage: https://www.jbhunt.com
    categories: [logistics]
    tier: C
    aliases: [jb hunt, j.b. hunt transport services]
    discover: { rss: true }
    sensors:
      - { name: newsroom, url: "https://www.jbhunt.com/our-company/newsroom", type: HTML, connector: http, tier: C }
  - id: tfi-international
    name: TFI International
    domain: tfiintl.com
    homepage: https://tfiintl.com
    categories: [logistics]
    tier: C
    aliases: [tfi, transforce]
    discover: { rss: false }
    notes: "tfiintl.com times out for non-browser clients (2026-09-08)."
  - id: flexport
    name: Flexport
    domain: flexport.com
    homepage: https://www.flexport.com
    categories: [logistics, technology]
    tier: C
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: blog, url: "https://www.flexport.com/blog/", type: HTML, connector: http, tier: C }
  - id: freightos
    name: Freightos
    domain: freightos.com
    homepage: https://www.freightos.com
    categories: [logistics, technology]
    tier: C
    aliases: [freightos baltic index, fbx]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.freightos.com/feed/", type: RSS, connector: rss, tier: C }
  - id: cargojet
    name: Cargojet
    domain: cargojet.com
    homepage: https://cargojet.com
    categories: [logistics, aviation]
    tier: C
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://cargojet.com/feed/", type: RSS, connector: rss, tier: C }
  - id: atlas-air
    name: Atlas Air Worldwide
    domain: atlasairworldwide.com
    homepage: https://www.atlasairworldwide.com
    categories: [logistics, aviation]
    tier: C
    aliases: [atlas air]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.atlasairworldwide.com/feed/", type: RSS, connector: rss, tier: C }
  - id: ryder
    name: Ryder System
    domain: ryder.com
    homepage: https://www.ryder.com
    categories: [logistics]
    tier: C
    aliases: [ryder]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.ryder.com/en-us/api/rssfeed/showrssfeed", type: RSS, connector: rss, tier: C, config: { maxItems: 50 } }
  - id: penske
    name: Penske Transportation Solutions
    domain: gopenske.com
    homepage: https://www.gopenske.com
    categories: [logistics]
    tier: C
    aliases: [penske logistics, penske truck leasing]
    discover: { rss: true }
    notes: "gopenske.com newsroom (RebelMouse) renders client-side — only 133 chars of server text (2026-09-08)."
  - id: uber-freight
    name: Uber Freight
    domain: uberfreight.com
    homepage: https://www.uberfreight.com
    categories: [logistics, technology]
    tier: C
    discover: { rss: true }
    sensors:
      - { name: blog, url: "https://www.uberfreight.com/en-US/blog", type: HTML, connector: http, tier: C }