# config/sources.d/14-retail-consumer-travel.yaml — retail & marketplaces, consumer brands, food & beverage,
# restaurants, hospitality & travel platforms, delivery, automotive retail, loyalty (added 2026-09-08).
# Every sensor below was fetched and parsed by apps/engine/src/validate.ts before being written. Investor-relations
# feeds hosted on Q4 behind a Cloudflare challenge (Costco, Best Buy, Kroger IR, eBay IR, Wayfair, Chewy, Canadian
# Tire, Aritzia, Roots, General Mills, Molson Coors, Kimberly-Clark, Whirlpool, Mattel, GoPro, Crocs, CarMax,
# Gap, Levi's, Hyatt IR, RBI, Starbucks, Yum, Wendy's, Darden, Booking, Uber IR, DoorDash IR) are NOT sensors —
# they are listed in `notes:`. `robots.txt` sensors (tier D) on the large marketplaces track AI-crawler policy shifts.

sources:
  # ───────────────────────── A · Retailers & marketplaces ─────────────────────────
  - id: amazon
    name: Amazon
    domain: amazon.com
    homepage: https://www.aboutamazon.com
    categories: [retail, commerce, technology]
    tier: A
    weight: 1.5
    aliases: [amazon.com, amazon inc]
    products:
      - { name: Amazon Prime, type: service, aliases: [prime] }
      - { name: Alexa, type: product }
      - { name: Kindle, type: product }
      - { name: Amazon Marketplace, type: service, aliases: [amazon marketplace, amazon sellers] }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "AWS is the separate `aws` source. press.aboutamazon.com/rss/news-releases.xml and ir.aboutamazon.com (Q4, Cloudflare challenge) are not reachable; the About Amazon newsroom feed is."
    sensors:
      - { name: news feed, url: "https://www.aboutamazon.com/rss/feed.rss", type: RSS, connector: rss, tier: A }
      - { name: crawler policy (robots.txt), url: "https://www.amazon.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: walmart
    name: Walmart
    domain: walmart.com
    homepage: https://corporate.walmart.com
    categories: [retail, commerce]
    tier: B
    weight: 1.3
    aliases: [walmart inc, wal-mart]
    products:
      - { name: Walmart+, type: service, aliases: [walmart plus] }
      - { name: Sam's Club, type: product, aliases: [sams club] }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "No RSS on corporate.walmart.com or stock.walmart.com (Q4 404); newsroom index page + robots."
    sensors:
      - { name: newsroom, url: "https://corporate.walmart.com/content/corporate/en_us/news.html", type: HTML, connector: http, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.walmart.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: target
    name: Target
    domain: target.com
    homepage: https://corporate.target.com
    categories: [retail, commerce]
    tier: B
    weight: 1.2
    aliases: [target corporation, target corp]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases feed, url: "https://corporate.target.com/feeds/pressreleases", type: RSS, connector: rss, tier: B }
      - { name: news feed, url: "https://corporate.target.com/feeds/news", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.target.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: costco
    name: Costco
    domain: costco.com
    homepage: https://investor.costco.com
    categories: [retail, commerce]
    tier: B
    weight: 1.2
    aliases: [costco wholesale]
    discover: { rss: true, sitemap: true }
    notes: "investor.costco.com (Q4) sits behind a Cloudflare challenge; costco.com times out for bots. No validated sensor yet."
  - id: home-depot
    name: The Home Depot
    domain: homedepot.com
    homepage: https://corporate.homedepot.com
    categories: [retail, commerce]
    tier: B
    weight: 1.2
    aliases: [home depot]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: investor news feed, url: "https://ir.homedepot.com/rss/news-releases.xml", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.homedepot.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: lowes
    name: Lowe's
    domain: lowes.com
    homepage: https://corporate.lowes.com
    categories: [retail, commerce]
    tier: B
    aliases: [lowes, lowe's companies]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "corporate.lowes.com newsroom has no feed (Akamai on lowes.com)."
    sensors:
      - { name: newsroom, url: "https://corporate.lowes.com/newsroom", type: HTML, connector: http, tier: B }
  - id: kroger
    name: Kroger
    domain: thekrogerco.com
    categories: [retail, food]
    tier: B
    aliases: [the kroger co]
    discover: { rss: true }
    notes: "ir.kroger.com (Q4) behind a Cloudflare challenge; corporate WordPress feed works."
    sensors:
      - { name: newsroom feed, url: "https://www.thekrogerco.com/feed/", type: RSS, connector: rss, tier: B }
  - id: best-buy
    name: Best Buy
    domain: bestbuy.com
    homepage: https://corporate.bestbuy.com
    categories: [retail, consumer-tech]
    tier: B
    aliases: [bestbuy]
    discover: { rss: true }
    notes: "investors.bestbuy.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: corporate news feed, url: "https://corporate.bestbuy.com/feed/", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.bestbuy.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: ikea
    name: IKEA
    domain: ikea.com
    categories: [retail, consumer]
    tier: B
    weight: 1.1
    aliases: [ingka, inter ikea]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "Newsroom (ikea.com/global/en/newsroom) is client-rendered, no feed."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.ikea.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: loblaw
    name: Loblaw Companies
    domain: loblaw.ca
    categories: [retail, food]
    tier: B
    weight: 1.1
    aliases: [loblaws, loblaw companies limited]
    products:
      - { name: PC Optimum, type: service, aliases: [pc optimum] }
      - { name: Shoppers Drug Mart, type: product, aliases: [shoppers, pharmaprix] }
      - { name: No Frills, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: our stories, url: "https://www.loblaw.ca/en/our-stories/", type: HTML, connector: http, tier: B }
  - id: empire-sobeys
    name: Empire Company (Sobeys)
    domain: empireco.ca
    categories: [retail, food]
    tier: B
    aliases: [empire, sobeys, iga, safeway canada]
    products:
      - { name: Scene+, type: service, aliases: [scene plus] }
      - { name: Voilà, type: service, aliases: [voila] }
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news releases, url: "https://www.empireco.ca/news", type: HTML, connector: http, tier: B }
  - id: dollarama
    name: Dollarama
    domain: dollarama.com
    categories: [retail]
    tier: B
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: corporate content sitemap, url: "https://www.dollarama.com/sitemap_content.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: couche-tard
    name: Alimentation Couche-Tard
    domain: couche-tard.com
    homepage: https://corporate.couche-tard.com
    categories: [retail]
    tier: B
    aliases: [couche-tard, circle k]
    products:
      - { name: Circle K, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: newsroom, url: "https://corporate.couche-tard.com/newsroom", type: HTML, connector: http, tier: B }
  - id: aldi
    name: ALDI
    domain: aldi.us
    homepage: https://corporate.aldi.us
    categories: [retail, food]
    tier: B
    aliases: [aldi us, aldi süd, aldi nord]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "aldi.co.uk newsroom is 403 to bots."
    sensors:
      - { name: US newsroom, url: "https://corporate.aldi.us/newsroom", type: HTML, connector: http, tier: B }
  - id: carrefour
    name: Carrefour
    domain: carrefour.com
    categories: [retail, food]
    tier: B
    weight: 1.1
    aliases: [groupe carrefour]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.carrefour.com/en/rss.xml", type: RSS, connector: rss, tier: B }
  - id: hm-group
    name: H&M Group
    domain: hmgroup.com
    categories: [retail, consumer]
    tier: B
    aliases: [h&m, hennes & mauritz, h and m]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://hmgroup.com/feed/", type: RSS, connector: rss, tier: B }
  - id: seven-and-i
    name: Seven & i Holdings
    domain: 7andi.com
    categories: [retail]
    tier: B
    aliases: [seven & i, 7-eleven, seven eleven, 7&i]
    products:
      - { name: 7-Eleven, type: product, aliases: [seven eleven] }
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.7andi.com/rss/en_news.xml", type: RSS, connector: rss, tier: B }
  - id: alibaba
    name: Alibaba Group
    domain: alibabagroup.com
    categories: [commerce, retail, technology]
    tier: B
    weight: 1.3
    aliases: [alibaba, taobao, tmall, aliexpress]
    products:
      - { name: AliExpress, type: service }
      - { name: Taobao, type: service }
      - { name: Tmall, type: service }
      - { name: Alizila, type: product }
    discover: { rss: true, sitemap: true }
    notes: "alibabagroup.com is client-rendered; Alizila (official news site) has a WordPress feed."
    sensors:
      - { name: alizila news feed, url: "https://www.alizila.com/feed/", type: RSS, connector: rss, tier: B }
      - { name: alibaba.com crawler policy (robots.txt), url: "https://www.alibaba.com/robots.txt", type: FILE, connector: http, tier: D }
      - { name: aliexpress crawler policy (robots.txt), url: "https://www.aliexpress.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: etsy
    name: Etsy
    domain: etsy.com
    homepage: https://investors.etsy.com
    categories: [commerce, retail]
    tier: B
    aliases: [etsy inc]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://investors.etsy.com/news-events/press-releases/rss", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.etsy.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: ebay
    name: eBay
    domain: ebay.com
    homepage: https://www.ebayinc.com
    categories: [commerce, retail]
    tier: B
    weight: 1.1
    aliases: [ebay inc]
    discover: { rss: true }
    notes: "investors.ebayinc.com (Q4) behind a Cloudflare challenge; ebayinc.com stories feed works."
    sensors:
      - { name: news feed, url: "https://www.ebayinc.com/stories/news/rss/", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.ebay.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: rakuten
    name: Rakuten Group
    domain: rakuten.co.jp
    homepage: https://global.rakuten.com/corp/
    categories: [commerce, retail, internet]
    tier: B
    aliases: [rakuten]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://global.rakuten.com/corp/rss/press.xml", type: RSS, connector: rss, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.rakuten.co.jp/robots.txt", type: FILE, connector: http, tier: D }
  - id: mercadolibre
    name: MercadoLibre
    domain: mercadolibre.com
    homepage: https://investor.mercadolibre.com
    categories: [commerce, retail, payments]
    tier: B
    weight: 1.1
    aliases: [mercado libre, meli, mercado pago]
    discover: { rss: true, sitemap: true }
    notes: "investor.mercadolibre.com exposes no RSS (404 on the usual paths)."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.mercadolibre.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: shein
    name: SHEIN
    domain: shein.com
    homepage: https://www.sheingroup.com
    categories: [commerce, retail, consumer]
    tier: B
    aliases: [shein group]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: newsroom, url: "https://www.sheingroup.com/newsroom", type: HTML, connector: http, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.shein.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: flipkart
    name: Flipkart
    domain: flipkart.com
    homepage: https://stories.flipkart.com
    categories: [commerce, retail]
    tier: B
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.flipkart.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: wayfair
    name: Wayfair
    domain: wayfair.com
    categories: [commerce, retail]
    tier: B
    discover: { rss: true }
    notes: "investor.wayfair.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.wayfair.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: chewy
    name: Chewy
    domain: chewy.com
    categories: [commerce, retail]
    tier: C
    discover: { rss: true }
    notes: "investor.chewy.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.chewy.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: instacart
    name: Instacart
    domain: instacart.com
    homepage: https://company.instacart.com
    categories: [commerce, food, technology]
    tier: B
    aliases: [maplebear]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: company updates, url: "https://company.instacart.com/updates/", type: HTML, connector: http, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.instacart.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: newegg
    name: Newegg
    domain: newegg.com
    categories: [commerce, consumer-tech]
    tier: C
    discover: { rss: true }
    sensors:
      - { name: insider feed, url: "https://www.newegg.com/insider/feed/", type: RSS, connector: rss, tier: C }
      - { name: crawler policy (robots.txt), url: "https://www.newegg.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: canadian-tire
    name: Canadian Tire Corporation
    domain: canadiantire.ca
    homepage: https://corp.canadiantire.ca
    categories: [retail]
    tier: B
    aliases: [canadian tire, ctc, sportchek, mark's]
    products:
      - { name: Triangle Rewards, type: service }
    discover: { rss: true, sitemap: true }
    notes: "corp.canadiantire.ca and investors.canadiantire.ca (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.canadiantire.ca/robots.txt", type: FILE, connector: http, tier: D }
  - id: walgreens
    name: Walgreens Boots Alliance
    domain: walgreens.com
    homepage: https://corporate.walgreens.com
    categories: [retail, health]
    tier: B
    aliases: [walgreens, boots, wba]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news and stories, url: "https://corporate.walgreens.com/news-and-stories/", type: HTML, connector: http, tier: B }
  - id: cvs
    name: CVS Health
    domain: cvshealth.com
    categories: [retail, health]
    tier: B
    weight: 1.1
    aliases: [cvs, cvs pharmacy, aetna]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: sitemap, url: "https://www.cvshealth.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }
  - id: metro-inc
    name: Metro Inc.
    domain: metro.ca
    homepage: https://corpo.metro.ca
    categories: [retail, food]
    tier: B
    aliases: [metro, jean coutu, brunet, super c]
    products:
      - { name: Jean Coutu, type: product, aliases: [pjc] }
    discover: { rss: true, sitemap: true }
    notes: "No feed on corpo.metro.ca; corporate sitemap only."
    sensors:
      - { name: corporate sitemap, url: "https://corpo.metro.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }
  - id: lidl
    name: Lidl
    domain: lidl.com
    homepage: https://corporate.lidl.co.uk
    categories: [retail, food]
    tier: B
    aliases: [lidl gb, schwarz group]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: UK media centre, url: "https://corporate.lidl.co.uk/media-centre", type: HTML, connector: http, tier: B }
  - id: tesco
    name: Tesco
    domain: tescoplc.com
    categories: [retail, food]
    tier: B
    weight: 1.1
    aliases: [tesco plc]
    discover: { rss: true, sitemap: true }
    notes: "tescoplc.com returns 403 to non-browser clients on every path (Akamai). No validated sensor yet."
  - id: sainsburys
    name: Sainsbury's
    domain: sainsburys.co.uk
    homepage: https://corporate.sainsburys.co.uk
    categories: [retail, food]
    tier: B
    aliases: [sainsburys, j sainsbury, argos]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: press releases feed, url: "https://corporate.sainsburys.co.uk/rss/news", type: RSS, connector: rss, tier: B }
      - { name: press releases, url: "https://corporate.sainsburys.co.uk/news/press-releases/", type: HTML, connector: http, tier: B }
  - id: inditex
    name: Inditex
    domain: inditex.com
    categories: [retail, consumer]
    tier: B
    weight: 1.1
    aliases: [zara, massimo dutti, bershka, pull&bear]
    products:
      - { name: Zara, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "zara.com is 403 to bots; inditex.com press pages are server-rendered."
    sensors:
      - { name: press news, url: "https://www.inditex.com/itxcomweb/en/press/news", type: HTML, connector: http, tier: B }
  - id: fast-retailing
    name: Fast Retailing
    domain: fastretailing.com
    categories: [retail, consumer]
    tier: B
    aliases: [uniqlo, gu]
    products:
      - { name: UNIQLO, type: product, aliases: [uniqlo] }
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news, url: "https://www.fastretailing.com/eng/about/news/", type: HTML, connector: http, tier: B }
  - id: jd-com
    name: JD.com
    domain: jd.com
    homepage: https://ir.jd.com
    categories: [commerce, retail]
    tier: B
    aliases: [jingdong, jd]
    discover: { rss: true, sitemap: true }
    notes: "ir.jd.com and corporate.jd.com are 403 to bots; jd.com robots.txt redirects to an HTML page. No validated sensor yet."
  - id: pdd-temu
    name: PDD Holdings (Temu)
    domain: pddholdings.com
    categories: [commerce, retail]
    tier: B
    aliases: [pdd, temu, pinduoduo]
    products:
      - { name: Temu, type: service }
      - { name: Pinduoduo, type: service }
    discover: { rss: true, sitemap: true }
    notes: "investor.pddholdings.com is 403 to bots; temu.com serves an HTML shell for robots.txt. No validated sensor yet."
  - id: bh-photo
    name: B&H Photo Video
    domain: bhphotovideo.com
    categories: [commerce, consumer-tech]
    tier: C
    aliases: [b&h, bh photo]
    discover: { rss: true }
    notes: "Whole site behind a Cloudflare challenge (Explora feed included)."
  - id: simons
    name: La Maison Simons
    domain: simons.ca
    categories: [retail, consumer]
    tier: C
    aliases: [simons]
    discover: { rss: true, sitemap: true }
    notes: "simons.ca is 403 to bots."
  - id: aritzia
    name: Aritzia
    domain: aritzia.com
    categories: [retail, consumer]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "aritzia.com and investors.aritzia.com (Q4) behind a Cloudflare challenge."
  - id: roots
    name: Roots
    domain: roots.com
    categories: [retail, consumer]
    tier: C
    aliases: [roots canada]
    discover: { rss: true, sitemap: true }
    notes: "investors.roots.com (Q4) behind a Cloudflare challenge; roots.com exposes no feed."
  - id: sephora
    name: Sephora
    domain: sephora.com
    homepage: https://newsroom.sephora.com
    categories: [retail, consumer]
    tier: B
    discover: { rss: true }
    sensors:
      - { name: newsroom feed, url: "https://newsroom.sephora.com/feed/", type: RSS, connector: rss, tier: B }
  - id: ulta
    name: Ulta Beauty
    domain: ulta.com
    categories: [retail, consumer]
    tier: B
    aliases: [ulta]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.ulta.com unreachable for bots; ulta.com newsroom is client-rendered — investor sitemap only."
    sensors:
      - { name: investor sitemap, url: "https://www.ulta.com/investor/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }

  # ───────────────────────── B · Consumer brands ─────────────────────────
  - id: nike
    name: Nike
    domain: nike.com
    homepage: https://about.nike.com
    categories: [consumer, retail]
    tier: B
    weight: 1.3
    aliases: [nike inc, jordan brand, converse]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom feed, url: "https://about.nike.com/en/feed", type: RSS, connector: rss, tier: B }
  - id: adidas
    name: adidas
    domain: adidas-group.com
    homepage: https://www.adidas-group.com
    categories: [consumer, retail]
    tier: B
    weight: 1.1
    aliases: [adidas ag]
    discover: { rss: true, sitemap: true }
    notes: "news.adidas.com answers 202 with an empty body (bot management); adidas-group.com exposes no feed. No validated sensor yet."
  - id: lululemon
    name: lululemon
    domain: lululemon.com
    homepage: https://corporate.lululemon.com
    categories: [consumer, retail]
    tier: B
    aliases: [lululemon athletica]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://corporate.lululemon.com/rss/press-releases", type: RSS, connector: rss, tier: B, config: { maxItems: 50 } }
  - id: canada-goose
    name: Canada Goose
    domain: canadagoose.com
    categories: [consumer, retail]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "canadagoose.com rate-limits bots (429); investors.canadagoose.com unreachable. No validated sensor yet."
  - id: lvmh
    name: LVMH
    domain: lvmh.com
    categories: [consumer, retail]
    tier: B
    weight: 1.3
    aliases: [louis vuitton, moët hennessy louis vuitton, dior, tiffany]
    products:
      - { name: Louis Vuitton, type: product }
      - { name: Dior, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "lvmh.com news pages are client-rendered; sitemap index only."
    sensors:
      - { name: sitemap, url: "https://www.lvmh.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: kering
    name: Kering
    domain: kering.com
    categories: [consumer, retail]
    tier: B
    weight: 1.1
    aliases: [gucci, saint laurent, bottega veneta, balenciaga]
    products:
      - { name: Gucci, type: product }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: sitemap (en), url: "https://www.kering.com/en/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: hermes
    name: Hermès
    domain: hermes.com
    homepage: https://finance.hermes.com
    categories: [consumer, retail]
    tier: B
    weight: 1.1
    aliases: [hermes, hermès international]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: finance sitemap, url: "https://finance.hermes.com/sitemap-index.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: richemont
    name: Richemont
    domain: richemont.com
    categories: [consumer, retail]
    tier: B
    aliases: [cartier, van cleef & arpels, iwc, compagnie financière richemont]
    products:
      - { name: Cartier, type: product }
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: sitemap, url: "https://www.richemont.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }
  - id: loreal
    name: L'Oréal
    domain: loreal.com
    categories: [consumer]
    tier: B
    weight: 1.2
    aliases: [loreal, l'oréal groupe, lancôme, maybelline, garnier]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news, url: "https://www.loreal.com/en/news/", type: HTML, connector: http, tier: B }
      - { name: finance news (fr), url: "https://www.loreal-finance.com/fr/actualites", type: HTML, connector: http, tier: B }
  - id: estee-lauder
    name: The Estée Lauder Companies
    domain: elcompanies.com
    categories: [consumer]
    tier: B
    weight: 1.1
    aliases: [estee lauder, estée lauder, mac cosmetics, clinique]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://www.elcompanies.com/en/rss/press-releases", type: RSS, connector: rss, tier: B }
  - id: procter-gamble
    name: Procter & Gamble
    domain: pg.com
    homepage: https://us.pg.com
    categories: [consumer]
    tier: B
    weight: 1.3
    aliases: [p&g, procter and gamble, pampers, tide, gillette]
    products:
      - { name: Gillette, type: product }
      - { name: Pampers, type: product }
      - { name: Tide, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "news.pg.com (Q4) redirects to the newsroom; no RSS."
    sensors:
      - { name: newsroom, url: "https://us.pg.com/newsroom/", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://us.pg.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }
  - id: unilever
    name: Unilever
    domain: unilever.com
    categories: [consumer, food]
    tier: B
    weight: 1.3
    aliases: [dove, hellmann's, ben & jerry's, knorr]
    discover: { rss: true, sitemap: true }
    notes: "unilever.com is 403 to non-browser clients on every path (Akamai). No validated sensor yet."
  - id: nestle
    name: Nestlé
    domain: nestle.com
    categories: [consumer, food]
    tier: B
    weight: 1.3
    aliases: [nestle, nespresso, purina, kitkat]
    products:
      - { name: Nespresso, type: product }
    discover: { rss: true, sitemap: true }
    notes: "nestle.com media pages are 403 to bots (Akamai); sitemap is reachable."
    sensors:
      - { name: sitemap, url: "https://www.nestle.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: coca-cola
    name: The Coca-Cola Company
    domain: coca-colacompany.com
    categories: [consumer, food]
    tier: B
    weight: 1.3
    aliases: [coca-cola, coke, sprite, fanta]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.coca-colacompany.com exposes no RSS."
    sensors:
      - { name: media center, url: "https://www.coca-colacompany.com/media-center", type: HTML, connector: http, tier: B }
      - { name: corporate sitemap (us-en), url: "https://www.coca-colacompany.com/content/corporate.sitemap.us-en-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 2000 } }
  - id: pepsico
    name: PepsiCo
    domain: pepsico.com
    categories: [consumer, food]
    tier: B
    weight: 1.3
    aliases: [pepsi, frito-lay, gatorade, quaker]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.pepsico.com and pepsico.com expose no RSS."
    sensors:
      - { name: newsroom, url: "https://www.pepsico.com/newsroom", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.pepsico.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: mondelez
    name: Mondelēz International
    domain: mondelezinternational.com
    categories: [consumer, food]
    tier: B
    weight: 1.1
    aliases: [mondelez, oreo, cadbury, toblerone]
    discover: { rss: true, sitemap: true }
    notes: "ir.mondelezinternational.com (Q4) is 403 to bots."
    sensors:
      - { name: sitemap, url: "https://www.mondelezinternational.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: kraft-heinz
    name: Kraft Heinz
    domain: kraftheinzcompany.com
    categories: [consumer, food]
    tier: B
    aliases: [kraft, heinz]
    discover: { rss: true, sitemap: true }
    notes: "news.kraftheinzcompany.com and ir.kraftheinzcompany.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: general-mills
    name: General Mills
    domain: generalmills.com
    categories: [consumer, food]
    tier: B
    aliases: [cheerios, pillsbury, häagen-dazs]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.generalmills.com (Q4) behind a Cloudflare challenge; generalmills.com news pages are client-rendered — sitemap only."
    sensors:
      - { name: sitemap, url: "https://www.generalmills.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: kellanova
    name: Kellanova
    domain: kellanova.com
    categories: [consumer, food]
    tier: C
    aliases: [kellogg's, kellogg, pringles]
    discover: { rss: true, sitemap: true }
    notes: "kellanova.com answers 405 to bots; investor.kellanova.com (Q4) likewise. No validated sensor yet."
  - id: mars
    name: Mars, Incorporated
    domain: mars.com
    categories: [consumer, food]
    tier: B
    aliases: [mars inc, m&m's, snickers, pedigree, royal canin]
    discover: { rss: true, sitemap: true }
    notes: "mars.com news pages are 403 to bots; sitemap is reachable."
    sensors:
      - { name: sitemap, url: "https://www.mars.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
  - id: danone
    name: Danone
    domain: danone.com
    categories: [consumer, food]
    tier: B
    aliases: [activia, evian, alpro]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: press releases, url: "https://www.danone.com/newsroom/press-releases.html", type: HTML, connector: http, tier: B }
  - id: ab-inbev
    name: AB InBev
    domain: ab-inbev.com
    categories: [consumer, food]
    tier: B
    weight: 1.1
    aliases: [anheuser-busch inbev, anheuser-busch, budweiser, stella artois, corona]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "ab-inbev.com news pages are client-rendered (React shell) and the sitemap 404s. No validated sensor yet."
  - id: diageo
    name: Diageo
    domain: diageo.com
    categories: [consumer, food]
    tier: B
    aliases: [johnnie walker, guinness, smirnoff, tanqueray]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://www.diageo.com/en/rss/press-releases", type: RSS, connector: rss, tier: B }
  - id: heineken
    name: Heineken
    domain: theheinekencompany.com
    categories: [consumer, food]
    tier: B
    aliases: [heineken n.v.]
    discover: { rss: true, sitemap: true }
    notes: "theheinekencompany.com is 403 to bots (Akamai). No validated sensor yet."
  - id: molson-coors
    name: Molson Coors
    domain: molsoncoors.com
    categories: [consumer, food]
    tier: B
    aliases: [molson, coors, miller lite]
    discover: { rss: true, sitemap: true }
    notes: "ir.molsoncoors.com (Q4) behind a Cloudflare challenge; the corporate site feed works."
    sensors:
      - { name: news feed, url: "https://www.molsoncoors.com/rss.xml", type: RSS, connector: rss, tier: B }
  - id: constellation-brands
    name: Constellation Brands
    domain: cbrands.com
    categories: [consumer, food]
    tier: B
    aliases: [constellation, modelo, corona usa, kim crawford]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://www.cbrands.com/blogs/press-releases.atom", type: ATOM, connector: rss, tier: B }
  - id: saputo
    name: Saputo
    domain: saputo.com
    categories: [consumer, food]
    tier: B
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news sitemap, url: "https://www.saputo.com/news-sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: lassonde
    name: Lassonde Industries
    domain: lassonde.com
    categories: [consumer, food]
    tier: C
    aliases: [lassonde, oasis]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.lassonde.com/en/feed/", type: RSS, connector: rss, tier: C }
  - id: agropur
    name: Agropur
    domain: agropur.com
    categories: [consumer, food, agriculture]
    tier: C
    aliases: [natrel, oka]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news, url: "https://www.agropur.com/en/news", type: HTML, connector: http, tier: C }
  - id: colgate-palmolive
    name: Colgate-Palmolive
    domain: colgatepalmolive.com
    categories: [consumer]
    tier: B
    aliases: [colgate, palmolive, hill's pet nutrition]
    discover: { rss: true, sitemap: true }
    notes: "colgatepalmolive.com and investor.colgatepalmolive.com are 403 to bots. No validated sensor yet."
  - id: kimberly-clark
    name: Kimberly-Clark
    domain: kimberly-clark.com
    categories: [consumer]
    tier: B
    aliases: [kleenex, huggies, kotex, scott]
    discover: { rss: true, sitemap: true }
    notes: "kimberly-clark.com and investor.kimberly-clark.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: clorox
    name: The Clorox Company
    domain: thecloroxcompany.com
    categories: [consumer]
    tier: B
    aliases: [clorox, burt's bees, brita, glad]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news feed, url: "https://www.thecloroxcompany.com/feed/", type: RSS, connector: rss, tier: B }
      - { name: newsroom, url: "https://www.thecloroxcompany.com/newsroom/", type: HTML, connector: http, tier: B }
  - id: reckitt
    name: Reckitt
    domain: reckitt.com
    categories: [consumer, health]
    tier: B
    aliases: [reckitt benckiser, dettol, lysol, durex, nurofen]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: news, url: "https://www.reckitt.com/news/", type: HTML, connector: http, tier: B }
  - id: henkel
    name: Henkel
    domain: henkel.com
    categories: [consumer]
    tier: B
    aliases: [persil, schwarzkopf, loctite, pritt]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: press releases feed, url: "https://www.henkel.com/service/en/33922/asFeed/index.xml", type: RSS, connector: rss, tier: B }
  - id: beiersdorf
    name: Beiersdorf
    domain: beiersdorf.com
    categories: [consumer]
    tier: B
    aliases: [nivea, eucerin, la prairie, tesa]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: press releases, url: "https://www.beiersdorf.com/newsroom/press-information/all-press-releases", type: HTML, connector: http, tier: B }
  - id: shiseido
    name: Shiseido
    domain: shiseido.com
    homepage: https://corp.shiseido.com
    categories: [consumer]
    tier: C
    aliases: [nars, drunk elephant]
    discover: { rss: true, sitemap: true }
    notes: "corp.shiseido.com exposes no feed and its English newsroom 404s on the usual paths. No validated sensor yet."
  - id: whirlpool
    name: Whirlpool Corporation
    domain: whirlpoolcorp.com
    categories: [consumer, consumer-tech]
    tier: B
    aliases: [whirlpool, kitchenaid, maytag]
    discover: { rss: true, sitemap: true }
    notes: "investors.whirlpoolcorp.com (Q4) behind a Cloudflare challenge; whirlpoolcorp.com/news 404. No validated sensor yet."
  - id: electrolux
    name: Electrolux Group
    domain: electroluxgroup.com
    categories: [consumer, consumer-tech]
    tier: B
    aliases: [electrolux, frigidaire, aeg]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.electroluxgroup.com/en/feed", type: RSS, connector: rss, tier: B }
  - id: dyson
    name: Dyson
    domain: dyson.com
    categories: [consumer, consumer-tech]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "dyson.com newsroom is 403 to bots. No validated sensor yet."
  - id: philips
    name: Philips
    domain: philips.com
    categories: [consumer, consumer-tech, health]
    tier: B
    weight: 1.1
    aliases: [royal philips, koninklijke philips]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: news feed, url: "https://www.philips.com/content/corporate/en_AA/feed.rss.xml?pageSize=15&startIndex=0&src=/content/corporate/en_AA/about/news/archive&sortMode=createdDate", type: RSS, connector: rss, tier: B }
  - id: sonos
    name: Sonos
    domain: sonos.com
    homepage: https://newsroom.sonos.com
    categories: [consumer-tech, consumer]
    tier: B
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://newsroom.sonos.com/press_releases.atom", type: ATOM, connector: rss, tier: B }
  - id: gopro
    name: GoPro
    domain: gopro.com
    categories: [consumer-tech, consumer]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "gopro.com news and investor.gopro.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: garmin
    name: Garmin
    domain: garmin.com
    categories: [consumer-tech, consumer]
    tier: B
    weight: 1.1
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: newsroom feed, url: "https://www.garmin.com/en-US/newsroom/feed/", type: RSS, connector: rss, tier: B }
  - id: peloton
    name: Peloton
    domain: onepeloton.com
    categories: [consumer-tech, consumer]
    tier: C
    aliases: [peloton interactive]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investor.onepeloton.com is 403 to bots."
    sensors:
      - { name: blog, url: "https://www.onepeloton.com/blog", type: HTML, connector: http, tier: C }
  - id: mattel
    name: Mattel
    domain: mattel.com
    homepage: https://corporate.mattel.com
    categories: [consumer]
    tier: B
    aliases: [barbie, hot wheels, fisher-price]
    products:
      - { name: Barbie, type: product }
    discover: { rss: true, sitemap: true }
    notes: "investors.mattel.com (Q4) behind a Cloudflare challenge; corporate sitemap is reachable."
    sensors:
      - { name: corporate sitemap, url: "https://corporate.mattel.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: hasbro
    name: Hasbro
    domain: hasbro.com
    categories: [consumer, gaming]
    tier: B
    aliases: [wizards of the coast, monopoly, nerf]
    discover: { rss: true, sitemap: true }
    notes: "newsroom.hasbro.com and investor.hasbro.com are 403 to bots. No validated sensor yet."
  - id: lego
    name: The LEGO Group
    domain: lego.com
    categories: [consumer]
    tier: B
    weight: 1.1
    aliases: [lego]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: newsroom, url: "https://www.lego.com/en-ca/aboutus/newsroom", type: HTML, connector: http, tier: B }
      - { name: local news sitemap, url: "https://www.lego.com/local-news/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: yeti
    name: YETI
    domain: yeti.com
    categories: [consumer]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "yeti.com press pages are 403 to bots. No validated sensor yet."
  - id: stanley
    name: Stanley 1913
    domain: stanley1913.com
    categories: [consumer]
    tier: C
    aliases: [stanley, stanley cup tumbler, pmi worldwide]
    discover: { rss: true, sitemap: true }
    sensors:
      - { name: stories feed, url: "https://www.stanley1913.com/blogs/stanley-story.atom", type: ATOM, connector: rss, tier: C }
  - id: crocs
    name: Crocs
    domain: crocs.com
    categories: [consumer, retail]
    tier: C
    aliases: [heydude]
    discover: { rss: true, sitemap: true }
    notes: "investors.crocs.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: vf-corp
    name: VF Corporation
    domain: vfc.com
    categories: [consumer, retail]
    tier: B
    aliases: [vf corp, the north face, vans, timberland]
    products:
      - { name: The North Face, type: product }
      - { name: Vans, type: product }
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://www.vfc.com/investors/news-events-presentations/press-releases/rss", type: RSS, connector: rss, tier: B }
  - id: levi-strauss
    name: Levi Strauss & Co.
    domain: levistrauss.com
    categories: [consumer, retail]
    tier: B
    aliases: [levi's, levis, dockers]
    discover: { rss: true }
    notes: "investors.levistrauss.com (Q4) behind a Cloudflare challenge; corporate WordPress feed works."
    sensors:
      - { name: news feed, url: "https://www.levistrauss.com/feed/", type: RSS, connector: rss, tier: B }
  - id: gap
    name: Gap Inc.
    domain: gapinc.com
    categories: [consumer, retail]
    tier: B
    aliases: [gap, old navy, banana republic, athleta]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.gapinc.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: newsroom, url: "https://www.gapinc.com/en-us/news", type: HTML, connector: http, tier: B }
  - id: abercrombie
    name: Abercrombie & Fitch Co.
    domain: abercrombie.com
    homepage: https://corporate.abercrombie.com
    categories: [consumer, retail]
    tier: C
    aliases: [abercrombie, hollister]
    discover: { rss: true, pages: true }
    notes: "abercrombieandfitchcompany.gcs-web.com feeds are 403 to bots."
    sensors:
      - { name: news, url: "https://corporate.abercrombie.com/news", type: HTML, connector: http, tier: C }
  - id: ralph-lauren
    name: Ralph Lauren
    domain: ralphlauren.com
    homepage: https://corporate.ralphlauren.com
    categories: [consumer, retail]
    tier: B
    aliases: [polo ralph lauren]
    discover: { rss: true, pages: true }
    sensors:
      - { name: newsroom, url: "https://corporate.ralphlauren.com/newsroom", type: HTML, connector: http, tier: B }
  - id: tapestry
    name: Tapestry
    domain: tapestry.com
    categories: [consumer, retail]
    tier: B
    aliases: [coach, kate spade, stuart weitzman]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.tapestry.com/feed/", type: RSS, connector: rss, tier: B }
  - id: capri-holdings
    name: Capri Holdings
    domain: capriholdings.com
    categories: [consumer, retail]
    tier: C
    aliases: [capri, michael kors, versace, jimmy choo]
    discover: { rss: true, sitemap: true }
    notes: "capriholdings.com is 403 to bots. No validated sensor yet."

  # ───────────────────────── C · Restaurants ─────────────────────────
  - id: mcdonalds
    name: McDonald's
    domain: mcdonalds.com
    homepage: https://corporate.mcdonalds.com
    categories: [food, retail]
    tier: B
    weight: 1.3
    aliases: [mcdonald's, mcdonalds, mcd]
    discover: { rss: true, sitemap: true }
    notes: "corporate.mcdonalds.com and mcdonalds.com time out for non-browser clients (Akamai); investors.mcdonalds.com unreachable. No validated sensor yet."
  - id: starbucks
    name: Starbucks
    domain: starbucks.com
    homepage: https://about.starbucks.com
    categories: [food, retail]
    tier: B
    weight: 1.2
    discover: { rss: true, sitemap: true }
    notes: "about.starbucks.com / stories.starbucks.com and investor.starbucks.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: yum-brands
    name: Yum! Brands
    domain: yum.com
    categories: [food, retail]
    tier: B
    aliases: [yum, kfc, taco bell, pizza hut]
    products:
      - { name: KFC, type: product }
      - { name: Taco Bell, type: product }
      - { name: Pizza Hut, type: product }
    discover: { rss: true, pages: true }
    notes: "investors.yum.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: news, url: "https://www.yum.com/wps/portal/yumbrands/Yumbrands/news", type: HTML, connector: http, tier: B }
  - id: restaurant-brands
    name: Restaurant Brands International
    domain: rbi.com
    categories: [food, retail]
    tier: B
    weight: 1.1
    aliases: [rbi, tim hortons, burger king, popeyes, firehouse subs]
    products:
      - { name: Tim Hortons, type: product, aliases: [tims] }
      - { name: Burger King, type: product }
      - { name: Popeyes, type: product }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "rbi.com (Q4) behind a Cloudflare challenge; timhortons.ca/news is a client-rendered shell (validator: thin). No validated sensor yet."
  - id: chipotle
    name: Chipotle Mexican Grill
    domain: chipotle.com
    homepage: https://newsroom.chipotle.com
    categories: [food, retail]
    tier: B
    aliases: [chipotle]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://newsroom.chipotle.com/press-releases?pagetemplate=rss", type: RSS, connector: rss, tier: B }
  - id: dominos
    name: Domino's Pizza
    domain: dominos.com
    homepage: https://ir.dominos.com
    categories: [food, retail]
    tier: B
    aliases: [dominos, domino's]
    discover: { rss: true, sitemap: true }
    notes: "ir.dominos.com is 403 to bots. No validated sensor yet."
  - id: subway
    name: Subway
    domain: subway.com
    homepage: https://newsroom.subway.com
    categories: [food, retail]
    tier: B
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://newsroom.subway.com/Press-Releases?pagetemplate=rss", type: RSS, connector: rss, tier: B }
  - id: mty-group
    name: MTY Food Group
    domain: mtygroup.com
    categories: [food, retail]
    tier: C
    aliases: [mty, thaï express, valentine, cold stone]
    discover: { rss: true, sitemap: true }
    notes: "mtygroup.com WordPress feeds (all languages/categories) are empty; press releases live behind a client-rendered investors page. No validated sensor yet."
  - id: aw-canada
    name: A&W Canada
    domain: aw.ca
    homepage: https://web.aw.ca
    categories: [food, retail]
    tier: C
    aliases: [a&w, a&w food services]
    discover: { rss: true, sitemap: true }
    notes: "web.aw.ca newsroom is a client-rendered shell. No validated sensor yet."
  - id: st-hubert
    name: St-Hubert
    domain: st-hubert.com
    categories: [food, retail]
    tier: C
    aliases: [rôtisseries st-hubert]
    discover: { rss: true, sitemap: true }
    notes: "st-hubert.com is 403 to bots (news, press, sitemap). No validated sensor yet."
  - id: wendys
    name: Wendy's
    domain: wendys.com
    homepage: https://www.irwendys.com
    categories: [food, retail]
    tier: B
    aliases: [wendys]
    discover: { rss: true, sitemap: true }
    notes: "irwendys.com (Q4) behind a Cloudflare challenge; wendys.com has no feed. No validated sensor yet."
  - id: darden
    name: Darden Restaurants
    domain: darden.com
    categories: [food, retail]
    tier: C
    aliases: [olive garden, longhorn steakhouse]
    discover: { rss: true, sitemap: true }
    notes: "investor.darden.com (Q4) behind a Cloudflare challenge; darden.com newsroom 404. No validated sensor yet."
  - id: chick-fil-a
    name: Chick-fil-A
    domain: chick-fil-a.com
    categories: [food, retail]
    tier: B
    discover: { rss: true }
    sensors:
      - { name: stories feed, url: "https://www.chick-fil-a.com/feed", type: RSS, connector: rss, tier: B }
  - id: inspire-brands
    name: Inspire Brands
    domain: inspirebrands.com
    categories: [food, retail]
    tier: B
    aliases: [dunkin, dunkin', arby's, buffalo wild wings, sonic, baskin-robbins, jimmy john's]
    products:
      - { name: Dunkin', type: product, aliases: [dunkin, dunkin donuts] }
      - { name: Arby's, type: product }
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://inspirebrands.com/feed/", type: RSS, connector: rss, tier: B }

  # ───────────────────────── D · Hospitality & travel ─────────────────────────
  - id: marriott
    name: Marriott International
    domain: marriott.com
    homepage: https://news.marriott.com
    categories: [travel]
    tier: B
    weight: 1.2
    aliases: [marriott, bonvoy, sheraton, westin, ritz-carlton]
    products:
      - { name: Marriott Bonvoy, type: service, aliases: [bonvoy] }
    discover: { rss: true, sitemap: true }
    notes: "news.marriott.com is fully client-rendered (2.5 KB shell); investors.marriott.com unreachable. No validated sensor yet."
  - id: hilton
    name: Hilton
    domain: hilton.com
    homepage: https://stories.hilton.com
    categories: [travel]
    tier: B
    weight: 1.2
    aliases: [hilton worldwide, hilton honors, waldorf astoria, doubletree]
    discover: { rss: true }
    sensors:
      - { name: stories feed, url: "https://stories.hilton.com/feed", type: RSS, connector: rss, tier: B }
  - id: hyatt
    name: Hyatt
    domain: hyatt.com
    homepage: https://newsroom.hyatt.com
    categories: [travel]
    tier: B
    aliases: [hyatt hotels, world of hyatt]
    discover: { rss: true }
    notes: "investors.hyatt.com (Q4) behind a Cloudflare challenge; newsroom RSS works."
    sensors:
      - { name: news releases feed, url: "https://newsroom.hyatt.com/news-releases?pagetemplate=rss", type: RSS, connector: rss, tier: B }
  - id: ihg
    name: IHG Hotels & Resorts
    domain: ihgplc.com
    categories: [travel]
    tier: B
    aliases: [ihg, intercontinental, holiday inn, crowne plaza]
    discover: { rss: true, sitemap: true }
    notes: "ihgplc.com is 403 to bots on news and RSS paths (Akamai). No validated sensor yet."
  - id: accor
    name: Accor
    domain: accor.com
    homepage: https://group.accor.com
    categories: [travel]
    tier: B
    aliases: [accorhotels, ibis, novotel, sofitel, fairmont]
    discover: { rss: true, sitemap: true }
    notes: "press.accor.com feed is 403 to bots; group.accor.com exposes no feed. No validated sensor yet."
  - id: wyndham
    name: Wyndham Hotels & Resorts
    domain: wyndhamhotels.com
    homepage: https://corporate.wyndhamhotels.com
    categories: [travel]
    tier: B
    aliases: [wyndham, days inn, la quinta, super 8]
    discover: { rss: true }
    sensors:
      - { name: news releases feed, url: "https://corporate.wyndhamhotels.com/news-releases/feed/", type: RSS, connector: rss, tier: B }
  - id: four-seasons
    name: Four Seasons
    domain: fourseasons.com
    homepage: https://press.fourseasons.com
    categories: [travel]
    tier: C
    aliases: [four seasons hotels and resorts]
    discover: { rss: true, pages: true }
    sensors:
      - { name: news releases, url: "https://press.fourseasons.com/news-releases/", type: HTML, connector: http, tier: C }
  - id: airbnb
    name: Airbnb
    domain: airbnb.com
    homepage: https://news.airbnb.com
    categories: [travel, technology]
    tier: B
    weight: 1.3
    discover: { rss: true, sitemap: true, pages: true }
    notes: "news.airbnb.com has no RSS; investors.airbnb.com exposes no feed."
    sensors:
      - { name: newsroom sitemap, url: "https://news.airbnb.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B, config: { maxUrls: 3000 } }
      - { name: crawler policy (robots.txt), url: "https://www.airbnb.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: booking-holdings
    name: Booking Holdings
    domain: booking.com
    homepage: https://www.bookingholdings.com
    categories: [travel, technology]
    tier: B
    weight: 1.3
    aliases: [booking, booking.com, priceline, agoda, kayak, opentable, rentalcars]
    products:
      - { name: Booking.com, type: service }
      - { name: Priceline, type: service }
      - { name: Agoda, type: service }
      - { name: OpenTable, type: service }
    discover: { rss: true, sitemap: true }
    notes: "ir.bookingholdings.com (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.booking.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: kayak
    name: KAYAK
    domain: kayak.com
    categories: [travel, technology]
    tier: C
    aliases: [kayak]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.kayak.com/news/feed/", type: RSS, connector: rss, tier: C }
  - id: expedia
    name: Expedia Group
    domain: expedia.com
    homepage: https://www.expediagroup.com
    categories: [travel, technology]
    tier: B
    weight: 1.2
    aliases: [expedia, hotels.com, vrbo, trivago, orbitz, travelocity]
    products:
      - { name: Vrbo, type: service }
      - { name: Hotels.com, type: service }
    discover: { rss: true, sitemap: true }
    notes: "expediagroup.com media/IR pages (Q4) behind a Cloudflare challenge."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.expedia.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: tripadvisor
    name: Tripadvisor
    domain: tripadvisor.com
    categories: [travel, internet]
    tier: B
    aliases: [trip advisor, viator, thefork]
    discover: { rss: true, sitemap: true }
    notes: "ir.tripadvisor.com is 403 to bots."
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.tripadvisor.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: trip-com
    name: Trip.com Group
    domain: trip.com
    homepage: https://investors.trip.com
    categories: [travel, internet]
    tier: B
    aliases: [trip.com, ctrip, skyscanner, qunar]
    products:
      - { name: Skyscanner, type: service }
    discover: { rss: true, sitemap: true }
    notes: "investors.trip.com is 403 to bots; skyscanner.net serves a captcha. No validated sensor yet."
  - id: hopper
    name: Hopper
    domain: hopper.com
    homepage: https://media.hopper.com
    categories: [travel, technology]
    tier: C
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: media room, url: "https://media.hopper.com/", type: HTML, connector: http, tier: C }
  - id: carnival
    name: Carnival Corporation
    domain: carnivalcorp.com
    categories: [travel]
    tier: B
    weight: 1.1
    aliases: [carnival, carnival cruise line, princess cruises, holland america, costa, aida, p&o cruises]
    discover: { rss: true }
    sensors:
      - { name: news feed, url: "https://www.carnivalcorp.com/feed/", type: RSS, connector: rss, tier: B }
  - id: royal-caribbean
    name: Royal Caribbean Group
    domain: royalcaribbeangroup.com
    categories: [travel]
    tier: B
    weight: 1.1
    aliases: [royal caribbean, celebrity cruises, silversea]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "rclinvestor.com exposes no RSS."
    sensors:
      - { name: news, url: "https://www.royalcaribbeangroup.com/news", type: HTML, connector: http, tier: B }
  - id: norwegian-cruise
    name: Norwegian Cruise Line Holdings
    domain: nclhltd.com
    categories: [travel]
    tier: B
    aliases: [norwegian cruise line, ncl, oceania cruises, regent seven seas]
    discover: { rss: true }
    sensors:
      - { name: press releases feed, url: "https://www.nclhltd.com/investors/news-events/press-releases/rss", type: RSS, connector: rss, tier: B }
  - id: msc-cruises
    name: MSC Cruises
    domain: msccruises.com
    categories: [travel]
    tier: C
    aliases: [msc]
    discover: { rss: true, sitemap: true }
    notes: "msccruises.com answers 401 to bots. No validated sensor yet."
  - id: vail-resorts
    name: Vail Resorts
    domain: vailresorts.com
    homepage: https://news.vailresorts.com
    categories: [travel, sports]
    tier: C
    aliases: [vail, epic pass, whistler blackcomb]
    discover: { rss: true, sitemap: true }
    notes: "investors.vailresorts.com is 403 to bots; news.vailresorts.com exposes no RSS. No validated sensor yet."
  - id: club-med
    name: Club Med
    domain: clubmed.com
    homepage: https://corporate.clubmed
    categories: [travel]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "corporate.clubmed feed is 403 to bots. No validated sensor yet."
  - id: transat
    name: Transat A.T.
    domain: transat.com
    categories: [travel, aviation]
    tier: C
    aliases: [air transat, transat]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: media, url: "https://www.transat.com/en-CA/corporate/media", type: HTML, connector: http, tier: C }
  - id: sunwing
    name: Sunwing
    domain: sunwing.ca
    categories: [travel, aviation]
    tier: C
    aliases: [sunwing vacations, westjet vacations]
    discover: { rss: true, sitemap: true }
    notes: "sunwing.ca exposes no press page or feed reachable by bots. No validated sensor yet."
  - id: uber
    name: Uber
    domain: uber.com
    categories: [travel, transport, technology]
    tier: B
    weight: 1.3
    aliases: [uber technologies, uber eats]
    products:
      - { name: Uber Eats, type: service }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investor.uber.com (Q4) behind a Cloudflare challenge; uber.com newsroom feed paths answer 406."
    sensors:
      - { name: newsroom (US), url: "https://www.uber.com/us/en/newsroom/", type: HTML, connector: http, tier: B }
      - { name: crawler policy (robots.txt), url: "https://www.uber.com/robots.txt", type: FILE, connector: http, tier: D }
  - id: lyft
    name: Lyft
    domain: lyft.com
    categories: [travel, transport, technology]
    tier: B
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investor.lyft.com exposes no RSS."
    sensors:
      - { name: blog, url: "https://www.lyft.com/blog", type: HTML, connector: http, tier: B }
  - id: doordash
    name: DoorDash
    domain: doordash.com
    homepage: https://about.doordash.com
    categories: [food, technology, commerce]
    tier: B
    weight: 1.1
    aliases: [dashpass, wolt]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "ir.doordash.com (Q4) and doordash.com robots.txt behind a Cloudflare challenge."
    sensors:
      - { name: news, url: "https://about.doordash.com/en-us/news", type: HTML, connector: http, tier: B }
  - id: deliveroo
    name: Deliveroo
    domain: deliveroo.co.uk
    homepage: https://corporate.deliveroo.co.uk
    categories: [food, technology, commerce]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "corporate.deliveroo.co.uk and deliveroo.news are unreachable for bots. No validated sensor yet."
  - id: just-eat-takeaway
    name: Just Eat Takeaway.com
    domain: justeattakeaway.com
    categories: [food, technology, commerce]
    tier: C
    aliases: [just eat, takeaway.com, skip the dishes, skipthedishes, lieferando, thuisbezorgd]
    products:
      - { name: SkipTheDishes, type: service, aliases: [skip] }
    discover: { rss: true, sitemap: true }
    notes: "justeattakeaway.com newsroom and RSS behind a Cloudflare challenge; skipthedishes.com/news 403. No validated sensor yet."
  - id: grab
    name: Grab
    domain: grab.com
    categories: [travel, transport, technology, commerce]
    tier: B
    aliases: [grab holdings, grabfood]
    discover: { rss: true }
    sensors:
      - { name: press feed, url: "https://www.grab.com/sg/press/feed/", type: RSS, connector: rss, tier: B }
  - id: bolt
    name: Bolt
    domain: bolt.eu
    categories: [travel, transport, technology]
    tier: C
    aliases: [bolt technology, taxify]
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: blog, url: "https://bolt.eu/en/blog/", type: HTML, connector: http, tier: C }
  - id: getaround
    name: Getaround
    domain: getaround.com
    categories: [travel, transport]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "getaround.com blog and feed redirect to the homepage. No validated sensor yet."
  - id: turo
    name: Turo
    domain: turo.com
    categories: [travel, transport]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "turo.com blog behind a Cloudflare challenge. No validated sensor yet."
  - id: hertz
    name: Hertz
    domain: hertz.com
    homepage: https://newsroom.hertz.com
    categories: [travel, transport]
    tier: B
    aliases: [hertz global, dollar, thrifty]
    discover: { rss: true }
    sensors:
      - { name: newsroom feed, url: "https://newsroom.hertz.com/feed/", type: RSS, connector: rss, tier: B }
  - id: avis-budget
    name: Avis Budget Group
    domain: avisbudgetgroup.com
    categories: [travel, transport]
    tier: B
    aliases: [avis, budget, zipcar]
    products:
      - { name: Zipcar, type: service }
    discover: { rss: true, sitemap: true, pages: true }
    notes: "ir.avisbudgetgroup.com is 403 to bots."
    sensors:
      - { name: press releases, url: "https://www.avisbudgetgroup.com/home/news-and-media/press-release", type: HTML, connector: http, tier: B }
      - { name: sitemap, url: "https://www.avisbudgetgroup.com/sitemap.xml", type: SITEMAP, connector: sitemap, tier: B }
  - id: enterprise-mobility
    name: Enterprise Mobility
    domain: enterprisemobility.com
    categories: [travel, transport]
    tier: C
    aliases: [enterprise, enterprise rent-a-car, national car rental, alamo]
    discover: { rss: true, sitemap: true }
    notes: "enterprisemobility.com press pages are 403 to bots. No validated sensor yet."
  - id: sixt
    name: Sixt
    domain: sixt.com
    homepage: https://about.sixt.com
    categories: [travel, transport]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "sixt.com and about.sixt.com press pages behind a Cloudflare challenge. No validated sensor yet."
  - id: amadeus
    name: Amadeus
    domain: amadeus.com
    categories: [travel, technology]
    tier: B
    aliases: [amadeus it group]
    discover: { rss: true, sitemap: true }
    notes: "amadeus.com newsroom is a client-rendered shell; no feed or XML sitemap. No validated sensor yet."
  - id: sabre
    name: Sabre
    domain: sabre.com
    categories: [travel, technology]
    tier: B
    aliases: [sabre corporation]
    discover: { rss: true, sitemap: true, pages: true }
    notes: "investors.sabre.com is 403 to bots; sabre.com releases pages are client-rendered and the feed answers 500. No validated sensor yet."
  - id: travelport
    name: Travelport
    domain: travelport.com
    categories: [travel, technology]
    tier: C
    discover: { rss: true, sitemap: true, pages: true }
    sensors:
      - { name: blog, url: "https://www.travelport.com/blog", type: HTML, connector: http, tier: C }

  # ───────────────────────── E · Automotive retail & loyalty ─────────────────────────
  - id: carmax
    name: CarMax
    domain: carmax.com
    categories: [automotive, retail]
    tier: B
    discover: { rss: true, sitemap: true }
    notes: "investors.carmax.com (Q4) behind a Cloudflare challenge. No validated sensor yet."
  - id: autonation
    name: AutoNation
    domain: autonation.com
    categories: [automotive, retail]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "autonation.com/news 403, newsroom.autonation.com behind a Cloudflare challenge, investors.autonation.com RSS 404. No validated sensor yet."
  - id: carvana
    name: Carvana
    domain: carvana.com
    homepage: https://investors.carvana.com
    categories: [automotive, retail, commerce]
    tier: B
    discover: { rss: true }
    sensors:
      - { name: investor news feed, url: "https://investors.carvana.com/rss/news-releases.xml", type: RSS, connector: rss, tier: B }
  - id: autocanada
    name: AutoCanada
    domain: autocan.ca
    categories: [automotive, retail]
    tier: C
    discover: { rss: true, sitemap: true }
    notes: "autocan.ca is 403 to bots. No validated sensor yet."
  - id: air-miles
    name: AIR MILES
    domain: airmiles.ca
    categories: [retail, commerce]
    tier: C
    aliases: [air miles, airmiles, bmo air miles]
    discover: { rss: true, sitemap: true }
    notes: "airmiles.ca redirects most pages through OAuth; sitemap is the only stable public surface."
    sensors:
      - { name: sitemap, url: "https://www.airmiles.ca/sitemap.xml", type: SITEMAP, connector: sitemap, tier: C, config: { maxUrls: 1000 } }

  # ───────────────────────── F · Extensions of founding-file sources ─────────────────────────
  - id: shopify
    extend: true
    sensors:
      - { name: crawler policy (robots.txt), url: "https://www.shopify.com/robots.txt", type: FILE, connector: http, tier: D }