SPB Git forge

spb/rareindex

Public
54commits 1branches 0releases
7.1 MBsize
maindefault branch
10 days agolast push
TypeScript 61.9% HTML 37.2% SQL 0.7%
8.6 KB · 266 lines json
Raw Blame History
1{2  "domains": {3    "numisbids.com": {4      "minIntervalMs": 2500,5      "concurrency": 1,6      "engines": [7        "firecrawl"8      ],9      "country": "US",10      "backfillMaxPages": 60,11      "firecrawl": {12        "maxCreditsPerRun": 6013      },14      "notes": "Cloudflare 403 on plain HTTPS → Firecrawl render. robots (*): only wantlist_add/bidlist/bidsubmit/watchlist disallowed (never fetched); ClaudeBot/Bytespider blocked site-wide. Terms https://www.numisbids.com/terms. Prices realized are hammer prices. Scrapfly is deliberately excluded here: its ASP render costs ~80 credits per page while Firecrawl passes the challenge for 1 credit."15    },16    "noonans.co.uk": {17      "minIntervalMs": 2500,18      "concurrency": 1,19      "engines": [20        "firecrawl"21      ],22      "country": "GB",23      "currency": "GBP",24      "timeoutMs": 120000,25      "backfillMaxPages": 40,26      "firecrawl": {27        "maxCreditsPerRun": 4028      },29      "notes": "Cloudflare 'Just a moment' on plain HTTPS → Firecrawl. robots: Allow / with Crawl-delay 2. Archive 1991→ hammer prices. Images © Noonans (URLs only). Scrapfly is deliberately excluded here: its ASP render costs ~80 credits per page while Firecrawl passes the challenge for 1 credit."30    },31    "noble.com.au": {32      "minIntervalMs": 2000,33      "concurrency": 1,34      "engines": [35        "api",36        "firecrawl"37      ],38      "country": "AU",39      "currency": "AUD",40      "timeoutMs": 90000,41      "backfillMaxPages": 20,42      "notes": "Static HTML, robots Allow /. One 1.5–2 MB prices-realised page per sale (1994→). Terms: catalogue text not to be reproduced without permission."43    },44    "spink.com": {45      "minIntervalMs": 1500,46      "concurrency": 1,47      "engines": [48        "api",49        "firecrawl"50      ],51      "country": "GB",52      "currency": "GBP",53      "backfillMaxPages": 120,54      "notes": "robots: Disallow: (all allowed). Cloudflare front, no challenge for the bot UA. One lot page per lot; sale dates only in the /auctions/prices dropdown."55    },56    "kuenker.de": {57      "minIntervalMs": 1500,58      "concurrency": 1,59      "engines": [60        "api",61        "firecrawl"62      ],63      "country": "DE",64      "currency": "EUR",65      "backfillMaxPages": 200,66      "notes": "Shopware. robots disallows /checkout/ /wishlist/ /account/ /store-api/ /widgets/ Merkliste (never fetched); Meta-ExternalAgent blocked. Sitemaps: 29 product sitemaps × 25k lot pages."67    },68    "ngccoin.com": {69      "minIntervalMs": 4000,70      "concurrency": 1,71      "engines": [72        "api",73        "firecrawl"74      ],75      "country": "US",76      "currency": "USD",77      "backfillMaxPages": 20,78      "refreshClass": "archive",79      "notes": "robots Allow / (AhrefsBot blocked). LEGAL: terms-of-use has an automated-access clause → lowest cadence, public retail guide pages only. World price guide behind Cloudflare challenge (not fetched)."80    },81    "api.numista.com": {82      "minIntervalMs": 1500,83      "concurrency": 1,84      "engines": [85        "api"86      ],87      "country": "FR",88      "currency": "EUR",89      "backfillMaxPages": 10,90      "notes": "Official API v3, header Numista-API-Key (NUMISTA_API_KEY). Free plan 2 000 requests/month; 429 = quota. Licence: attribution 'Source: Numista' + N#, no bulk download / no feed re-serving."91    },92    "numista.com": {93      "minIntervalMs": 3000,94      "concurrency": 1,95      "engines": [96        "api"97      ],98      "country": "FR",99      "notes": "Public catalogue HTML not scraped (robots disallow index.php?/?q= searches; values only via the API)."100    },101    "api.collectiblesshowcase.com": {102      "minIntervalMs": 1500,103      "concurrency": 1,104      "engines": [105        "api"106      ],107      "country": "US",108      "currency": "USD",109      "backfillMaxPages": 100,110      "notes": "JSON API of the davidlawrence.com SPA; public tenant header x-client-id (3) resolved from /consumer/client?url=. No robots.txt (404). No buyer's fee at DLRC."111    },112    "davidlawrence.com": {113      "minIntervalMs": 2000,114      "concurrency": 1,115      "engines": [116        "api"117      ],118      "country": "US",119      "currency": "USD",120      "notes": "React SPA; robots.txt serves the SPA shell. Only used for lot URLs (/inventory/<id>) and the client-id lookup."121    },122    "sgbaldwins.com": {123      "minIntervalMs": 1500,124      "concurrency": 1,125      "engines": [126        "api"127      ],128      "country": "GB",129      "currency": "GBP",130      "backfillMaxPages": 60,131      "notes": "Next.js; /_next/data/<buildId>/…json. robots disallows /account/ /auth/ /search /collection_* (not fetched). Hammer + premium explicit per lot."132    },133    "shop.stanleygibbons.com": {134      "minIntervalMs": 1500,135      "concurrency": 1,136      "engines": [137        "api"138      ],139      "country": "GB",140      "currency": "GBP",141      "crawlDepth": 2,142      "backfillMaxPages": 30,143      "notes": "Shopify storefront; robots: public product/collection JSON crawlable. Fixed-price stamp stock."144    },145    "corinphila.ch": {146      "minIntervalMs": 10000,147      "concurrency": 1,148      "engines": [149        "api",150        "firecrawl"151      ],152      "country": "CH",153      "currency": "CHF",154      "timeoutMs": 60000,155      "backfillMaxPages": 20,156      "refreshClass": "archive",157      "notes": "robots: Disallow /geheim, *ajax=1, *admin=1; Crawl-Delay 10 (respected). Static c4ms archive with CHF hammer prices (auctions 12–28, 2016–2024)."158    },159    "auction.corinphila.ch": {160      "minIntervalMs": 10000,161      "concurrency": 1,162      "engines": [163        "api"164      ],165      "country": "CH",166      "notes": "Live WordPress catalogue; lots load via admin-ajax (JS) — not used."167    },168    "sixbid.com": {169      "minIntervalMs": 5000,170      "concurrency": 1,171      "engines": [172        "api"173      ],174      "country": "DE",175      "notes": "Vue SPA; microservice APIs (auctions/lots.sixbid.com) answer HTTP 204 to non-browser UAs; archive is the paid Sixbid Coin Collector's Archive → not crawled."176    },177    "jmbullion.com": {178      "minIntervalMs": 5000,179      "concurrency": 1,180      "engines": [181        "api"182      ],183      "country": "US",184      "currency": "USD",185      "notes": "REJECTED: terms forbid automated retrieval; sitemap geo-403; product pages 401 reCAPTCHA (Webscale). Not crawled."186    },187    "providentmetals.com": {188      "minIntervalMs": 5000,189      "concurrency": 1,190      "engines": [191        "api"192      ],193      "country": "US",194      "currency": "USD",195      "notes": "REJECTED: same platform/terms as JM Bullion; product pages 401 reCAPTCHA. Not crawled."196    },197    "sdbullion.com": {198      "minIntervalMs": 3000,199      "concurrency": 1,200      "engines": [201        "api"202      ],203      "country": "US",204      "currency": "USD",205      "notes": "Magento 2; robots disallow /*? and /catalog/ (no paginated listings); plain category and product URLs allowed (planned listings connector)."206    },207    "banknoteworld.com": {208      "minIntervalMs": 5000,209      "concurrency": 1,210      "engines": [211        "firecrawl"212      ],213      "country": "US",214      "currency": "USD",215      "notes": "X-Cart shop behind a Cloudflare challenge on every page incl. sitemap (403 to plain HTTPS); robots Crawl-delay 10. Planned, not crawled yet."216    },217    "colnect.com": {218      "minIntervalMs": 10000,219      "concurrency": 1,220      "engines": [221        "api"222      ],223      "notes": "REJECTED: robots.txt states automated use is prohibited without a CAPI licence; Anubis proof-of-work interstitial. Not crawled."224    },225    "coinarchives.com": {226      "minIntervalMs": 10000,227      "concurrency": 1,228      "engines": [229        "api"230      ],231      "country": "US",232      "notes": "BLOCKED: archive is a paid subscription (CoinArchives Pro); robots blocks most crawlers. Not crawled."233    },234    "davidfeldman.com": {235      "minIntervalMs": 10000,236      "concurrency": 1,237      "engines": [238        "api"239      ],240      "country": "CH",241      "notes": "BLOCKED: Cloudflare 'Attention Required' 403 for bots. Not crawled."242    },243    "lynknight.com": {244      "minIntervalMs": 3000,245      "concurrency": 1,246      "engines": [247        "api"248      ],249      "country": "US",250      "currency": "USD",251      "notes": "Rails site; no public prices-realized archive (login), catalogue lots via JS endpoint with 'Current Price' only. Rejected."252    },253    "stampauctionnetwork.com": {254      "minIntervalMs": 10000,255      "concurrency": 1,256      "engines": [257        "api",258        "firecrawl"259      ],260      "country": "US",261      "currency": "USD",262      "notes": "robots Crawl-delay 10; Disallow bidform.cfm, exportaAll.cfm, exportaTop.cfm, /admin/. Kelleher connector covers firm V; generic cCatalog3 connector for other firms is planned (POST pagination)."263    }264  }265}266