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%
4.5 KB · 125 lines json
Raw Blame History
1{2  "domains": {3    "comics.org": {4      "minIntervalMs": 2500,5      "concurrency": 1,6      "maxRetries": 0,7      "engines": [8        "api"9      ],10      "country": "US",11      "currency": "USD",12      "backfillMaxPages": 40,13      "refreshClass": "normal",14      "notes": "GCD public JSON API (no key). robots: Allow / (Content-Signal search=yes, ai-train=no). Throttled server-side: ~60 requests/hour per client — HTTP 429 with Retry-After up to ~1,741 s (verified twice 2026-09-08) → maxRetries 0 so the engine never sleeps on Retry-After; connector stops at its checkpoint. HTML pages and /download/ are Cloudflare-challenged + account-gated: not fetched."15    },16    "comiclink.com": {17      "minIntervalMs": 3000,18      "concurrency": 1,19      "engines": [20        "scrapfly"21      ],22      "scrapfly": {23        "renderJs": false,24        "asp": true,25        "country": "us",26        "maxCreditsPerRun": 6027      },28      "country": "US",29      "currency": "USD",30      "backfillMaxPages": 40,31      "refreshClass": "archive",32      "notes": "robots: Allow / (Cloudflare managed content signals search=yes, ai-train=no). Every page served with a Cloudflare managed JS challenge to non-browser clients → Scrapfly without rendering (~1 credit/page). Only /auctions/auctionschedule.asp and /results/generate_highlights.asp are read; item pages hide prices behind login and are never fetched."33    },34    "mycomicshop.com": {35      "minIntervalMs": 3000,36      "concurrency": 1,37      "timeoutMs": 120000,38      "engines": [39        "scrapfly"40      ],41      "scrapfly": {42        "renderJs": false,43        "asp": true,44        "country": "us",45        "maxCreditsPerRun": 4046      },47      "country": "US",48      "currency": "USD",49      "backfillMaxPages": 60,50      "refreshClass": "normal",51      "notes": "robots: /search allowed; /auctions, /newlistings, /restocked, /account, /cart, /wantlist disallowed (never fetched). Imperva Incapsula interstitial for all non-browser clients → Scrapfly (~1 credit per title page, pages are 1–3 MB)."52    },53    "entertainmentearth.com": {54      "minIntervalMs": 3000,55      "concurrency": 1,56      "engines": [57        "scrapfly"58      ],59      "scrapfly": {60        "renderJs": false,61        "asp": true,62        "country": "us",63        "maxCreditsPerRun": 6064      },65      "country": "US",66      "currency": "USD",67      "backfillMaxPages": 80,68      "refreshClass": "normal",69      "notes": "robots: only /news/* admin paths disallowed; /s/ listing pages allowed; sitemap index at /sitemap/sitemap_index.xml. Cloudflare managed challenge for non-browser clients → Scrapfly without rendering (~1 credit/page). Product pages not fetched."70    },71    "miniaturemarket.com": {72      "minIntervalMs": 10000,73      "concurrency": 1,74      "engines": [75        "api"76      ],77      "country": "US",78      "currency": "USD",79      "backfillMaxPages": 60,80      "refreshClass": "normal",81      "notes": "Shopware 6 storefront, plain HTTPS 200 for the bot UA. robots: Crawl-delay 10 (honoured: 10 s interval), Allow ?p= pagination, Disallow ?dir=/?mode=/?limit=/?SID=, /search/, /checkout/, /account/, /wishlist/ (never used)."82    },83    "videogametrader.com": {84      "minIntervalMs": 1500,85      "concurrency": 2,86      "engines": [87        "api"88      ],89      "country": "US",90      "currency": "USD",91      "refreshClass": "normal",92      "notes": "Shopify storefront; public /collections/<handle>/products.json. robots (Shopify standard) allows products/collections; checkout/cart never touched."93    },94    "creations.mattel.com": {95      "minIntervalMs": 1500,96      "concurrency": 2,97      "engines": [98        "api"99      ],100      "country": "US",101      "currency": "USD",102      "refreshClass": "normal",103      "notes": "Shopify storefront (Mattel Creations); public /collections/<handle>/products.json. robots (Shopify standard) allows products/collections; checkout/cart never touched."104    },105    "estarland.com": {106      "minIntervalMs": 3000,107      "concurrency": 1,108      "engines": [109        "scrapfly"110      ],111      "scrapfly": {112        "renderJs": false,113        "asp": true,114        "country": "us",115        "maxCreditsPerRun": 40116      },117      "country": "US",118      "currency": "USD",119      "backfillMaxPages": 60,120      "refreshClass": "normal",121      "notes": "robots: Allow / except /login, /handler*, /checkout, /shopcart, /forgot-password*, /sandbox; sitemap declared. Cloudflare managed challenge for non-browser clients → Scrapfly without rendering (~1 credit/page). Product pages not fetched."122    }123  }124}125