{ "openapi": "3.0.1", "info": { "title": "Bluethumb.com.au Artist & Artwork Scraper", "description": "Bluethumb.com.au artist & artwork scraper with real per-artist sold/available/total counts read straight from each artist's profile page, no per-artwork fan-out, plus delta mode.", "version": "0.1", "x-build-id": "qtQV5WA0ArXeuqoAy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~bluethumb-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-bluethumb-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~bluethumb-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-bluethumb-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~bluethumb-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-bluethumb-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "entityType": { "title": "Entity type", "enum": [ "artworks", "artists" ], "type": "string", "description": "Scrape artworks or artist profiles. Each produces a different output shape (see dataset_schema.json).", "default": "artworks" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional list of specific Bluethumb artist (https://bluethumb.com.au/{slug}) or artwork (https://bluethumb.com.au/{artist-slug}/Artwork/{artwork-slug}) URLs to scrape directly, instead of discovering via the full site sitemap — use whichever kind matches entityType. A startUrls-scoped run cannot detect delistings or update the incremental baseline.", "items": { "type": "string" } }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after pushing this many dataset items. Defaults to 50 — a fast, cheap preview, and what keeps an unconfigured run within Apify's automated 5-minute QA check. A full, uncapped sitemap crawl covers the entire site (~500,000 artworks, or the full ~19,000-artist directory as of this build) — raise this or clear it (set to null) for that.", "default": 50 }, "minSoldArtworks": { "title": "Minimum sold artworks (artists only)", "minimum": 0, "type": "integer", "description": "Only push artist records with at least this many sold artworks (rollup field sold_artworks, read straight from Bluethumb's own server-computed counts — no extra cost to filter on here, unlike some other actors in this collection). Set to 1 to skip artists who have never sold anything. Artists are still fully tracked internally either way (delta baseline, delisted-detection), so this only filters what gets pushed to the dataset. Ignored when entityType is \"artworks\".", "default": 0 }, "mode": { "title": "Incremental mode", "enum": [ "auto", "full", "incremental" ], "type": "string", "description": "\"auto\" (recommended): full scan on the first run for a given entityType/scope, incremental (new/changed only) afterwards. \"full\": always push every item and refresh the baseline — schedule this periodically to catch delistings. \"incremental\": always push only new/changed items. Only a plain, unscoped sitemap crawl (no startUrls) can detect delistings or update the baseline.", "default": "auto" }, "concurrency": { "title": "Concurrency", "minimum": 1, "type": "integer", "description": "How many artwork/artist detail pages to fetch in parallel. Defaults to 20 — validated live against bluethumb.com.au with zero blocking at concurrency 10/25/40 (only the site's already-known ~4-6% transient HTTP 504 rate, retried automatically). Lower it only if you start seeing errors; there's no anti-bot reason to.", "default": 20 }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. Defaults to \"chrome\" internally — a hedge against Cloudflare bot-management the site runs on at least one route (its internal search API), even though every route this actor actually uses worked cleanly without impersonation in testing. Override only if that stops holding." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Leave off unless you start seeing blocks from your own IP reputation — no anti-bot friction was found on any route this actor uses while building it.", "default": { "useApifyProxy": false } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }