{ "openapi": "3.0.1", "info": { "title": "Artmajeur.com Artist & Artwork Scraper", "description": "Artmajeur.com artist & artwork scraper with real per-artist rollup stats (avg price, medium mix, sold count) from each artist's full catalog, plus delta mode.", "version": "0.1", "x-build-id": "ite9M0AhBaBJyHDHv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~artmajeur-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-artmajeur-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~artmajeur-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-artmajeur-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~artmajeur-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-artmajeur-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 Artmajeur artist or artwork URLs to scrape directly, instead of discovering via the full site sitemap — use whichever kind matches entityType. For artists specifically, consider artistUrls below instead: it checks each URL against the site's member sitemap and gets its own persisted tracking across repeat runs.", "items": { "type": "string" } }, "artistUrls": { "title": "Artist URL list (verified for entityType=artists)", "type": "array", "description": "Paste a list of specific Artmajeur artist URLs (one per line — paste a .txt file's contents directly, no upload needed) to scrape exactly those artists, instead of crawling the full site. For entityType=\"artists\": each URL is checked against the real member sitemap first (found/not-found is logged; not-found ones are skipped) unless verifyArtistUrls is off, and this list gets its own persisted tracking scope — re-running the same list on a schedule gives real new/changed/delisted detection for just those artists. For entityType=\"artworks\": fetches every artwork for exactly these artists instead of the full artwork sitemap (deliberately unverified — expected to come from a prior entityType=artists run already); pair with minSoldArtworks on an entityType=artists run to first collect the artist URLs you want. Ignored when startUrls is set.", "items": { "type": "string" } }, "verifyArtistUrls": { "title": "Verify artist URL list against sitemap (entityType=artists only)", "type": "boolean", "description": "When artistUrls is set and entityType is \"artists\", check each URL against the real member sitemap before scraping (adds one full sitemap walk, ~2 minutes, regardless of list size) and skip any not found. Turn off to scrape the list as given, unverified. Has no effect for entityType=\"artworks\", which never verifies artistUrls.", "default": true }, "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 — ~3.1 million artworks, or the full ~108K-artist directory — raise this or clear it (set to null) for that. Even at the default concurrency, a full artworks crawl is many hours and a full artists crawl is several hours, purely from data volume (see the concurrency field) — for most uses, a large maxItems (thousands to tens of thousands) is more practical than a truly unbounded run.", "default": 50 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 15, "type": "integer", "description": "How many items to fetch in parallel (the OUTER crawl loop). For entityType=\"artists\" this multiplies with the existing, unchanged per-artist rollup fan-out (up to 25-way internally) — total simultaneous connections can be up to concurrency × 25. Defaults to 8. Load-tested live against artmajeur.com: clean through 15 for both entity types (up to 375 simultaneous connections for artists) — capped there as a safety margin.", "default": 8 }, "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). Set to 1 to skip artists who have never sold anything — useful if you only care about active sellers and want to save on results. Artists are still fully tracked internally either way (delta baseline, delisted-detection), so this only filters what gets pushed to the dataset, not the incremental logic. 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" }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. Artmajeur.com's Cloudflare protection challenges plain (non-impersonated) requests, so this defaults to \"chrome\" internally — override only if that stops working." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Leave off unless you start seeing blocks from your own IP reputation; if so, try residential rather than datacenter groups.", "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 } } } } } } } } } }