{ "openapi": "3.0.1", "info": { "title": "Artsy.net Artist, Artwork & Gallery Scraper", "description": "Artsy.net artist, artwork, and gallery/dealer (\"partner\") scraper via Artsy's own public GraphQL API — real represented-artist and inventory data per gallery, real per-artist aggregate stats with no per-artwork fan-out, plus delta mode.", "version": "0.1", "x-build-id": "Igu1ofkudm4brBbJ1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~artsy-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-artsy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~artsy-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-artsy-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~artsy-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-artsy-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "partners" ], "type": "string", "description": "Scrape artworks, artist profiles, or galleries/dealers (\"partners\" — real represented-artist lists and inventory samples). Each produces a different output shape (see dataset_schema.json).", "default": "artworks" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional list of specific artsy.net artist/artwork/partner URLs (e.g. https://www.artsy.net/artist/andy-warhol) to scrape directly, instead of discovering via the full site sitemap — use whichever kind matches entityType.", "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 — 173K+ artists, millions of artworks, or the full ~5,800-partner directory — raise this or clear it (set to null) for that.", "default": 50 }, "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 artworks/artists/partners to fetch in parallel. Defaults to 25 — validated live against artsy.net with zero blocking well above this (up to 190 req/s in testing). Lower it only if you start seeing errors; there's no anti-bot reason to.", "default": 25 }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. No blocking was observed against artsy.net during scoping even without impersonation, but this defaults to \"chrome\" internally as a safety margin — override only if needed." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Leave off — no anti-bot blocking was found against this site during scoping, so a proxy shouldn't be needed; only turn one on if you start seeing blocks from your own IP reputation.", "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 } } } } } } } } } }