{ "openapi": "3.0.1", "info": { "title": "Artfinder.com Artist & Artwork Scraper", "description": "Artfinder.com artist and artwork scraper with real per-artist rollup stats, a sold-artworks filter, and built-in delta mode.", "version": "0.1", "x-build-id": "n4VWv4Esrw8402Zw5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~artfinder-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-artfinder-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~artfinder-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-artfinder-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~artfinder-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-artfinder-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 Artfinder artist (https://www.artfinder.com/artist/{slug}/) or product (https://www.artfinder.com/product/{slug}/) URLs to scrape directly, instead of discovering via the artist-search API or the product sitemap — use whichever kind matches entityType. A start_urls-scoped run cannot detect delistings or update the incremental baseline (see docs/incremental-mode.md), and for entityType=artists it skips the artist-search pass entirely, so the `country` field is not populated for that scope (see README known gaps).", "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 run covers the entire site (~144,000 artworks, or the full ~3,785-artist directory as of this build — real-tested at ~1.8s/artist including rollup, so under 2 hours end to end) — raise this or clear it 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). 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, 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 run (no startUrls) can detect delistings or update the baseline — see docs/incremental-mode.md.", "default": "auto" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Leave off unless you start seeing blocks from your own IP reputation — this actor's default (plain browser User-Agent, no TLS impersonation) worked cleanly from every network tested 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 } } } } } } } } } }