{ "openapi": "3.0.1", "info": { "title": "Lempertz.com Auction Results & Artist Scraper", "description": "Lempertz.com auction scraper — real realized prices, upcoming estimates, rich provenance detail, and cross-run artist rollups, with delta mode.", "version": "0.1", "x-build-id": "UFmVqJgvf5sofIHFg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~lempertz-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-lempertz-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~lempertz-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-lempertz-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~lempertz-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-lempertz-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "currentAuctions", "auctionResults", "artists" ], "type": "string", "description": "\"currentAuctions\": whatever the site's own /en/auctions.html currently links to — not confirmed to be a clean \"upcoming only\" list, see README. \"auctionResults\": historical, resolved lots with real realized prices (inclusive of buyer's premium) — the full archive by default, the default entityType. \"artists\": a real cross-run artist rollup, accumulated from auctionResults lots as they're crawled (not a fresh crawl of its own — run auctionResults at least once first, ideally a full/unbounded run, or this will push nothing). Each produces a different output shape (see dataset_schema.json).", "default": "auctionResults" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional list of specific Lempertz catalogue URLs (e.g. https://www.lempertz.com/en/catalogues/detail/1296-1-african-and-oceanic-art.html), lot URLs (any lot from the catalogue you want), or bare catalogue ids (e.g. \"1296-1\") to scrape directly, instead of the full sitemap-driven crawl. Ignored for entityType=artists. Scope is always \"custom\", with no delisting-detection or persisted incremental baseline (a hand-picked list is necessarily partial) — leave empty for the full crawl instead.", "items": { "type": "string" } }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after pushing this many dataset items (lots or artists). Defaults to 50 — a fast, cheap preview, and what keeps an unconfigured run within Apify's automated 5-minute QA check. A full auctionResults crawl covers the entire historical archive (439+ catalogues, each with many lots) — raise this or clear it (set to null) for that; note a capped run never updates the incremental baseline (see mode below) or feeds the artist rollup for lots it never reaches.", "default": 50 }, "mode": { "title": "Incremental mode", "enum": [ "auto", "full", "incremental" ], "type": "string", "description": "\"auto\" (recommended): for auctionResults, full scan on the first run for a scope, incremental (new/changed only) afterwards. For currentAuctions specifically, \"auto\" always behaves as a full refresh every run regardless of an existing baseline — upcoming sales are a small, frequently-changing dataset where a full refresh is more useful than a delta. \"full\": always push every item and refresh the baseline. \"incremental\": always push only new/changed items. Only a plain, unscoped crawl (no startUrls) can detect delistings or update the baseline. Has no effect for entityType=artists (every run there just reads the current rollup state).", "default": "auto" }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. No Cloudflare or other bot-management signal was observed anywhere on lempertz.com while building this Actor, so this defaults to \"chrome\" internally — override only if that stops working." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Leave off — this Actor clears the site fine without one in testing so far (it doesn't appear to sit behind Cloudflare or any other bot-management layer at all).", "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 } } } } } } } } } }