{ "openapi": "3.0.1", "info": { "title": "Incollect Dealer & Listing Scraper", "description": "Scrape Incollect.com fine-art, decorative-arts, furniture, and jewelry listings from vetted dealers (price, dimensions, images, dealer link) and dealer/professional profiles (bio, address, tracked inventory), with built-in delta mode. No login required.", "version": "0.1", "x-build-id": "ITiVjxb1YJvjHuQHX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~incollect-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-incollect-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~incollect-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-incollect-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~incollect-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-incollect-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "listings", "dealers" ], "type": "string", "description": "Scrape listings (fine-art, decorative-arts, furniture, and jewelry pieces from vetted dealers, with price/dimensions/images/dealer link) or dealer/professional profiles (bio, address, and a tracked inventory count/category footprint accumulated from listings runs). See dataset_schema.json for the field set of each.", "default": "listings" }, "categories": { "title": "Categories to include", "type": "array", "description": "Optional, listings only: only crawl listings in these categories. This is a real discovery-level filter — each selected category is queried independently via the site's own landing-page API, so a non-matching category is never fetched at all. Leave empty to include all 4 categories.", "items": { "type": "string", "enum": [ "fine-art", "furniture", "decorative-arts", "jewelry" ], "enumTitles": [ "Fine Art", "Furniture & Lighting", "Decorative Arts", "Jewelry" ] } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional, listings only: specific Incollect listing URLs (https://www.incollect.com/listings/{category}/{subcategory}/{slug}) to scrape directly, instead of the normal category-driven discovery. Overrides \"Categories to include\". A startUrls-scoped run cannot detect delistings, update the incremental baseline, or feed the dealer rollup as completely as a full crawl.", "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. The site has ~139,763 real live listings across its 4 categories (Fine Art 22,079 / Furniture & Lighting 79,421 / Decorative Arts 34,150 / Jewelry 4,113) and ~560 dealers. Raise this or clear it (set to null) for a full run, or narrow \"Categories to include\" instead.", "default": 50 }, "mode": { "title": "Incremental mode", "enum": [ "auto", "full", "incremental" ], "type": "string", "description": "Listings only (dealers runs are always a live snapshot). \"auto\" (recommended): full scan on the first run for a given categories scope, incremental (new/changed only) afterwards. \"full\": always push every item and refresh the baseline — schedule this periodically to catch delistings and price changes. \"incremental\": always push only new/changed items. Only a plain, unscoped run (no startUrls, same \"Categories to include\" every time) can detect delistings or update the baseline.", "default": "auto" }, "concurrency": { "title": "Concurrency", "minimum": 1, "type": "integer", "description": "How many pages to fetch in parallel. Defaults to 25 — a real burst test against live incollect.com (100 concurrent single-IP requests) came back with zero blocking of any kind (no 403/429/503, no CAPTCHA), so this is the portfolio's standard default, not a conservative override. Raise if you need faster runs at real scale; there is no known technical rate limit on this site.", "default": 25 }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. Defaults to \"chrome\" internally." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Left off by default: incollect.com showed no IP-based rate limiting at all during investigation (up to 100 concurrent requests from one IP, zero blocks), so a proxy adds cost with no measured benefit here. Enable only 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 } } } } } } } } } }