{ "openapi": "3.0.1", "info": { "title": "Australian Real Estate ๐Ÿ’ฐ$1.50๐Ÿ’ฐยท All Major Portals (/w EMAILS)", "description": "[Only ๐Ÿ’ฐ$1.50] Scrape Australian property listings across multiple portals (Domain.com.au + Ray White office subdomains) in one unified output. Auto-classifies any URL. Bundled email harvest from each office's website. Pure HTTP, no browser. REA Group properties excluded by design", "version": "0.0", "x-build-id": "BLXezMJrWQf0p3fUE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~au-property-multi-portal-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-au-property-multi-portal-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~au-property-multi-portal-scraper/runs": { "post": { "operationId": "runs-sync-memo23-au-property-multi-portal-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/memo23~au-property-multi-portal-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-au-property-multi-portal-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": { "startUrls": { "title": "AU property portal URLs", "type": "array", "description": "Full URLs from supported portals. Search/listing URLs are paginated/fanned-out automatically until `Maximum items` is reached. Mix portals freely.", "items": { "type": "string" } }, "harvestEmails": { "title": "Harvest contact emails from each portal's office website", "type": "boolean", "description": "When enabled (default), each row's office `websiteUrl` is followed and any contact emails found on that site are added to `harvestedEmails`. Per-URL deduped across the run โ€” same office website is only fetched once. Adds ~0.3-1s per unique office site. For LJ Hooker, this also follows each listing's agents to their profile pages to capture the agent's email (set on `agents[].email`) and the office contact block (name/address/phone/email/website) โ€” requires `Fetch per-listing agents` to also be on.", "default": true }, "fetchAgentDetails": { "title": "Fetch per-listing agents (LJ Hooker)", "type": "boolean", "description": "When enabled (default), each LJ Hooker listing's detail page is fetched to attach the listing's `agents` (name, title, mobile, profile URL), feature tags and marketing headline โ€” data the LJ Hooker search API doesn't return. Costs one extra request per LJ Hooker row. Turn off for faster, lighter LJ Hooker runs. Other portals already include agents inline, so this only affects LJ Hooker.", "default": true }, "flatten": { "title": "Flatten nested fields for CSV-friendly output", "type": "boolean", "description": "When enabled (default), nested objects (`address`, `office`, `agents`) are expanded to underscore-separated top-level keys (e.g. `address_suburb`, `office_email`). Arrays of objects are JSON-stringified into `*_json` fields. Disable to keep the full nested JSON for code post-processing.", "default": true }, "enrichEmails": { "title": "Enrich with contact emails (experimental, billed per email)", "type": "boolean", "description": "If enabled, finds a contact email for each result from its own website (or by discovering it from the name). Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. Billed per contact email found; only charged when an email is returned, never for misses.", "default": false }, "qualifyByPayment": { "title": "๐Ÿ’ณ Qualify by payment (flag businesses that take money online)", "type": "boolean", "description": "Requires \"Enrich with contact emails\". Scans each business's website โ€” reusing the pages already fetched for email discovery, so no extra cost or time โ€” for payment processors and e-commerce platforms (Stripe, Shopify, PayPal, Paddle, Lemon Squeezy, WooCommerce, Square, Chargebee and more). Adds takesPayments (is this a real paying business?), paymentProcessors (which stack), stripeLiveKey (the public key if exposed) and paymentConfidence. Turn raw contacts into monetization-qualified leads. No extra charge โ€” included with each enriched company.", "default": false }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of properties collected. Domain listings paginate 20 results per page; use this cap to control billing.", "default": 10000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of detail pages processed in parallel. Higher = faster but more proxy bandwidth + higher risk of transient errors. 6-10 is the sweet spot.", "default": 8 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum number of detail pages processed in parallel.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed request is given up. Transient errors (thin or empty bodies) are auto-detected and retried; this counter covers other failures too.", "default": 5 }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty โ€” the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." } } }, "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 } } } } } } } } } }