{ "openapi": "3.0.1", "info": { "title": "Yellow Pages UAE Scraper", "description": "Scrape UAE business listings from Yello (yellowpages UAE) by category and emirate: name, phone, website, address, geo. MCP-ready. $0.003 per business.", "version": "0.1", "x-build-id": "5PmitzWnZge6noBvh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~yellow-pages-uae-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-yellow-pages-uae-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/khadinakbar~yellow-pages-uae-scraper/runs": { "post": { "operationId": "runs-sync-khadinakbar-yellow-pages-uae-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/khadinakbar~yellow-pages-uae-scraper/run-sync": { "post": { "operationId": "run-sync-khadinakbar-yellow-pages-uae-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": { "categories": { "title": "Categories", "type": "array", "description": "Business categories to scrape from yello.ae, as slugs or plain names (e.g. 'restaurants', 'estate-agents', 'doctors and clinics'). Each is resolved to a yello.ae category listing and paginated. Leave empty if you provide Start URLs instead. NOT a free-text keyword search - use a real directory category.", "items": { "type": "string" } }, "city": { "title": "Emirate / City filter", "enum": [ "", "dubai", "abu-dhabi", "sharjah", "ajman", "ras-al-khaimah", "fujairah", "umm-al-quwain", "al-ain", "jebel-ali-free-zone" ], "type": "string", "description": "Optional emirate or city to restrict category results to (applied as a yello.ae city filter). Pick one value; leave empty to scrape all of the UAE. Only applies to the Categories input above, not to direct company Start URLs. Example: 'dubai'.", "default": "" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Direct yello.ae URLs to scrape, one per line: category pages (https://www.yello.ae/category/), location pages (https://www.yello.ae/location/), or company pages (https://www.yello.ae/company//). Category and location URLs are paginated; company URLs are scraped directly. Use this for precise control. NOT for non-yello.ae domains.", "default": [], "items": { "type": "string" } }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Maximum number of business records to return across the whole run (hard cap on billing). The run stops and finishes gracefully once this many businesses are scraped. Defaults to 1000; set lower for a quick test. Counts final business records, not intermediate listing pages.", "default": 1000 }, "enrichDetails": { "title": "Enrich from detail pages", "type": "boolean", "description": "When true (default), each business's own page is visited to extract full data (phone, website, address, geo, working hours, established year) from its JSON-LD block. When false, only the lighter listing-page fields (name, profile URL, address) are returned - faster and cheaper but less complete. Keep true for lead-generation use cases.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for outbound requests. Defaults to Apify datacenter proxy, which is sufficient because yello.ae has no anti-bot protection. Leave as default unless you have a specific network requirement.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }