{ "openapi": "3.0.1", "info": { "title": "Waitrose Scraper - UK Grocery Products & Prices", "description": "Scrape the full Waitrose UK grocery catalogue: names, brands, prices, price-per-unit, promotions, ratings, and images. Full category-tree walk with exact per-category counts. No login or cookies required.", "version": "0.1", "x-build-id": "4bLe0pheImGwJ7HSp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/studio-amba~waitrose-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-studio-amba-waitrose-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/studio-amba~waitrose-scraper/runs": { "post": { "operationId": "runs-sync-studio-amba-waitrose-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/studio-amba~waitrose-scraper/run-sync": { "post": { "operationId": "run-sync-studio-amba-waitrose-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "category": { "title": "Category (optional)", "type": "string", "description": "Scope the run to a single Waitrose grocery department or shelf. Use the slug from the browse URL, e.g. 'fresh_and_chilled', 'food_cupboard/tins_cans_and_packets', or 'frozen'. Leave empty to walk the entire grocery catalogue." }, "searchQuery": { "title": "Search Query (optional)", "type": "string", "description": "Keyword search across the whole Waitrose catalogue, e.g. 'heinz baked beans' or 'oat milk'. When set, this replaces the category walk entirely: only products whose name matches every word of the query are fetched, bounded by Max Products, and Category / full-catalogue mode is skipped. Leave empty to use Category mode instead." }, "maxProducts": { "title": "Max Products", "minimum": 1, "maximum": 60000, "type": "integer", "description": "Maximum number of unique products to return. Use a small value (e.g. 20) for a quick test, or a large value (e.g. 30000) for the full catalogue.", "default": 20 }, "sortBy": { "title": "Sort By", "enum": [ "RECOMMENDED", "PRICE_LOW_TO_HIGH", "PRICE_HIGH_TO_LOW", "NAME" ], "type": "string", "description": "Ordering hint for the listing pages (Waitrose default is RECOMMENDED). Cosmetic — the catalogue walk returns the same set regardless.", "default": "RECOMMENDED" }, "fetchBarcodes": { "title": "Fetch EAN barcodes", "type": "boolean", "description": "Fetch the EAN/GTIN barcode for every product (adds 'ean' and 'barcodes' output fields). Barcodes only exist on Waitrose product detail pages, so this costs ONE EXTRA Bright Data request per product on top of the normal catalogue walk — on a full ~16k-product catalogue that roughly doubles run time and Bright Data spend. Leave off for the fast price-only crawl.", "default": false }, "brightDataApiKey": { "title": "Bright Data API Key", "type": "string", "description": "Your Bright Data API key for the Web Unlocker zone. Required to bypass Waitrose's UK geo-block and Akamai Bot Manager. Get one at https://brightdata.com. Can also be supplied via the BRIGHT_DATA_API_KEY environment variable." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Not used — this actor routes all traffic through Bright Data Web Unlocker (GB), not Apify 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 } } } } } } } } } }