{ "openapi": "3.0.1", "info": { "title": "Waitrose Product Scraper", "description": "Extract grocery products from Waitrose.com — names, prices, unit prices, offers, reviews, categories, and images. Search, category browse, and offers modes with optional price-change monitoring.", "version": "1.0", "x-build-id": "emoJ4mPLkCZN9pMWd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/trev0n~waitrose-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-trev0n-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/trev0n~waitrose-scraper/runs": { "post": { "operationId": "runs-sync-trev0n-waitrose-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/trev0n~waitrose-scraper/run-sync": { "post": { "operationId": "run-sync-trev0n-waitrose-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchTerms": { "title": "Search keywords", "type": "array", "description": "Keywords to search Waitrose for. Each keyword is scraped as a separate search. Example: [\"whole milk\", \"sourdough\", \"olive oil\"].", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Waitrose search, category, offers, or product URLs to scrape directly. Category URLs are expanded automatically into their sub-categories. Example: https://www.waitrose.com/ecom/shop/browse/groceries/fresh_and_chilled/milk_butter_and_eggs/milk", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "scrapeOffers": { "title": "Scrape current offers", "type": "boolean", "description": "Also scrape the Waitrose Offers page (products currently on promotion).", "default": false }, "maxResults": { "title": "Maximum products", "minimum": 0, "type": "integer", "description": "Maximum number of products to collect across the whole run (0 = unlimited).", "default": 500 }, "descendCategories": { "title": "Expand sub-categories", "type": "boolean", "description": "When scraping a category, automatically descend into its sub-categories to cover the full catalogue (Waitrose shows only ~48 products per category page).", "default": true }, "maxCategoryDepth": { "title": "Max category depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many levels deep to descend the category tree when expanding sub-categories.", "default": 6 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Maximum number of pages fetched in parallel.", "default": 8 }, "incremental": { "title": "Incremental monitoring", "type": "boolean", "description": "Track changes across runs. The first run is a baseline; later runs emit only products that are new, changed (e.g. price drop), or back in stock — cutting the cost of recurring monitoring by 80–95%.", "default": false }, "stateKey": { "title": "Monitoring state key", "type": "string", "description": "Optional name for the monitoring baseline. Leave empty to derive one from your search configuration. Use distinct keys to track different searches independently." }, "emitUnchanged": { "title": "Emit unchanged products", "type": "boolean", "description": "In incremental mode, also output products whose price and details are unchanged.", "default": false }, "emitExpired": { "title": "Emit expired products", "type": "boolean", "description": "In incremental mode, also output products that disappeared from results since the last run.", "default": false }, "skipReposts": { "title": "Skip reposts", "type": "boolean", "description": "Drop products that are the same as a recently expired one relisted under a new id.", "default": false }, "notify": { "title": "Notifications", "type": "object", "description": "Optional webhook / Telegram / Discord / Slack notifications for new and changed products (used with incremental monitoring)." }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Waitrose is geo-gated to the UK and bot-protected — a GB residential proxy is strongly recommended.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "GB" } } } }, "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 } } } } } } } } } }