{ "openapi": "3.0.1", "info": { "title": "Carrefour Spain Scraper — Grocery Prices & EAN Data", "description": "Scrape products, prices, unit prices, EAN barcodes, and images from carrefour.es, Carrefour's Spanish grocery storefront. Search any grocery keyword and export clean structured supermarket data.", "version": "0.1", "x-build-id": "hU0DChUl9gwUKPNWC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/studio-amba~carrefour-es-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-studio-amba-carrefour-es-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/studio-amba~carrefour-es-scraper/runs": { "post": { "operationId": "runs-sync-studio-amba-carrefour-es-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/studio-amba~carrefour-es-scraper/run-sync": { "post": { "operationId": "run-sync-studio-amba-carrefour-es-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Search Query", "type": "string", "description": "A Spanish grocery keyword (e.g. 'leche', 'pan', 'cafe', 'huevos'). carrefour.es has no working free-text search endpoint, so this is matched against the site's own category list and the best-matching category is scraped. For precise control, use \"Category URL\" instead." }, "categoryUrl": { "title": "Category URL (optional, overrides Search Query)", "type": "string", "description": "An exact carrefour.es category URL, e.g. https://www.carrefour.es/supermercado/la-despensa/lacteos/leche/cat20093/c. When set, this is scraped directly instead of resolving Search Query to a category." }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of products to return.", "default": 100 }, "fetchDetails": { "title": "Fetch product details (slower)", "type": "boolean", "description": "Visit each product page to enrich results with a confirmed brand, EAN, rating, review count, and full description from structured data. This makes one extra request per product, so runs take longer and cost more. Without this, brand/EAN are only present when carrefour.es's listing tile exposes them (mainly Carrefour-exclusive lines), and rating/review count are never present in the listing.", "default": false }, "brightDataApiKey": { "title": "Bright Data API Key", "type": "string", "description": "Your Bright Data API key for the Web Unlocker zone (web_unlocker1). Required to bypass carrefour.es's Cloudflare Bot Management. Get one at https://brightdata.com. Can also be provided via the BRIGHT_DATA_API_KEY environment variable." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Kept for schema compatibility — page fetching is handled by Bright Data Web Unlocker, so this does not affect scraping." } } }, "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 } } } } } } } } } }