{ "openapi": "3.0.1", "info": { "title": "Amazon Search, Category & Best Sellers Scraper", "description": "Scrape Amazon keyword search, category browse, and Best Sellers across 21 storefronts. Export ASINs, titles, prices, ratings, images, and product URLs.", "version": "0.3", "x-build-id": "7Bodn37EbCYA6cZmP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lentic_clockss~amazon-search-results-collector/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lentic_clockss-amazon-search-results-collector", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lentic_clockss~amazon-search-results-collector/runs": { "post": { "operationId": "runs-sync-lentic_clockss-amazon-search-results-collector", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lentic_clockss~amazon-search-results-collector/run-sync": { "post": { "operationId": "run-sync-lentic_clockss-amazon-search-results-collector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Keywords", "minItems": 0, "maxItems": 10, "type": "array", "description": "Amazon search keywords. Required for keyword mode. Optional for category mode (search within a category). Ignored for pure bestsellers browsing when empty.", "items": { "type": "string" }, "default": [ "usb hub" ] }, "mode": { "title": "Collection mode", "enum": [ "keyword", "category", "bestsellers", "newreleases", "detail" ], "type": "string", "description": "keyword = Amazon search results; category = category browse or in-category search; bestsellers = Best Sellers ranking pages; newreleases = New Releases ranking pages; detail = fetch each detailUrls entry (product pages and/or seller profiles) with full seller lead extraction.", "default": "keyword" }, "detailUrls": { "title": "Detail URLs (for detail mode)", "minItems": 0, "maxItems": 20, "type": "array", "description": "Product (/dp/{ASIN}) or seller profile (/sp?seller={sellerId}) URLs to fetch when mode=detail. Product pages are enriched with the seller profile (business name + business address).", "items": { "type": "string" }, "default": [] }, "scrapeDetails": { "title": "Scrape detail pages for seller leads", "type": "boolean", "description": "Fetch detail pages (PDP) and follow the seller-profile chain to collect seller organization and address leads. On by default.", "default": true }, "enrichDetails": { "title": "Enrich items with seller profile leads", "type": "boolean", "description": "Follow the PDP merchant link to the seller profile (Detailed Seller Information: business name + business address) and merge leads into items. On by default.", "default": true }, "enrichMaxItems": { "title": "Max items to enrich with seller leads", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many list rows (from the top of results) to enrich with seller-profile leads per run (0-20).", "default": 1 }, "market": { "title": "Market", "enum": [ "AE", "AU", "BE", "BR", "CA", "DE", "EG", "ES", "FR", "GB", "IE", "IN", "IT", "JP", "MX", "NL", "PL", "SA", "SE", "SG", "TR", "US", "ZA" ], "type": "string", "description": "Amazon storefront to query.", "default": "US" }, "category": { "title": "Category key", "enum": [ "all", "amazon-devices", "audible", "automotive", "baby", "beauty", "books", "computers", "electronics", "fashion", "garden", "grocery", "handmade", "health", "home", "industrial", "kindle-store", "kitchen", "luggage", "movies-tv", "music", "office-products", "pet-supplies", "software", "sports", "tools", "toys-and-games", "video-games" ], "type": "string", "description": "Stable ecommerce department key (e.g. electronics, books, kitchen). Required for category/bestsellers unless categoryNodeId or categorySlug is set." }, "categoryNodeId": { "title": "Category browse node ID", "type": "string", "description": "Optional Amazon browse node ID. Overrides the mapped node for any subcategory." }, "categorySlug": { "title": "Best Sellers category slug", "type": "string", "description": "Optional Best Sellers path slug (e.g. electronics). Overrides the mapped slug." }, "sort": { "title": "Search sort order", "enum": [ "featured", "relevance", "price-asc", "price-desc", "newest", "avg-review", "review-count" ], "type": "string", "description": "Sort order for keyword/category search (s= parameter). Not supported for bestsellers/newreleases/detail.", "default": "featured" }, "condition": { "title": "Condition filter", "enum": [ "new", "used", "collectible", "refurbished", "renewed" ], "type": "string", "description": "Item condition facet for keyword/category search. Not supported for bestsellers/newreleases/detail." }, "minPrice": { "title": "Minimum price", "minimum": 0, "type": "number", "description": "Lower price bound for keyword/category search (low-price parameter). Not supported for bestsellers/newreleases/detail." }, "maxPrice": { "title": "Maximum price", "minimum": 0, "type": "number", "description": "Upper price bound for keyword/category search (high-price parameter). Not supported for bestsellers/newreleases/detail." }, "pages": { "title": "Pages per keyword", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of result pages to request for each task.", "default": 1 }, "maxItems": { "title": "Max results per keyword or detail URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "Most product rows for each keyword or detail URL; a category or ranking target is one input. Default 70; larger numbers are collected in parts of 70. All row types count together. The whole run stops at your maximum total charge. Free Apify plan: up to 200 rows per run and 10 runs of this Actor (limits set by the Actor developer).", "default": 70 }, "maxItemsPerKeyword": { "title": "Maximum output items per keyword", "minimum": 1, "maximum": 100, "type": "integer", "description": "Optional secondary cap for one keyword task. It defaults to the schema maximum so maxItems controls the per-input row limit.", "default": 100 }, "workerBaseUrl": { "title": "Worker base URL (optional)", "type": "string", "description": "Override the Cloud Run worker origin for this run. Defaults to Actor env WORKER_BASE_URL. Production migrations should update WORKER_BASE_URL in Actor settings (no code change).", "default": "" }, "provider": { "title": "Engine provider", "enum": [ "direct", "render", "httpx", "zyte" ], "type": "string", "description": "Worker acquisition engine. `direct` (default) uses the UA-whitelist direct-HTTP channel (curl_cffi + UA pool) — Amazon's primary gate is a UA whitelist, so a correct UA gets live SSR rows with no browser. `render` uses the real-browser render ladder as fallback (UA burn / login-gated surfaces). `httpx` is a probe/diagnostic arm only. `zyte` uses the control-plane HTTP extract.", "default": "direct" }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "HTTP timeout for each Amazon request.", "default": 30 }, "userAgent": { "title": "User-Agent override", "type": "string", "description": "Optional HTTP User-Agent override for local debugging." }, "debug": { "title": "Debug mode", "type": "boolean", "description": "Enable verbose diagnostic logging and extra debugging artifacts.", "default": false }, "includeRawHtml": { "title": "Save raw HTML", "type": "boolean", "description": "Persist raw HTML snapshots to the default key-value store for debugging.", "default": false }, "fixtureHtmlPath": { "title": "Local fixture HTML path", "type": "string", "description": "Optional local HTML fixture path for deterministic offline validation and gate runs." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }