{ "openapi": "3.0.1", "info": { "title": "AliExpress Product Search Scraper (Crawlee, Proxy-Ready)", "description": "Scrape AliExpress search results by keywords with proxy support, session rotation, and cost guardrails. Outputs a clean, typed dataset (type: product) plus optional suggestion/unknown entries.\n\nAlso available as Pay-per-event version (better for automation/MCP).", "version": "1.3", "x-build-id": "dSh7Zj7PezWwp8IvL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/opalescent_junior~aliexpress-product-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-opalescent_junior-aliexpress-product-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/opalescent_junior~aliexpress-product-scraper/runs": { "post": { "operationId": "runs-sync-opalescent_junior-aliexpress-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/opalescent_junior~aliexpress-product-scraper/run-sync": { "post": { "operationId": "run-sync-opalescent_junior-aliexpress-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "queries" ], "properties": { "queries": { "title": "Search queries", "type": "array", "description": "List of search keywords to scrape on AliExpress. Example: [\"LED strip lights\", \"wireless earbuds\", \"phone case iPhone 15\"].", "items": { "type": "string" } }, "maxQueries": { "title": "Max queries", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of queries to process from the list. Queries beyond this limit are silently dropped.", "default": 10 }, "maxPages": { "title": "Max pages per query", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many search result pages to scrape per query. AliExpress shows ~48 products per page. More pages = more products but higher cost and block risk.", "default": 3 }, "maxItemsTotal": { "title": "Max items total", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on total items pushed to the dataset across ALL queries. The Actor stops enqueueing new pages once this limit is reached. This is your main cost-control lever.", "default": 200 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Number of browser pages open simultaneously. AliExpress is sensitive to concurrent requests — keep this at 1-2 for reliability. Higher values increase speed but also block risk.", "default": 2 }, "throttleMs": { "title": "Throttle (ms)", "minimum": 1000, "maximum": 10000, "type": "integer", "description": "Minimum delay in milliseconds between page loads (plus random jitter). Lower = faster but higher block risk. Recommended: 2500+ for AliExpress.", "default": 2500 }, "maxRequestRetries": { "title": "Max retries per request", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times a failed/blocked request is retried with a new session before being marked as failed.", "default": 3 }, "headless": { "title": "Headless browser", "type": "boolean", "description": "Run browser without a visible window. Set to false for debugging only (increases cost).", "default": true }, "enrich": { "title": "Enable enrichment", "type": "boolean", "description": "Visit individual product detail pages to extract more accurate prices, ratings, and order counts. Significantly increases run time and cost — use selectively.", "default": false }, "enrichLimit": { "title": "Enrichment limit", "minimum": 0, "maximum": 200, "type": "integer", "description": "Maximum number of products to enrich (visit detail pages). Only relevant when enrichment is enabled.", "default": 20 }, "includeSuggestions": { "title": "Include suggestions", "type": "boolean", "description": "Capture related-search / suggestion blocks from search result pages. When enabled, suggestions are added to the dataset with type='suggestion'. Products always have type='product'.", "default": false }, "includeUnknown": { "title": "Include unknown items", "type": "boolean", "description": "Include items that have a valid product URL but no commerce signals (no price, rating, orders, storeName) and no valid image. These are likely suggestion anchors. When enabled, they appear in the dataset with type='unknown'.", "default": false }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for AliExpress scraping. STRONGLY RECOMMENDED — scraping without proxy will almost certainly get blocked. Use RESIDENTIAL group for best reliability.", "default": { "useApifyProxy": true, "apifyProxyGroups": [], "apifyProxyCountry": "US", "proxyUrls": [] } }, "debugLog": { "title": "Debug logging", "type": "boolean", "description": "Enable verbose debug-level logs. Useful for troubleshooting but generates a lot of output.", "default": false }, "saveHtmlOnError": { "title": "Save HTML on error", "type": "boolean", "description": "When a request is blocked or enrichment fails, save the page HTML to the Key-Value store for debugging. Limited to a few pages to avoid storage bloat.", "default": false } } }, "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 } } } } } } } } } }