{ "openapi": "3.0.1", "info": { "title": "Alibaba Category Scraper", "description": "Extract comprehensive product data from Alibaba's marketplace using keyword searches. This Apify Actor scrapes details like prices, supplier ratings, images, and certifications, delivering structured JSON output for easy analysis....", "version": "1.2", "x-build-id": "XAxihFoUQ1v0OvUKt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/w3crawler~alibaba-category-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-w3crawler-alibaba-category-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/w3crawler~alibaba-category-scraper/runs": { "post": { "operationId": "runs-sync-w3crawler-alibaba-category-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/w3crawler~alibaba-category-scraper/run-sync": { "post": { "operationId": "run-sync-w3crawler-alibaba-category-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keyword": { "title": "Search keyword", "minLength": 1, "maxLength": 200, "type": "string", "description": "Product phrase used to build the default Alibaba search URL. If startUrls is supplied, the URL's SearchText is used when this is omitted.", "default": "wireless earbuds" }, "startUrls": { "title": "Start URLs", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "One or more public HTTPS Alibaba category, search, catalog, or product-detail URLs. All sources share one maxItems limit.", "items": { "type": "string" } }, "categoryUrl": { "title": "Category URL", "type": "string", "description": "Convenience field for one Alibaba category/search URL; it is processed after startUrls." }, "categoryUrls": { "title": "Additional category URLs", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Additional Alibaba category/search URLs; they are processed after startUrls.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum product rows", "minimum": 1, "maximum": 500, "type": "integer", "description": "Global maximum number of product rows emitted across every source and page.", "default": 40 }, "maxPages": { "title": "Maximum pages per source", "minimum": 0, "maximum": 100, "type": "integer", "description": "Pages per source. Use 0 for bounded automatic pagination up to 100 pages; every page remains subject to maxItems.", "default": 3 }, "sortBy": { "title": "Sort results", "enum": [ "best_match", "price_asc", "price_desc", "rating_desc", "reviews_desc", "sold_desc", "supplier_years_desc" ], "type": "string", "description": "Sort after extraction and filtering; best_match preserves page and card order.", "default": "best_match" }, "includeMedia": { "title": "Include product media", "type": "boolean", "description": "Keep product image URLs and thumbnail. Images are restricted to product-scoped public Alibaba CDN assets.", "default": true }, "deduplicate": { "title": "Deduplicate products", "type": "boolean", "description": "Remove repeated product IDs or canonical product URLs across pages and sources.", "default": true }, "includeDiagnostics": { "title": "Include diagnostics", "type": "boolean", "description": "Add minimal {url, error, errorCode, scrapedAt} rows when a source is blocked or has no public product evidence.", "default": true }, "excludeAds": { "title": "Exclude sponsored products", "type": "boolean", "description": "Exclude rows explicitly marked as advertisements by the public page.", "default": false }, "certifiedOnly": { "title": "Certified suppliers only", "type": "boolean", "description": "Keep rows with an observed certification, verified, assessed, or equivalent public supplier signal.", "default": false }, "supplierCountry": { "title": "Supplier country", "pattern": "^(?:any|[A-Za-z]{2,3})$", "type": "string", "description": "Optional two- or three-letter supplier country code, or any." }, "supplierLocation": { "title": "Supplier location text", "maxLength": 120, "type": "string", "description": "Optional case-insensitive text match against observed supplier location or country." }, "minPrice": { "title": "Minimum price", "minimum": 0, "type": "number", "description": "Keep rows whose observed price range reaches this value." }, "maxPrice": { "title": "Maximum price", "minimum": 0, "type": "number", "description": "Keep rows whose observed price range reaches this value." }, "minOrderQuantity": { "title": "Minimum order quantity", "minimum": 1, "type": "number", "description": "Keep rows with an observed MOQ at or above this value." }, "minSupplierRating": { "title": "Minimum supplier rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Keep rows with an observed supplier/product rating at or above this value." }, "minReviewCount": { "title": "Minimum review count", "minimum": 0, "type": "integer", "description": "Keep rows with at least this observed rating/review count." }, "minSoldCount": { "title": "Minimum sold count", "minimum": 0, "type": "integer", "description": "Keep rows with at least this observed sold count." }, "requiredBadges": { "title": "Required badges", "maxItems": 10, "uniqueItems": true, "type": "array", "description": "Keep rows whose observed badge, certification, or selling-point text contains every value.", "items": { "type": "string", "minLength": 1, "maxLength": 60 } }, "requestDelayMs": { "title": "Page delay (ms)", "minimum": 0, "maximum": 15000, "type": "integer", "description": "Delay before page navigations and retries. Respectful pacing is recommended.", "default": 1000 }, "maxConcurrency": { "title": "Source concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of source URLs processed concurrently; pages within one source remain sequential.", "default": 2 }, "maxRequestRetries": { "title": "Request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries for transient navigation failures. Challenge responses fail closed and are not bypassed.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 15, "maximum": 300, "type": "integer", "description": "Per-navigation timeout.", "default": 60 }, "requestHandlerTimeoutSecs": { "title": "Request handler timeout (seconds)", "minimum": 60, "maximum": 900, "type": "integer", "description": "Maximum time budget documented for one source/page operation.", "default": 300 }, "selectorTimeoutSecs": { "title": "Selector timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout used while waiting for the public page body before extracting HTML and embedded data.", "default": 30 }, "proxyConfiguration": { "title": "Apify Proxy", "type": "object", "description": "Optional standard Apify Proxy route for public requests. Proxying does not solve CAPTCHA or bypass access controls.", "properties": { "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route browser requests through Apify Proxy." }, "apifyProxyGroups": { "title": "Proxy groups", "type": "array", "description": "Optional Apify Proxy groups.", "items": { "type": "string" } }, "apifyProxyCountry": { "title": "Proxy country", "type": "string", "description": "Optional two- or three-letter Apify Proxy country code.", "pattern": "^[A-Za-z]{2,3}$" } }, "additionalProperties": false }, "fixtureFile": { "title": "Local HTML fixture", "pattern": "^(?!.*(?:^|[/\\\\])\\.\\.(?:[/\\\\]|$))(?![/\\\\])[^:]+\\.(?:html?|xhtml)$", "type": "string", "description": "Optional Actor-relative HTML fixture for deterministic QA. Page 2+ automatically uses sibling files named -page-2.html, -page-3.html, etc., when present." } } }, "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 } } } } } } } } } }