{ "openapi": "3.0.1", "info": { "title": "Alibaba Email Scraper", "description": "Extract publicly indexed Alibaba seller emails from Google search results and public profile pages.", "version": "1.1", "x-build-id": "kMnLUHCPBgjtDepGG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/w3crawler~alibaba-email-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-w3crawler-alibaba-email-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/w3crawler~alibaba-email-scraper/runs": { "post": { "operationId": "runs-sync-w3crawler-alibaba-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/w3crawler~alibaba-email-scraper/run-sync": { "post": { "operationId": "run-sync-w3crawler-alibaba-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Default search query", "minLength": 1, "maxLength": 200, "type": "string", "description": "Supplier keyword used to build a public Google site search when no explicit startUrls or profileUrls are provided.", "default": "industrial supplier" }, "queries": { "title": "Search queries", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional supplier keywords. Each becomes a public Google site:alibaba.com source; explicit startUrls/profileUrls take precedence over generated searches.", "items": { "type": "string", "minLength": 1, "maxLength": 200 } }, "profileUrls": { "title": "Alibaba source URLs", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Optional public Alibaba supplier-search, company-profile, supplier-index, or product URLs. These are combined with startUrls and suppress generated Google searches.", "items": { "type": "string" } }, "startUrls": { "title": "Public start URLs", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Optional Google or Alibaba URLs in request-list form. URLs are deduplicated, paginated per source, and share one global maxResults limit.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "HTTPS Google search or public Alibaba page URL.", "type": "string" } }, "required": [ "url" ], "additionalProperties": false } }, "emailDomains": { "title": "Email domain filters", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Optional lowercase or @-prefixed domains. A contact passes when its domain equals a value or is a subdomain of it.", "items": { "type": "string", "minLength": 3, "maxLength": 120 } }, "textQuery": { "title": "Text filter", "maxLength": 200, "type": "string", "description": "Optional case-insensitive text match across email, supplier, company, product, country, badges, tags, markets, revenue, and context fields. Missing text does not match." }, "supplierCountry": { "title": "Supplier country", "maxLength": 100, "type": "string", "description": "Optional case-insensitive exact match against the observed Country/Region value, such as China or Vietnam." }, "minSupplierYears": { "title": "Minimum supplier years", "minimum": 0, "maximum": 200, "type": "number", "description": "Keep only records with an observed supplier tenure at or above this value. Records without a tenure value do not pass." }, "minResponseRate": { "title": "Minimum response rate", "minimum": 0, "maximum": 100, "type": "number", "description": "Keep only records with an observed response rate at or above this percentage. Records without a response rate do not pass." }, "requiredBadges": { "title": "Required supplier badges", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Keep records whose observed badge list contains every requested value, case-insensitively, such as Gold Supplier or Trade Assurance.", "items": { "type": "string", "minLength": 1, "maxLength": 80 }, "default": [] }, "sortBy": { "title": "Sort results", "enum": [ "relevance", "supplier_years_desc", "response_rate_desc", "company_asc", "country_asc", "email_asc" ], "type": "string", "description": "Relevance keeps source/page/card order. Other choices sort globally after all permitted pages are fetched; missing numeric values sort last and text ties are stable.", "default": "relevance" }, "maxResults": { "title": "Maximum contacts", "minimum": 1, "maximum": 500, "type": "integer", "description": "Global maximum number of unique email-bearing contact records emitted across every source and page.", "default": 50 }, "maxPages": { "title": "Maximum pages per source", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum pages followed for each source URL. Use 0 for automatic pagination up to the hard 100-page safety cap.", "default": 1 }, "deduplicate": { "title": "Deduplicate contacts", "type": "boolean", "description": "Merge repeated public observations globally by normalized email across pages and sources.", "default": true }, "maxEmailsPerResult": { "title": "Emails per source page", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum parsed email-bearing rows considered from each response before filters. The global maxResults limit still applies.", "default": 5 }, "includeProducts": { "title": "Include product details", "type": "boolean", "description": "Include observed product title/URL pairs and productUrls. The first productUrl remains available as the primary URL when present.", "default": true }, "maxProductsPerResult": { "title": "Products per contact", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum product title/URL pairs retained per contact. Use 0 to omit product arrays while retaining the observed product count.", "default": 5 }, "includeTags": { "title": "Include supplier tags", "type": "boolean", "description": "Keep the bounded Tags list observed on supplier cards.", "default": true }, "includeContext": { "title": "Include email context", "type": "boolean", "description": "Keep a bounded public contextSnippet around each normalized email. When enabled, the snippet contains the exact email.", "default": true }, "requestDelayMs": { "title": "Request delay (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Minimum delay between starts of public requests. Use respectful pacing for live sources.", "default": 250 }, "maxConcurrency": { "title": "Source concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of source URLs processed concurrently. Pagination within one source stays sequential.", "default": 2 }, "maxRequestRetries": { "title": "Request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Finite retries for transient network, timeout, 408, 425, 429, and 5xx responses. Challenge and access-denied pages fail closed.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum time allowed for one public response.", "default": 30 }, "maxResponseBytes": { "title": "Maximum response bytes", "minimum": 100000, "maximum": 30000000, "type": "integer", "description": "Safety cap for one HTML or JSON response.", "default": 20000000 }, "proxyConfiguration": { "title": "Apify Proxy", "type": "object", "description": "Optional standard Apify Proxy route for permitted public requests. Proxying never bypasses robots, login, CAPTCHA, or access controls.", "properties": { "useApifyProxy": { "title": "Use Apify Proxy", "description": "Route permitted public requests through standard Apify Proxy.", "type": "boolean" }, "apifyProxyGroups": { "title": "Proxy groups", "description": "Optional standard Apify Proxy groups.", "type": "array", "items": { "type": "string" } }, "apifyProxyCountry": { "title": "Proxy country", "description": "Optional two-letter standard Apify Proxy country code.", "type": "string", "pattern": "^[A-Za-z]{2}$" } }, "additionalProperties": false }, "userAgent": { "title": "User agent", "maxLength": 300, "type": "string", "description": "Optional transparent single-line HTTP user-agent string." }, "timeoutMs": { "title": "Legacy timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Backward-compatible alias for requestTimeoutSecs. Prefer requestTimeoutSecs in new inputs." } } }, "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 } } } } } } } } } }