{ "openapi": "3.0.1", "info": { "title": "Alibaba Email Scraper: Top Supplier Leads", "description": "Alibaba Email Scraper extracts publicly available email addresses from Alibaba supplier and company pages. Build targeted contact lists for sourcing, negotiations, and direct manufacturer outreach at scale.", "version": "0.3", "x-build-id": "r2ckyJapC5LpXHneF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scraper-engine~alibaba-email-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scraper-engine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scraper-engine~alibaba-email-scraper/runs": { "post": { "operationId": "runs-sync-scraper-engine-alibaba-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scraper-engine~alibaba-email-scraper/run-sync": { "post": { "operationId": "run-sync-scraper-engine-alibaba-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "businessKeywords": { "title": "🔍 Business Keywords", "type": "array", "description": "Product, industry, or company keywords to harvest supplier emails for (e.g. ['led lighting', 'stainless steel', 'packaging']). Each keyword is expanded into ~29 business-email search patterns in Bulk mode. Accepts the base `keywords` key as a fallback.", "items": { "type": "string" } }, "mode": { "title": "⚙️ Harvest Mode", "enum": [ "standard", "bulk" ], "type": "string", "description": "Standard = a curated set of ~6 high-yield business-email dork patterns per keyword (fast, finishes inside the sync window). Bulk = fire ~29 engineered patterns per keyword for maximum corporate-email yield (longer runs). Default is Standard.", "default": "standard" }, "selectedPatterns": { "title": "🧩 Selected Patterns (optional)", "type": "array", "description": "Run just a subset of the patterns by name (e.g. ['contact_at_domain', 'careers_hiring', 'customer_service']). Leave empty to use the mode default (Standard = ~6 curated, Bulk = all 29). Unknown names fail fast. See the README for the full pattern list.", "items": { "type": "string" } }, "maxEmailsPerPattern": { "title": "🔢 Max Emails per Pattern", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap on emails collected from each pattern, so yield spreads across patterns instead of exhausting on the first. Example: 10 → up to 10 emails per pattern. Default is 10.", "default": 10 }, "maxRunSeconds": { "title": "⏱️ Max Run Seconds", "minimum": 30, "maximum": 270, "type": "integer", "description": "Overall wall-clock budget. The run stops cleanly (streaming whatever it has collected) once this is reached, so a run-sync call finishes before the 300s timeout instead of being killed. Default 235 (max 270).", "default": 235 }, "excludeFreeMail": { "title": "🏢 Business Emails Only", "type": "boolean", "description": "Keep only corporate/business emails and drop free-mail addresses (gmail, yahoo, outlook, qq, 163, …). Default is true.", "default": true }, "maxBusinessEmails": { "title": "🎯 Business Email Harvest Cap (total)", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Total unique business emails to harvest across every keyword and pattern before the run stops cleanly. Example: 100. Accepts the base `maxEmails` key as a fallback. Default is 20." }, "region": { "title": "📍 Region Filter", "type": "string", "description": "Optional country/city term added to every search (e.g. 'India', 'Shenzhen'). Leave empty to search globally. Accepts the base `location` key as a fallback.", "default": "" }, "businessDomains": { "title": "🌐 Email Domain Filter (optional)", "type": "array", "description": "Optional: keep only emails ending in these domains (e.g. ['.com.cn', '@company.com']). Leave empty to keep all business domains. Accepts the base `emailDomains` key as a fallback.", "items": { "type": "string" } }, "supplierMarketplace": { "title": "🏬 Supplier Marketplace", "enum": [ "Alibaba" ], "type": "string", "description": "B2B marketplace that drives the `site:` search restriction and the network label on every row. Accepts the base `platform` key as a fallback." }, "engine": { "title": "⚙️ Engine", "enum": [ "legacy", "residential" ], "type": "string", "description": "Fetch engine — selects which Apify proxy group Google requests run through. Legacy: GOOGLE_SERP proxy group (Google's SERP-optimized IPs). Residential: RESIDENTIAL proxy group (async requests over residential IPs). Accepts the base `engine` key." }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "Proxy settings. Google requests run through the Apify proxy group selected by the Engine input (GOOGLE_SERP for Legacy, RESIDENTIAL for Residential) with automatic fresh-IP retries on block." } } }, "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 } } } } } } } } } }