{ "openapi": "3.0.1", "info": { "title": "Naukrigulf Job Scraper — UAE / Saudi / Gulf · $1/1k", "description": "Scrape Naukrigulf.com (UAE / Saudi / Qatar / wider GCC) — paste any naukrigulf.com URL or build a search from keyword + city + experience + salary + employment type. Structured rows: company, parsed MinCtc/MaxCtc salary, work mode, skills, apply link. Pure HTTP, no browser, $1/1k.", "version": "0.0", "x-build-id": "cFuC8vbSrGwua4III" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~naukrigulf-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-naukrigulf-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~naukrigulf-jobs-scraper/runs": { "post": { "operationId": "runs-sync-memo23-naukrigulf-jobs-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/memo23~naukrigulf-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-naukrigulf-jobs-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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Naukrigulf job list / search URLs. Non-empty = only these URLs are used. Prefill is empty so new runs default to the filter form below. Individual job pages (…-jid-) are also supported and fetched directly by JobId — no search is run for them.", "items": { "type": "string" } }, "platform": { "title": "Platform", "enum": [ "naukrigulf" ], "type": "string", "description": "This actor targets Naukrigulf only (Gulf-region jobs). For Naukri.com (India) coverage, use the combined memo23/naukri-scraper.", "default": "naukrigulf" }, "searchQuery": { "title": "Keyword to search", "type": "string", "description": "Job keyword or role (filter mode only)." }, "location": { "title": "Location (city / region)", "type": "string", "description": "Gulf city or region (filter mode only) — e.g. dubai, abu-dhabi, riyadh, doha, jeddah." }, "maximumJobs": { "title": "Maximum jobs", "minimum": 1, "type": "integer", "description": "Cap on jobs per run.", "default": 10000 }, "experienceLevel": { "title": "Experience (years)", "minimum": 0, "type": "integer", "description": "Minimum years of experience (filter mode)." }, "salaryFilter": { "title": "Salary filter (Naukrigulf CTC values)", "type": "string", "description": "Comma-separated Naukrigulf ctc values (e.g. 5,6,7,8,9,10)." }, "jobType": { "title": "Job type", "type": "string", "description": "Optional employment-type filter." }, "timeFilter": { "title": "Time filter (posted within)", "enum": [ "", "24h", "7d", "30d", "90d" ], "type": "string", "description": "Drop rows whose PostedDate is older than this window. Rows without a parseable date are kept.", "default": "" }, "minSalary": { "title": "Minimum salary", "minimum": 0, "type": "integer", "description": "Drop rows whose parsed Compensation.MinCtc is below this. Permissive — rows without salary are kept.", "default": 0 }, "includeDescription": { "title": "Include description fields", "type": "boolean", "description": "When OFF, the actor strips description / Description / jobDescription from every row.", "default": true }, "cleanHtml": { "title": "Clean HTML (plain text only)", "type": "boolean", "description": "When ON, strip HTML tags from description fields. Ignored when includeDescription is OFF.", "default": false }, "enrichEmails": { "title": "Enrich with employer contact emails (experimental)", "type": "boolean", "description": "If enabled, tries to find a contact email for each employer by discovering the company's website (Clearbit) and reading its contact/about pages. Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. Best-effort.", "default": false }, "qualifyByPayment": { "title": "💳 Qualify by payment (flag businesses that take money online)", "type": "boolean", "description": "Requires \"Enrich with contact emails\". Scans each business's website — reusing the pages already fetched for email discovery, so no extra cost or time — for payment processors and e-commerce platforms (Stripe, Shopify, PayPal, Paddle, Lemon Squeezy, WooCommerce, Square, Chargebee and more). Adds takesPayments (is this a real paying business?), paymentProcessors (which stack), stripeLiveKey (the public key if exposed) and paymentConfidence. Turn raw contacts into monetization-qualified leads. No extra charge — included with each enriched company.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "type": "integer", "description": "Maximum parallel pages / requests.", "default": 10 }, "minConcurrency": { "title": "Min concurrency", "type": "integer", "description": "Minimum parallel workers.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 1, "maximum": 10, "type": "integer", "description": "Retries per failed request before giving up.", "default": 10 }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." }, "includeKeywords": { "title": "✅ Include keywords", "type": "array", "description": "Only keep jobs whose title, company or description contains at least one of these (case-insensitive). Filtered rows are never charged.", "items": { "type": "string" } }, "excludeKeywords": { "title": "🚫 Exclude keywords", "type": "array", "description": "Drop jobs whose title, company or description contains any of these (case-insensitive).", "items": { "type": "string" } }, "fromDate": { "title": "📅 Posted from", "type": "string", "description": "Only keep jobs posted on or after this date (ISO 8601, e.g. 2026-08-01)." }, "toDate": { "title": "📅 Posted to", "type": "string", "description": "Only keep jobs posted on or before this date (ISO 8601). A date-only value means through the end of that day." }, "maxAgeMinutes": { "title": "⏱️ Max age (minutes)", "minimum": 0, "type": "integer", "description": "Only keep jobs posted within the last N minutes. Empty or 0 = no age limit. Ideal for tight scheduled runs." }, "incrementalMode": { "title": "♻️ Incremental mode", "type": "boolean", "description": "Compare against the previous run and only emit jobs that are NEW, UPDATED, or REAPPEARED — you are only charged for what changed. The first run seeds the baseline. Each emitted row carries `changeType` and `firstSeenAt`.", "default": false }, "stateKey": { "title": "🔑 State key", "type": "string", "description": "Optional stable name for this tracked search (e.g. \"nurse-toronto\"). Leave empty to auto-derive one from the search inputs — same inputs, same baseline." }, "emitUnchanged": { "title": "♻️ Emit unchanged records", "type": "boolean", "description": "When incremental, also emit rows whose content did not change (charged as normal results).", "default": false }, "emitExpired": { "title": "⚰️ Emit expired records", "type": "boolean", "description": "When incremental, emit a small `changeType: EXPIRED` row for every previously-tracked job that vanished from the source.", "default": false }, "skipReposts": { "title": "🚫 Skip reposts", "type": "boolean", "description": "When incremental, skip jobs whose content matches a previously-expired posting (employer re-listed the same ad under a new id).", "default": false }, "resetIncrementalState": { "title": "🧨 Reset incremental state", "type": "boolean", "description": "One-shot: drop the stored baseline for this state key at the start of the run.", "default": false }, "compact": { "title": "📦 Compact output", "type": "boolean", "description": "Emit only the core fields — small payloads for AI-agent / MCP / LLM pipelines.", "default": false }, "excludeEmptyFields": { "title": "🧹 Exclude empty fields", "type": "boolean", "description": "Drop null / empty-string / empty-array fields from each record.", "default": false }, "descriptionMaxLength": { "title": "✂️ Description max length", "minimum": 0, "type": "integer", "description": "Truncate description fields to this many characters (0 = full text). Controls LLM prompt cost and dataset size." }, "telegramBotToken": { "title": "🔔 Telegram bot token", "type": "string", "description": "Your bot's token from @BotFather. With Chat ID set, a summary of new jobs is sent after each run." }, "telegramChatId": { "title": "🔔 Telegram chat ID", "type": "string", "description": "Chat or channel id the bot posts to (e.g. \"-1001234567890\")." }, "slackWebhookUrl": { "title": "💼 Slack webhook URL", "type": "string", "description": "Slack incoming-webhook URL (api.slack.com/messaging/webhooks)." }, "discordWebhookUrl": { "title": "🎮 Discord webhook URL", "type": "string", "description": "Discord incoming-webhook URL (Server Settings → Integrations → Webhooks)." }, "whatsappAccessToken": { "title": "📱 WhatsApp access token", "type": "string", "description": "WhatsApp Cloud API token (Meta Business system user). The recipient must have messaged your business number within the last 24h — Cloud API rule." }, "whatsappPhoneNumberId": { "title": "📱 WhatsApp phone-number ID", "type": "string", "description": "Your WhatsApp Business phone-number id (numeric, from the Meta dashboard)." }, "whatsappTo": { "title": "📱 WhatsApp recipient", "type": "string", "description": "Recipient phone in E.164 without + (e.g. \"14165551234\")." }, "webhookUrl": { "title": "🪝 Generic webhook URL", "type": "string", "description": "Receives one JSON POST with { metadata, items } after the run — the universal escape hatch for n8n / Make / Zapier / custom backends." }, "webhookHeaders": { "title": "🪝 Webhook headers", "type": "object", "description": "Optional custom headers for the generic webhook (e.g. {\"Authorization\": \"Bearer …\"})." }, "notificationLimit": { "title": "🔔 Max jobs per notification", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many job lines each chat notification includes (1–20). The rest are summarised as a count.", "default": 5 }, "notifyOnlyChanges": { "title": "🔔 Notify only new/updated", "type": "boolean", "description": "With Incremental mode on, notify only about NEW / UPDATED / REAPPEARED jobs.", "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 }, "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 } } } } } } } } } }