{ "openapi": "3.0.1", "info": { "title": "Bayt.com Scraper โ€” MENA Jobs with Salary & Skills Filter", "description": "Scrape bayt.com โ€” the leading Middle East job board covering UAE, Saudi Arabia, Qatar, Egypt and more. Salary data, experience requirements, skill-based filtering, career level, and full job descriptions across 10,000+ active listings. Incremental mode detects new jobs.", "version": "0.3", "x-build-id": "fEwgH3EgkIFuOtYn7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blackfalcondata~bayt-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blackfalcondata-bayt-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blackfalcondata~bayt-scraper/runs": { "post": { "operationId": "runs-sync-blackfalcondata-bayt-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blackfalcondata~bayt-scraper/run-sync": { "post": { "operationId": "run-sync-blackfalcondata-bayt-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ” Search Term(s)", "type": "string", "description": "Job search keywords (e.g. `software engineer`, `marketing manager`, `accountant`). Bayt matches against job title and description. Use multiple words for narrower results โ€” `software engineer` returns fewer (more relevant) jobs than `software`. Leave empty if you use Start URLs below." }, "startUrls": { "title": "๐Ÿ”— Start URLs", "type": "array", "description": "Optional alternative to **Search Term(s)** โ€” paste Bayt URLs directly:\n\n- **Search URLs** (e.g. `https://www.bayt.com/en/uae/jobs/?q=accountant`) are crawled page-by-page like a normal search. Build the search in your browser with the filters you want, then copy the URL.\n- **Job detail URLs** (e.g. `https://www.bayt.com/en/uae/jobs/it-support-engineer-5444606/`) skip the search step entirely and fetch only those specific listings. Useful for refreshing a known set of jobs.\n\nYou can mix both types in one run. Filters/Country/Location below are ignored when Start URLs are set.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "A Bayt search URL or job detail URL." } } } }, "country": { "title": "๐ŸŒ Country", "enum": [ "INTERNATIONAL", "AE", "SA", "EG", "KW", "QA", "BH", "JO", "LB", "PK", "IN", "OM", "IQ", "MA" ], "type": "string", "description": "Country to search in. **International** searches across all 13 supported Bayt markets at once. Pick a specific country to scope results โ€” recommended for higher-quality matches and faster runs. Supported: UAE, Saudi Arabia, Egypt, Kuwait, Qatar, Bahrain, Jordan, Lebanon, Pakistan, India, Oman, Iraq, Morocco.", "default": "INTERNATIONAL" }, "location": { "title": "๐Ÿ“ Location", "type": "string", "description": "Optional city or region within the selected country (e.g. `Dubai`, `Riyadh`, `Cairo`, `Doha`). Narrows results geographically โ€” leave empty to search the whole country. Bayt's free-text location field, so spelling matches what appears in listings." }, "employmentType": { "title": "๐Ÿ’ผ Employment Type", "enum": [ "full-time", "part-time", "freelance", "contract", "remote", "internship" ], "type": "string", "description": "Filter by employment contract type. **Full time** is the default behavior on Bayt and usually the largest segment. **Remote** filters for jobs explicitly tagged remote-first by the employer (also surfaced via the `isRemote` output flag). Leave empty to include all types." }, "careerLevel": { "title": "๐Ÿ“ˆ Career Level", "enum": [ "student", "entry-level", "mid-career", "senior", "manager", "director", "executive" ], "type": "string", "description": "Filter by required seniority. **Mid career** and **Senior** typically have the most listings; **Executive / C-level** the fewest. Career level also appears in the output as both the raw `careerLevel` string and the structured `yearsOfExperience` field when Bayt provides it." }, "datePosted": { "title": "๐Ÿ“… Date Posted", "enum": [ "past-24h", "past-week", "past-month" ], "type": "string", "description": "Filter by how recently the job was posted. **Past 24 hours** is the tightest โ€” useful when running on a daily cron to catch fresh jobs. **Past 30 days** gives the largest pool. Combine with `incrementalMode` for a near-zero-cost daily delta feed." }, "maxResults": { "title": "๐Ÿ’ฏ Max Results", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum number of job records to return per run. Set to `0` for unlimited (returns every matching job โ€” can be thousands for broad queries). For ad-hoc exploration start with 10โ€“50; for production monitoring 100โ€“500 is typical. You pay $0.001 per result returned, so this is also your hard cost cap per run.", "default": 50 }, "includeDetails": { "title": "๐Ÿ“‹ Include Full Details", "type": "boolean", "description": "When enabled (default), fetches each job's full detail page to populate `description`, `skills`, `salaryMin`/`Max`, `employmentTypeNormalized`, `hiringOrganizationId`, `isAiTranslated`, `nationality`, `gender`, `directApply`, and the preferred-candidate criteria. Disable to skip detail fetches โ€” runs ~3ร— faster but only SERP-card fields are populated.", "default": true }, "descriptionMaxLength": { "title": "โœ‚๏ธ Description Max Length", "minimum": 0, "type": "integer", "description": "Truncate the `description` field to N characters. `0` keeps full descriptions. Useful for LLM pipelines where descriptions cost tokens โ€” try `500`โ€“`2000` to keep enough context while capping prompt size. Does not affect `descriptionHtml` or `descriptionMarkdown`.", "default": 0 }, "compact": { "title": "๐Ÿ“ฆ Compact Output", "type": "boolean", "description": "Returns only 11 core fields per record: `jobId`, `title`, `company`, `location`, `salaryText`, `employmentType`, `careerLevel`, `url`, `postedDate`, `contentHash`, `changeType`. Designed for AI-agent and MCP workflows where token budget matters. Mutually exclusive with `removeEmptyFields` โ€” `compact` wins if both are enabled.", "default": false }, "removeEmptyFields": { "title": "๐Ÿงน Remove Empty Fields", "type": "boolean", "description": "Recursively drops `null`, empty string `\"\"`, and empty array `[]` values from each record before output. Empty nested objects (e.g. `socialProfiles` with all-null values) are also pruned. **Preserves** `false` and `0` since those are real signals. Recommended for AI agents, Make, Zapier, n8n, and any webhook flow where smaller payloads matter. **Keep disabled** for fixed-schema warehouse loads (Snowflake/BigQuery `COPY INTO`) where every row needs identical columns.", "default": false }, "incrementalMode": { "title": "โ™ป๏ธ Incremental Mode", "type": "boolean", "description": "When enabled, the actor tracks state across runs and emits/charges only for jobs that are **NEW** or **UPDATED** (or **REAPPEARED** โ€” a previously expired job that came back). Identical, unchanged jobs are silently skipped. On daily monitors this typically cuts cost by 80โ€“90% after the first baseline run. First run with a given `stateKey` always emits everything (the baseline). State is stored in Apify Key-Value Store and pruned after 30 days.", "default": false }, "stateKey": { "title": "๐Ÿ”‘ State Key", "type": "string", "description": "Stable identifier for the tracked search universe. **Leave empty to auto-derive** from your inputs โ€” different keyword/location/filter combinations get isolated state automatically. Set explicitly only if you want two different searches to share a single tracked universe (rare). Two concurrent runs with the same stateKey will not corrupt each other โ€” the second exits gracefully." }, "emitUnchanged": { "title": "โ™ป๏ธ Emit Unchanged", "type": "boolean", "description": "Also emit (and charge for) jobs that haven't changed since the last run, with `changeType: \"UNCHANGED\"`. Off by default โ€” that's the whole point of incremental mode. Enable only if your downstream pipeline needs the full current universe every run rather than just the delta.", "default": false }, "emitExpired": { "title": "โšฐ๏ธ Emit Expired", "type": "boolean", "description": "Also emit records for jobs that **disappeared** from the search universe since the last run, marked `changeType: \"EXPIRED\"` with the `expiredAt` timestamp. Useful for tracking when listings close. These are synthetic records โ€” only lifecycle metadata, no fresh job details.", "default": false }, "skipReposts": { "title": "๐Ÿšซ Skip Reposts", "type": "boolean", "description": "When a new job's tracked content (title, company, location, salary, description) matches a previously expired job exactly, treat it as a repost rather than NEW. By default reposts are still emitted with `isRepost: true` and `repostOfId` pointing to the original โ€” enable this to suppress them entirely. Useful for filtering out employers who recycle the same listing weekly.", "default": false }, "telegramToken": { "title": "๐Ÿ”‘ Telegram Bot Token", "type": "string", "description": "Telegram bot token from [@BotFather](https://t.me/BotFather). Create a bot with `/newbot`, copy the token (looks like `123456:ABC-DEF...`), and paste here. Required to enable Telegram notifications โ€” also fill in **Telegram Chat ID** below." }, "telegramChatId": { "title": "๐Ÿ’ฌ Telegram Chat ID", "type": "string", "description": "ID of the chat or channel to send job alerts to. For a personal chat: message your bot once, then visit `https://api.telegram.org/bot/getUpdates` to find your chat ID. For a channel: add the bot as admin, then forward a channel message to [@userinfobot](https://t.me/userinfobot). Required when **Telegram Bot Token** is set." }, "discordWebhookUrl": { "title": "๐ŸŽฎ Discord Webhook URL", "type": "string", "description": "Discord incoming webhook URL. Create one in **Server Settings โ†’ Integrations โ†’ Webhooks โ†’ New Webhook**, then copy the URL (looks like `https://discord.com/api/webhooks//`). Jobs are posted as rich embeds with title, company, salary, and apply link." }, "slackWebhookUrl": { "title": "๐Ÿ’ผ Slack Webhook URL", "type": "string", "description": "Slack incoming webhook URL (looks like `https://hooks.slack.com/services/T.../B.../...`). Create one at [api.slack.com/apps](https://api.slack.com/apps) โ†’ your app โ†’ **Incoming Webhooks**. Jobs are posted as Block Kit messages with title, company, salary, and apply button." }, "whatsappAccessToken": { "title": "๐Ÿ“ฑ WhatsApp Access Token", "type": "string", "description": "WhatsApp Cloud API access token from Meta Business. **Important constraint:** the recipient phone must have messaged your business number within the last 24 hours (Meta's free service-conversation window since Nov 2024). Cold-start outreach requires pre-approved message templates โ€” not supported here." }, "whatsappPhoneNumberId": { "title": "๐Ÿ“ž WhatsApp Phone Number ID", "type": "string", "description": "WhatsApp Business phone-number ID (numeric, found in Meta Business dashboard under **WhatsApp โ†’ API Setup**). Different from the phone number itself โ€” this is Meta's internal ID. Required when **WhatsApp Access Token** is set." }, "whatsappTo": { "title": "๐Ÿ“ฒ WhatsApp Recipient", "type": "string", "description": "Recipient phone in [E.164 format](https://en.wikipedia.org/wiki/E.164) without the leading `+` (e.g. `971501234567` for UAE, `971` is the country code). Must have messaged your business number within the last 24h." }, "webhookUrl": { "title": "๐Ÿช Generic Webhook URL", "type": "string", "description": "Catch-all webhook for n8n, Make, Zapier, or your own backend. Receives a single `POST` after each run with `{ metadata: {...}, items: [...] }` as JSON. Sent once at run end โ€” not per-item. Use the standard Apify integrations tab for per-result webhooks instead." }, "webhookHeaders": { "title": "๐Ÿ“‹ Webhook Headers", "type": "object", "description": "Optional JSON object of extra HTTP headers sent with the webhook POST. Use for auth tokens or content negotiation. Example: `{\"Authorization\": \"Bearer abc123\", \"X-Source\": \"apify\"}`." }, "notificationLimit": { "title": "๐Ÿ“Š Max Jobs Per Notification", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many job records to include in each Telegram/Discord/Slack/WhatsApp message (1โ€“20). Default `5` keeps notifications readable. The webhook destination always receives the full unlimited list โ€” this cap only applies to chat-style platforms.", "default": 5 }, "notifyOnlyChanges": { "title": "๐Ÿ”„ Notify Only New/Updated", "type": "boolean", "description": "When **Incremental Mode** is on, restrict notifications to `NEW` and `UPDATED` jobs only โ€” skip `UNCHANGED`, `EXPIRED`, and `REAPPEARED`. Recommended for daily monitors so you only get pinged about genuinely fresh listings. Has no effect when incremental mode is off.", "default": false }, "phoneExtractionMode": { "title": "๐Ÿ“ž Phone Extraction Mode", "enum": [ "strict", "lenient" ], "type": "string", "description": "How aggressively to detect phone numbers in job descriptions. **Strict** (default) only accepts numbers with explicit phone-context prefix (Tel:, Phone:, ู‡ุงุชู, ุฌูˆุงู„, ุชู…ุงุณ, etc.) or an international `+CC` prefix โ€” high precision, may miss bare local numbers. **Lenient** also accepts bare local numbers starting with `0` followed by 9โ€“15 digits, filtered against VAT IDs and dates โ€” more recall but some false positives.", "default": "strict" } } }, "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 } } } } } } } } } }