{ "openapi": "3.0.1", "info": { "title": "ATS Jobs Scraper (All In One)", "description": "Scrapes live jobs from four ATS platforms — Ashby, BambooHR, Breezy HR and SmartRecruiters — into one unified schema. Paste mixed career page URLs and each is routed automatically. Split city/state/country, ISO 8601 UTC dates, and descriptions as clean Markdown for LLM use.", "version": "0.1", "x-build-id": "5TXeCEFRhUa6IzDWr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~ats-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-ats-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~ats-jobs-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-ats-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~ats-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-ats-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Career page URLs", "type": "array", "description": "Career page URLs from any mix of the four supported ATS platforms — the Actor detects which is which from the URL and routes each one automatically, so you can paste them all into a single run.\n\nSupported forms:\n\n- **Ashby** — `https://jobs.ashbyhq.com/posthog`\n- **BambooHR** — `https://nectar.bamboohr.com/careers`\n- **Breezy HR** — `https://boldare.breezy.hr`\n- **SmartRecruiters** — `https://jobs.smartrecruiters.com/BoschGroup`\n\nA URL that points at one specific job (`https://jobs.ashbyhq.com/posthog/`, `https://nectar.bamboohr.com/careers/157`, `https://boldare.breezy.hr/p/`) scrapes just that posting instead of the whole board.\n\nYou can also use the shorthand `platform:company` — `ashby:posthog`, `bamboohr:nectar`, `breezy:boldare`, `smartrecruiters:BoschGroup`.\n\nIf a company's careers page lives on its own domain, use the ATS URL its Apply button points at — that is the one this Actor can read.", "default": [ "https://jobs.ashbyhq.com/posthog", "https://nectar.bamboohr.com/careers", "https://boldare.breezy.hr", "https://jobs.smartrecruiters.com/BoschGroup" ], "items": { "type": "string" } }, "includeDescription": { "title": "Fetch full job descriptions", "type": "boolean", "description": "Fetch each job's full description and convert it to clean Markdown (`descriptionMarkdown`) alongside the original HTML.\n\nThis is the Actor's main cost lever. On **Ashby** it is free — the description already ships in the board response, so no extra requests are made either way. On **BambooHR**, **Breezy** and **SmartRecruiters** it costs one extra request per job.\n\nTurning it off on BambooHR also drops `location.country`, which only appears on that platform's detail response.", "default": true }, "maxItems": { "title": "Max jobs per board", "minimum": 0, "type": "integer", "description": "Stop after this many jobs from each career page. Set to 0 for every job on the board.\n\nDefaults to a bounded 200 rather than unlimited because board sizes vary enormously — a single Ashby board can hold 700+ postings and one SmartRecruiters enterprise board over 4,700 (the default example, BoschGroup, is one of these) — so an unbounded first run can turn into a multi-thousand-request crawl. Raise it or set it to 0 once you know how big your target boards are.", "default": 200 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Rows per request, for SmartRecruiters — the only one of the four platforms that paginates at all. Ashby, BambooHR and Breezy return their whole board in a single response and ignore this setting.\n\nCapped at 100 because SmartRecruiters silently clamps anything higher back to 100 while still reporting success, so a larger number here would quietly mean something other than what it says.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Upper bound on requests in flight across the whole run — boards and their per-job detail fetches draw from the same budget.\n\nNone of these four platforms showed rate limiting during testing, but they are small companies' careers pages as often as they are enterprises'; the default is deliberately modest.", "default": 6 }, "minRequestInterval": { "title": "Minimum interval between requests", "minimum": 0, "maximum": 60, "type": "integer", "description": "Seconds to leave between the START of one request and the next, across the whole run. 0 disables pacing.\n\nThis, not concurrency, is the honest speed control: once a rate cap binds, extra concurrency buys nothing.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "All four platforms answered every TLS fingerprint tested from a plain residential connection, so a proxy is not needed to get past a bot wall here — there isn't one.\n\nResidential is still the default on the platform, because a cloud run shares datacenter egress with every other Actor and these APIs rate-limit by IP long before they fingerprint.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }