{ "openapi": "3.0.1", "info": { "title": "Greenhouse Jobs Scraper", "description": "Scrape every open job from any company's Greenhouse careers board. Give it a list of company board tokens (e.g. stripe, databricks, airbnb) and get one clean row per job: title, company, department, location, salary range, apply URL and full description.", "version": "0.1", "x-build-id": "u9uR6nPvER55UzkON" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeworks~greenhouse-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeworks-greenhouse-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapeworks~greenhouse-jobs-scraper/runs": { "post": { "operationId": "runs-sync-scrapeworks-greenhouse-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapeworks~greenhouse-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-scrapeworks-greenhouse-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "boardTokens": { "title": "Company board tokens", "uniqueItems": true, "type": "array", "description": "The Greenhouse board tokens (company slugs) to scrape. A board token is the slug in a company's Greenhouse careers URL - e.g. for 'https://boards.greenhouse.io/stripe' the token is 'stripe'. You can paste either the bare token ('stripe', 'databricks') OR a full Greenhouse board URL (https://boards.greenhouse.io/, https://job-boards.greenhouse.io//jobs, or the embed '...job_board?for=' link) and the token is extracted for you. One board can hold hundreds of jobs, so a handful of tokens returns thousands of rows. Duplicate jobs across boards are removed automatically. A company's own careers domain (e.g. 'stripe.com/jobs') does not contain the token - open its 'View all jobs' page to find the boards.greenhouse.io slug.", "items": { "type": "string" } }, "searchTerms": { "title": "Keyword filter (optional)", "uniqueItems": true, "type": "array", "description": "Optional. Keep only jobs whose title OR department contains any of these words (case-insensitive substring match). For example ['engineer', 'data', 'product'] pulls just the engineering/data/product roles across every board. Leave empty to keep EVERY open job on each board.", "items": { "type": "string" } }, "locationQuery": { "title": "Location filter (optional)", "uniqueItems": true, "type": "array", "description": "Optional. Keep only jobs whose location or office text contains any of these (case-insensitive substring) - e.g. ['New York', 'Remote', 'London', 'United States']. Leave empty to keep jobs in every location.", "items": { "type": "string" } }, "updatedAfter": { "title": "Updated on/after (optional)", "type": "string", "description": "Optional. Keep only jobs whose 'last updated' date is on or after this date (format YYYY-MM-DD, e.g. 2026-06-01). Useful for pulling only freshly-updated roles on a repeat run. Leave empty to keep jobs regardless of date." }, "includeDescription": { "title": "Include full job description", "type": "boolean", "description": "If enabled (default), each row includes the full job description as both clean plain text (descriptionText) and HTML (descriptionHtml). Turn this off for a lighter, listing-only dataset (title, company, location, department, salary, apply URL) without the large description fields.", "default": true }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of unique jobs to return for the whole run (across all boards, after removing duplicates). Results are billed per job row. The default board list holds roughly 4,000 live jobs, so lower this to cap cost on a test run.", "default": 5000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used to reach the Greenhouse Job Board API. The actor fetches directly first (cheapest) and only falls back to this proxy, rotating to a fresh session, if a response comes back blocked. The default (Apify Residential, US) is a safe fallback and is rarely needed - the public API answers plain requests.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }