{ "openapi": "3.0.1", "info": { "title": "Greenhouse Jobs Scraper — All Companies, All Jobs", "description": "Scrape jobs from 1,000+ Greenhouse companies. Auto-discovers boards — no URLs needed. Structured output: title, department, location, salary, seniority, apply URL. Unified/raw/both modes. Regex filters.", "version": "1.0", "x-build-id": "KyXj3OCZBSRnwb7z4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deadlyaccurate~greenhouse-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deadlyaccurate-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/deadlyaccurate~greenhouse-jobs-scraper/runs": { "post": { "operationId": "runs-sync-deadlyaccurate-greenhouse-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/deadlyaccurate~greenhouse-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-deadlyaccurate-greenhouse-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "all", "companies", "search" ], "type": "string", "description": "How to run the scraper:\n- 'all' — Auto-discover ALL companies and scrape every job board. Zero config.\n- 'companies' — Scrape only the company slugs you specify.\n- 'search' — Search a specific company's jobs by keyword (fast, single API call).", "default": "all" }, "companies": { "title": "Company Slugs (Board Tokens)", "type": "array", "description": "Greenhouse board tokens to scrape. Used in 'companies' and 'search' modes.\n\nThe token is the path segment in boards.greenhouse.io/{token}. Examples: 'stripe', 'airbnb', 'cloudflare', 'figma'.\n\nNot sure of the token? Run in 'all' mode first — the output includes every slug.", "default": [], "items": { "type": "string" } }, "locationFilter": { "title": "Location Filter", "type": "string", "description": "Regex pattern to match job locations.\n\nExamples:\n- 'europe|germany|uk|france' — European jobs\n- 'remote' — Any location containing 'remote'\n- 'new york|san francisco|austin' — US tech hubs\n- 'prague|czech' — Specific city/country", "default": "" }, "departmentFilter": { "title": "Department Filter", "type": "string", "description": "Regex pattern to match departments.\n\nExamples:\n- 'engineering|product' — Tech roles\n- 'sales|marketing|growth' — Go-to-market\n- 'design|creative' — Design teams\n- 'data|machine.learning|ai' — Data/ML roles", "default": "" }, "officeFilter": { "title": "Office Filter", "type": "string", "description": "Regex pattern to match office names.\n\nExamples:\n- 'berlin|london|amsterdam' — European offices\n- 'remote' — Remote offices\n- 'new york|san francisco' — US offices", "default": "" }, "keywordFilter": { "title": "Title/Keyword Filter", "type": "string", "description": "Regex pattern to match job titles.\n\nExamples:\n- 'senior|staff|lead|principal' — Senior roles\n- 'full.?stack|fullstack' — Full-stack engineers\n- 'react|typescript|node' — Tech-specific\n- 'founding|head.of|vp|director' — Leadership\n- 'intern|junior|entry' — Entry-level", "default": "" }, "includeContent": { "title": "Include Full Descriptions", "type": "boolean", "description": "Include the full HTML job description in output. Increases dataset size significantly (~10x). Default: off to keep results lean.", "default": false }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of parallel API requests. Higher = faster scraping but more memory. Recommended: 10 for full scrape, 5 for testing.", "default": 10 }, "outputFormat": { "title": "Output Format", "enum": [ "unified", "raw", "both" ], "type": "string", "description": "How to format output records:\n- 'unified' (default) — Normalized schema consistent across all ATS platforms with structured location, salary, company objects\n- 'raw' — Native Greenhouse format, no normalization\n- 'both' — Unified schema with original Greenhouse data in the 'raw' field", "default": "unified" }, "maxCompanies": { "title": "Max Companies", "minimum": 0, "type": "integer", "description": "Limit the number of companies to scrape. 0 = no limit (scrape all). Useful for testing or staying within budget.", "default": 0 } } }, "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 } } } } } } } } } }