{ "openapi": "3.0.1", "info": { "title": "Greenhouse Jobs Scraper (Fast API & Salaries)", "description": "Fast 128MB HTTP scraper for Greenhouse job boards (US & EU). Extracts job listings, structured salaries (pay_transparency), locations, departments, screening questions, and tracks new jobs across scheduled runs. 100% drop-in compatible.", "version": "1.0", "x-build-id": "zvc78LKTVr5QVmc9r" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data-goose~greenhouse-job-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data-goose-greenhouse-job-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/data-goose~greenhouse-job-scraper/runs": { "post": { "operationId": "runs-sync-data-goose-greenhouse-job-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/data-goose~greenhouse-job-scraper/run-sync": { "post": { "operationId": "run-sync-data-goose-greenhouse-job-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Company Board URLs, Job URLs, or Slugs", "type": "array", "description": "Paste Greenhouse board URLs (https://job-boards.greenhouse.io/stripe), custom career URLs (https://stripe.com/jobs), single job URLs (?gh_jid=...), or bare company slugs (stripe, anthropic, figma). Also accepts legacy [{'url': '...'}] objects via API.", "default": [ "https://job-boards.greenhouse.io/stripe", "https://job-boards.greenhouse.io/anthropic", "https://job-boards.greenhouse.io/figma", "https://job-boards.greenhouse.io/cloudflare", "https://job-boards.greenhouse.io/databricks" ], "items": { "type": "string" } }, "includeBuiltInTechDirectory": { "title": "Scan Built-In Tech Directory (45+ Companies)", "type": "boolean", "description": "Automatically scan 45+ verified tech companies on Greenhouse (Stripe, Anthropic, Airbnb, Coinbase, GitLab, Figma, Vercel, Scale AI, Databricks, etc.) in addition to your input list. Optional: any Greenhouse company works if you paste its board URL or slug above." }, "keywordFilter": { "title": "Keyword / Role Filter (Supports OR & -Exclude)", "type": "string", "description": "Optional case-insensitive regex, comma/pipe-separated OR terms, and -exclude tokens matched against job title or description." }, "excludeKeywordFilter": { "title": "Exclude Title Keywords", "type": "string", "description": "Case-insensitive regex or comma-separated keywords to exclude from job titles (e.g. 'Senior, Staff, Director')." }, "departmentFilter": { "title": "Department Filter", "type": "string", "description": "Optional case-insensitive substring matched against department names (e.g. Engineering, Sales)." }, "locationFilter": { "title": "Location Filter", "type": "string", "description": "Optional case-insensitive substring matched against job locations or offices (e.g. San Francisco, New York, Remote, EMEA)." }, "remoteOnly": { "title": "Remote Jobs Only", "type": "boolean", "description": "Only return jobs classified as Remote." }, "publishedAfter": { "title": "Published / Updated After (YYYY-MM-DD)", "type": "string", "description": "Only return jobs published or updated on or after this ISO date." }, "deduplicateMultiLocationJobs": { "title": "Deduplicate Multi-Location Postings", "type": "boolean", "description": "Collapses identical (companyToken, title, department) postings across multiple cities into a single dataset item with all locations merged." }, "onlyNewJobs": { "title": "Only New Jobs Since Last Run (Change Monitor)", "type": "boolean", "description": "Persists seen job IDs in a named Key-Value Store ('greenhouse-job-monitor-state') and outputs only net-new jobs since your previous run, while tracking closed/delisted jobs in RUN_SUMMARY." }, "monitorName": { "title": "Monitor State Name", "type": "string", "description": "Identifier for the change-monitor state key so multiple scheduled tasks can track separate watchlists.", "default": "default" }, "includeApplicationQuestions": { "title": "Include Application Screening Questions", "type": "boolean", "description": "Fetches the single-job detail endpoint (?questions=true) for each matched job to extract custom application form fields." }, "maxJobsPerCompany": { "title": "Max Jobs Per Company (0 = Auto Fair Share)", "minimum": 0, "type": "integer", "description": "Cap the number of jobs extracted per company board. 0 = automatic fair share: Max Total Jobs is split evenly across boards (minimum 10 each), so large boards like Stripe can't crowd out the others.", "default": 0 }, "maxTotalJobs": { "title": "Max Total Jobs", "minimum": 1, "type": "integer", "description": "Maximum total jobs to output across the entire run.", "default": 1000 } } }, "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 } } } } } } } } } }