{ "openapi": "3.0.1", "info": { "title": "Personio Jobs Scraper & API — Any Company", "description": "Scrape every open job from any company on Personio (jobs.personio.com). Give a company subdomain and get each position with full description, location, department, employment type and apply URL — from the public feed. Filter by title, location, remote. No proxy. JSON or CSV out.", "version": "0.0", "x-build-id": "qd8723Hw1JBQDgywb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~personio-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-personio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~personio-scraper/runs": { "post": { "operationId": "runs-sync-memo23-personio-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~personio-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-personio-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Personio board URLs", "type": "array", "description": "Personio board URLs (e.g. https://deskbird.jobs.personio.com) or bare company subdomains.", "items": { "type": "string" } }, "organizations": { "title": "Organization slugs", "type": "array", "description": "Bare Personio company subdomains, e.g. [\"vodeno\", \"get-e\"]. The subdomain is the part before .jobs.personio.com. Merged with any Start URLs above.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum jobs to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on job rows emitted across the whole run (across all companies). Use it to control billing — large boards like OpenAI have 700+ open roles.", "default": 5000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "How many company boards to fetch in parallel.", "default": 10 }, "titleKeyword": { "title": "Title contains", "type": "string", "description": "Keep only jobs whose title contains this text (case-insensitive), e.g. \"engineer\"." }, "location": { "title": "Location contains", "type": "string", "description": "Keep only jobs whose location (primary or secondary) contains this text, e.g. \"remote\", \"London\", \"New York\"." }, "department": { "title": "Department contains", "type": "string", "description": "Keep only jobs whose department contains this text, e.g. \"Engineering\"." }, "employmentType": { "title": "Employment type / schedule", "enum": [ "Full-time", "Part-time", "Permanent", "Intern", "Trainee", "Freelance", "Working student", "Apprenticeship" ], "type": "string", "description": "Keep only jobs matching this. Matches Personio's schedule (Full-time / Part-time) OR employment type (Permanent / Intern / Trainee / Freelance / Working student), case-insensitive." }, "remoteOnly": { "title": "Remote only", "type": "boolean", "description": "Keep only jobs flagged remote.", "default": false }, "postedAfter": { "title": "Posted on/after", "type": "string", "description": "Keep only jobs published on or after this date (YYYY-MM-DD). Ideal for scheduled monitoring runs that only want fresh roles." }, "includeDescription": { "title": "Include full job description", "type": "boolean", "description": "Include `descriptionHtml` and `descriptionText` on each row. Turn off for leaner, cheaper rows when you only need title/location/compensation/links.", "default": true }, "language": { "title": "Job description language", "type": "string", "description": "ISO language code requested from Personio's feed (e.g. \"en\", \"de\", \"fr\"). Defaults to \"en\", which also fills in descriptions many boards leave empty in their default feed. Leave blank to use each board's own default language. Note: only languages the company actually published are available — Personio falls back to its default if the requested one is missing.", "default": "en" }, "includeRawJson": { "title": "Include raw Personio payload", "type": "boolean", "description": "Attach the original, unmodified Personio position to each row under a `raw` field. Useful for advanced fields not in the normalized schema. Off by default to keep rows lean.", "default": false }, "enrichEmails": { "title": "Enrich with company contact emails (experimental)", "type": "boolean", "description": "If enabled, tries to find a contact email for the company by discovering its website (Clearbit) and reading its contact/about pages. Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. Best-effort.", "default": false }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." } } }, "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 } } } } } } } } } }