{ "openapi": "3.0.1", "info": { "title": "Validated Jobs Scraper: Dedup, No Ghost Jobs, Confidence Scored", "description": "Job data with a correctness guarantee: per-field confidence, ghost-job filtering and cross-source dedup — never silently wrong, duplicated or expired. Reaches LinkedIn and ATS boards cookieless, gets through Cloudflare/DataDome, self-healing on layout shifts. Built on the data.hilgard.cz engine.", "version": "0.0", "x-build-id": "KqxADGulvgMLkOZE5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jan_hilgard~validated-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jan_hilgard-validated-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jan_hilgard~validated-jobs-scraper/runs": { "post": { "operationId": "runs-sync-jan_hilgard-validated-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jan_hilgard~validated-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-jan_hilgard-validated-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "source" ], "properties": { "source": { "title": "Source", "enum": [ "linkedin", "indeed", "greenhouse", "lever", "ashby", "smartrecruiters", "remoteok" ], "type": "string", "description": "Which board to pull jobs from. A concrete source is required. ATS sources (Greenhouse / Lever / Ashby / SmartRecruiters) take a company slug; LinkedIn, Indeed and RemoteOK take keywords (+ location).", "default": "greenhouse" }, "keywords": { "title": "Keywords", "type": "string", "description": "Search query for LinkedIn / RemoteOK, e.g. 'backend engineer'." }, "location": { "title": "Location", "type": "string", "description": "Location filter for LinkedIn / aggregators, e.g. 'Berlin' or 'Remote'." }, "company": { "title": "Company (ATS slug)", "type": "string", "description": "Company / board slug, e.g. 'gitlab'. REQUIRED when source is an ATS board (Greenhouse / Lever / Ashby / SmartRecruiters). Not used for LinkedIn / Indeed / RemoteOK — give 'keywords' there instead." }, "title_include": { "title": "Title must include", "type": "array", "description": "Keep only jobs whose title contains one of these terms (case-insensitive).", "items": { "type": "string" } }, "title_exclude": { "title": "Title must not include", "type": "array", "description": "Drop jobs whose title contains one of these terms (case-insensitive).", "items": { "type": "string" } }, "employment_type": { "title": "Employment type", "type": "array", "description": "Keep only these employment types. Values match the output enum (the engine filters against the normalized employment_type).", "items": { "type": "string", "enum": [ "FULL_TIME", "PART_TIME", "CONTRACT", "INTERN", "TEMP" ] } }, "workplace_type": { "title": "Workplace type", "type": "array", "description": "Keep only these workplace types.", "items": { "type": "string", "enum": [ "onsite", "hybrid", "remote" ] } }, "country": { "title": "Country", "type": "array", "description": "ISO country filter, e.g. ['DE', 'US'].", "items": { "type": "string" } }, "language": { "title": "Language", "type": "array", "description": "ISO language filter for the job description, e.g. ['en'].", "items": { "type": "string" } }, "posted_within_days": { "title": "Posted within (days)", "minimum": 1, "maximum": 365, "type": "integer", "description": "Keep only jobs first posted within this many days. Helps avoid stale and reposted listings.", "default": 30 }, "drop_expired": { "title": "Drop expired", "type": "boolean", "description": "Drop jobs the engine detects as expired / closed. Dropped jobs are not returned and not charged.", "default": true }, "drop_ghost": { "title": "Drop ghost jobs", "type": "boolean", "description": "Drop jobs whose ghost_job_score is above 'Ghost threshold'. When off (default), ghost-suspect jobs are still returned, just flagged — you decide. Dropped jobs are not returned and not charged.", "default": false }, "enrich": { "title": "Enrich", "type": "boolean", "description": "Run the cheap local-inference enrichment on every returned record (quality / dedup / normalize / hiring-intent). On by default.", "default": true }, "enrich_layers": { "title": "Enrichment layers", "type": "array", "description": "Which enrichment layers to run when 'Enrich' is on.", "items": { "type": "string", "enum": [ "quality", "dedup", "normalize", "hiring_intent" ] }, "default": [ "quality", "dedup", "normalize", "hiring_intent" ] }, "dedup_across_sources": { "title": "Dedup across sources", "type": "boolean", "description": "Collapse the same opening seen on multiple sources into one record, listing the others under also_at. On by default.", "default": true }, "ghost_threshold": { "title": "Ghost threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Ghost-job score (0–1) above which a job counts as a ghost. Used for flagging, and for dropping when 'Drop ghost jobs' is on.", "default": 0.7 }, "start": { "title": "Start offset", "minimum": 0, "type": "integer", "description": "Result offset to start from (for paging through a large search).", "default": 0 }, "limit": { "title": "Page size", "minimum": 1, "maximum": 200, "type": "integer", "description": "Results per page the engine fetches.", "default": 25 }, "max_results": { "title": "Max results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on total jobs returned for this run. You are charged per returned job, so this caps spend.", "default": 100 }, "fetch_all": { "title": "Fetch all", "type": "boolean", "description": "Page through every available result up to 'Max results'. When off, fetch a single page of 'Page size'.", "default": false }, "include_description": { "title": "Fetch full description", "type": "boolean", "description": "Ask the engine to fetch the full job description (description_html + description_text). On by default. ATS boards (Greenhouse / Lever / Ashby / SmartRecruiters) include it inline regardless; for sources fetched per-posting (e.g. LinkedIn) this enables it, at some extra time. Descriptions can be large.", "default": true }, "requestTimeoutSecs": { "title": "Request budget (seconds)", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Total time budget for the search, across retries. Hard-capped internally — values above the cap are clamped.", "default": 600 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 20, "type": "integer", "description": "Retries if the search stream drops before returning results.", "default": 3 }, "retryBackoffSecs": { "title": "Retry backoff (seconds)", "minimum": 0, "maximum": 120, "type": "integer", "description": "Delay before retrying a dropped search stream.", "default": 3 } } }, "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 } } } } } } } } } }