{ "openapi": "3.0.1", "info": { "title": "Remote Jobs Scraper - Employer-Direct, No Job-Board Reposts", "description": "Remote postings read straight from employer boards on Greenhouse, Lever, Ashby, Recruitee and Workable, not job-board reposts. Remote is location-inferred on Greenhouse. New-since-last-run diff.", "version": "1.0", "x-build-id": "goZRSVkq2MgOqox5c" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maydit~remote-jobs-employer-direct/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maydit-remote-jobs-employer-direct", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maydit~remote-jobs-employer-direct/runs": { "post": { "operationId": "runs-sync-maydit-remote-jobs-employer-direct", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maydit~remote-jobs-employer-direct/run-sync": { "post": { "operationId": "run-sync-maydit-remote-jobs-employer-direct", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "preset": { "title": "Company preset", "enum": [ "remote-first", "none" ], "type": "string", "description": "'remote-first' scrapes a built-in list of 70 employer boards that were majority-remote when last verified (2026-09-25): every board had at least 5 remote postings and remote postings were at least half of its open roles. The list is in the README. The preset is used only when 'companies' and the per-platform lists are empty - listing companies replaces it. Choose 'none' when you pass your own companies and want an error rather than the preset if the list is empty.", "default": "remote-first" }, "companies": { "title": "Companies (platform auto-detected)", "type": "array", "description": "Company slugs to scrape, one per line. The slug is the path segment of the employer's board URL: job-boards.greenhouse.io/, jobs.lever.co/, jobs.ashbyhq.com/, .recruitee.com or apply.workable.com/. Each slug is tried on Greenhouse, Lever, Ashby, Recruitee and Workable in that order and the first board found is used. Slugs are case-insensitive. A slug with no board on any platform is reported and skipped. When you fill this in, the preset is not added.", "items": { "type": "string" } }, "greenhouse": { "title": "Greenhouse boards", "type": "array", "description": "Board tokens to read from Greenhouse only, skipping detection (e.g. 'gitlab'). Remote on Greenhouse is always inferred from the location text, because the platform publishes no workplace field.", "items": { "type": "string" } }, "lever": { "title": "Lever boards", "type": "array", "description": "Company slugs to read from Lever only (e.g. 'toptal'). Lever publishes a workplaceType per posting (remote / hybrid / onsite / unspecified).", "items": { "type": "string" } }, "ashby": { "title": "Ashby boards", "type": "array", "description": "Board names to read from Ashby only (e.g. 'zapier'). Ashby publishes a workplaceType per posting (Remote / Hybrid / OnSite) but many employers leave it blank, in which case the location text decides.", "items": { "type": "string" } }, "recruitee": { "title": "Recruitee boards", "type": "array", "description": "Subdomains to read from Recruitee only (e.g. 'timedoctor' for timedoctor.recruitee.com). Recruitee publishes remote / hybrid / on-site flags per posting.", "items": { "type": "string" } }, "workable": { "title": "Workable accounts", "type": "array", "description": "Account names to read from Workable only (e.g. 'zyte' for apply.workable.com/zyte). Workable publishes a 'telecommuting' yes/no per posting and nothing that separates hybrid from on-site; postings without the flag are checked against their location text. Workable enforces a per-IP daily quota (HTTP 429 with a Retry-After of about 24 hours), so a board here can fail in one run and work in the next; such a board is named in SUMMARY.failedSources and the rest of the run continues. That is why no Workable board is in the preset.", "items": { "type": "string" } }, "titleContains": { "title": "Job title contains", "type": "string", "description": "Optional. Keep only postings whose title contains this text (case-insensitive, partial match), for example 'engineer' or 'account executive'. Applied after the remote rule." }, "strictRemote": { "title": "Strict remote (drop hybrid/on-site even if the location text says remote)", "type": "boolean", "description": "On (default): when the platform publishes a workplace type and it is Hybrid or OnSite, the posting is dropped even if its location text says 'Remote'. Off: such a posting is kept and marked remoteBasis 'location-text'. Postings with no workplace type at all (every Greenhouse posting, and many Ashby ones) are decided by their location text either way.", "default": true }, "onlyWithSalary": { "title": "Only postings with a published salary range", "type": "boolean", "description": "Keep only postings where the platform returned a structured salary (salaryMin or salaryMax). Lever, Ashby and Recruitee publish one when the employer fills it in; Greenhouse and Workable never do, so this drops every Greenhouse and Workable row. On the default preset run of 2026-09-25, 12% of the 800 rows carried a salary.", "default": false }, "postedWithinDays": { "title": "Posted within the last N days", "minimum": 1, "type": "integer", "description": "Optional. Keep only postings whose postedAt is within the last N days. Rows are always sorted newest first, so this simply trims the tail. Leave empty for no date filter." }, "includeDescription": { "title": "Include full job description", "type": "boolean", "description": "Add a 'description' column with the posting text as clean plain text (HTML unescaped and stripped, list items kept as '- ' bullets, capped at 20,000 characters). Off by default because it multiplies the dataset size.", "default": false }, "maxResultsPerCompany": { "title": "Max postings per company", "minimum": 1, "type": "integer", "description": "Upper bound on remote postings kept from any one board, newest first. Every board is fetched in one request regardless, so this only shapes the output.", "default": 100 }, "maxResults": { "title": "Max postings in total", "minimum": 1, "type": "integer", "description": "Upper bound on rows in the dataset. Postings from every company are merged and sorted newest first before this cap applies, so a capped run is the freshest N remote postings across the whole list, not the first few companies. The default preset had 3,292 remote postings on 2026-09-25, so the default of 800 returns the newest 800 of them; raise it for the full list.", "default": 800 }, "onlyNewSinceLastRun": { "title": "Only postings new since the last run", "type": "boolean", "description": "Save only remote postings this Actor has not seen before. The job IDs of every remote posting on each board are recorded in a named key-value store ('remote-jobs-employer-direct-state') and compared on the next run with this option on. The FIRST run has no baseline, so it returns every posting and records the baseline (the log says so); from the second run on you get only new ones. A run with nothing new finishes successfully with an empty dataset. Do not enable this on a run you expect to return rows every time.", "default": false }, "maxRunSeconds": { "title": "Max run seconds", "minimum": 30, "type": "integer", "description": "Wall-clock budget for fetching boards. When it is reached the Actor stops cleanly, keeps everything already collected, and names the companies it did not reach - instead of being killed with a failed run. The default preset finishes in well under a minute; raise this only for very long custom lists.", "default": 240 } } }, "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 } } } } } } } } } }