{ "openapi": "3.0.1", "info": { "title": "HN Jobs Scraper — Who Is Hiring, Salary, Visa & Remote", "description": "HN jobs: /jobs board + monthly Who-is-Hiring thread via official API. Filter by remote, visa, keyword; historical months. Salary, emails, tech stack, apply links. Sheets-ready.", "version": "0.1", "x-build-id": "FaBt3GiNebOZemAqM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sequined_fan~hn-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sequined_fan-hn-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sequined_fan~hn-jobs-scraper/runs": { "post": { "operationId": "runs-sync-sequined_fan-hn-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sequined_fan~hn-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-sequined_fan-hn-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "jobs-board", "who-is-hiring", "both", "search" ], "type": "string", "description": "Job surface to scrape. 'jobs-board' = the persistent /jobs index. 'who-is-hiring' = monthly hiring threads (current + up to 24 months back). 'search' = full-text search across all HN comments. 'both' runs jobs-board + current thread.", "default": "jobs-board" }, "searchQuery": { "title": "Search query", "type": "string", "description": "Full-text query over all HN comments (source=search only), e.g. 'Django remote'. maxPages controls how many result pages to pull (100 per page).", "default": "" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of HN listing pages to follow (each page has ~30 listings). Cap to control runtime / cost.", "default": 1 }, "maxItems": { "title": "Max items", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Hard cap on total listings returned. 0 = unlimited. Also your spend control: listings bill per returned record. Raise for multi-month pulls (one thread holds ~200-450 posts; 24 months need several thousand).", "default": 30 }, "fetchDescription": { "title": "Fetch full descriptions", "type": "boolean", "description": "If true, follow each /jobs board item page to pull the full posting text. Thread and search rows always include full text at no extra step. Set false for title/company/date only.", "default": true }, "descriptionMaxChars": { "title": "Description max chars", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Truncate each description to this many characters (0 = no truncation).", "default": 8000 }, "keyword": { "title": "Keyword filter", "type": "string", "description": "Keep only listings matching this keyword (title, company, description). Empty = no filtering. Lowers spend on targeted runs.", "default": "" }, "new_only": { "title": "Only new listings", "type": "boolean", "description": "Push only listings never seen by previous runs (tracked in the actor's store). Empty result ends the run cleanly with no bill. Ideal for scheduled monitoring.", "default": false }, "month": { "title": "Thread month", "type": "string", "description": "Who-is-hiring month as YYYY-MM (e.g. 2026-07). Empty = current month. Combine with monthsBack for multi-month pulls.", "default": "" }, "monthsBack": { "title": "Recent months to scrape", "minimum": 1, "maximum": 24, "type": "integer", "description": "How many of the most recent monthly threads to include (thread mode only). 1 = selected month only. Each extra month adds one API call.", "default": 1 }, "threadUrls": { "title": "Specific thread links", "type": "string", "description": "Scrape specific HN threads instead of auto-discovery. Full item URLs or bare IDs, one per line. Overrides month/monthsBack.", "default": "" }, "excludeKeywords": { "title": "Must not contain", "type": "string", "description": "Drop postings mentioning any of these words (comma-separated). Matching is case-insensitive across title, company and description.", "default": "" }, "remoteOnly": { "title": "Remote only", "type": "boolean", "description": "Keep only remote roles (remote_status == remote). Ideal for remote job seekers; lowers spend on targeted runs.", "default": false }, "visaOnly": { "title": "Visa sponsorship only", "type": "boolean", "description": "Keep only posts explicitly offering visa sponsorship. Ideal for international job seekers.", "default": false }, "minSalary": { "title": "Minimum salary (USD)", "minimum": 0, "type": "integer", "description": "Keep only jobs with parsed salary floor at or above this annual USD number (hourly rates annualized x2080). Empty/0 = no filter. Rows without parseable salary are dropped when set.", "default": 0 }, "threadType": { "title": "Thread family", "enum": [ "hiring", "seeking", "freelancer" ], "type": "string", "description": "Which monthly HN thread family to scrape (who-is-hiring sources): hiring = companies posting roles, seeking = candidates looking for work, freelancer = contract/freelance gigs.", "default": "hiring" } } }, "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 } } } } } } } } } }