{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper — Submissions, Jobs, Users & Comments", "description": "Scrape Hacker News top/new/best/ask/show/job/user submissions. Returns title, author, score, comments, URL, and full text. No login required. Pay-per-result.", "version": "1.0", "x-build-id": "cktxLAURVkfb4QdFJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/santamaria-automations~ycombinator-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-santamaria-automations-ycombinator-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/santamaria-automations~ycombinator-scraper/runs": { "post": { "operationId": "runs-sync-santamaria-automations-ycombinator-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/santamaria-automations~ycombinator-scraper/run-sync": { "post": { "operationId": "run-sync-santamaria-automations-ycombinator-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search Queries", "type": "array", "description": "Keywords to look for, one per entry (for example \"python\", \"rust engineer\"). Filters the titles of whichever Story Feed (storyType) is selected. To search HN job posts (\"(YC ...) Is Hiring\"), set storyType to \"job\". Each query is matched case-insensitively against the item title (prefix-token match: all words are required, in any order, and a query word also matches longer words that start with it). HN job titles usually embed the company name, so company names match too. A story matching several queries is returned once, tagged with the first matching query. Leave empty to get everything in the feed.", "items": { "type": "string" }, "default": [] }, "maxResultsPerQuery": { "title": "Max Results per Query", "minimum": 1, "type": "integer", "description": "Cap per search query when searchQueries is used. Results are split round-robin across queries so one query cannot starve the others. Ignored without searchQueries. If Maximum Stories is 0, the total cap is this value times the number of queries.", "default": 100 }, "storyType": { "title": "Story Feed", "enum": [ "top", "new", "best", "ask", "show", "job" ], "type": "string", "description": "Which HN feed to scrape. 'top' = front page (/news), 'new' = newest, 'best' = all-time best, 'ask' = Ask HN, 'show' = Show HN, 'job' = YC jobs (/jobs). Search Queries filter the titles of whichever feed is selected here, so to search HN job posts (\"(YC ...) Is Hiring\") with searchQueries, set this to 'job'.", "default": "top" }, "storyIds": { "title": "Story IDs", "type": "array", "description": "Specific HN story/thread IDs to scrape (e.g. [47601859]). Overrides storyType. Use with includeComments to extract comments from any thread.", "items": { "type": "integer" } }, "usernames": { "title": "Usernames", "type": "array", "description": "HN usernames to scrape all submissions from (e.g. [\"whoishiring\", \"pg\"]). Returns all their stories and comments.", "items": { "type": "string" } }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Also extract comments for each story. Useful for 'Who is Hiring' threads, Ask HN discussions, etc.", "default": false }, "commentDepth": { "title": "Comment Depth", "minimum": 1, "maximum": 5, "type": "integer", "description": "How deep to fetch comment replies. 1 = top-level only, 2 = include direct replies, 3 = replies to replies. Max 5.", "default": 1 }, "maxResults": { "title": "Maximum Stories", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum number of stories to return from the feed. With searchQueries this caps the total across all queries (0 = maxResultsPerQuery x number of queries).", "default": 100 }, "maxCommentsPerStory": { "title": "Max Comments Per Story", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum top-level comments to extract per story (when includeComments is true).", "default": 100 } } }, "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 } } } } } } } } } }