{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper — Stories, Comments & Users", "description": "Scrape Hacker News stories, comments, user profiles, Ask HN, Show HN, jobs, and threaded discussions from the public Firebase API.", "version": "1.0", "x-build-id": "WZgfGlu3mBTpKyRhS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~hacker-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-hacker-news-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~hacker-news-scraper/runs": { "post": { "operationId": "runs-sync-junipr-hacker-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~hacker-news-scraper/run-sync": { "post": { "operationId": "run-sync-junipr-hacker-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "scrapeType": { "title": "Scrape Type", "enum": [ "topStories", "newStories", "bestStories", "askStories", "showStories", "jobStories", "search", "user", "item" ], "type": "string", "description": "What type of content to scrape from Hacker News. Choose a story feed (top, new, best, ask, show, jobs), search for content via Algolia, look up specific users, or fetch individual items by ID.", "default": "topStories" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of stories or items to return. Applies to story feeds and search results. Higher values take longer but return more data.", "default": 1 }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Fetch and include the full comment tree for each story. Disabling this significantly speeds up scraping when you only need story metadata.", "default": false }, "maxCommentsPerItem": { "title": "Max Comments Per Item", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum number of comments to fetch per story. Comments are fetched in order of the thread tree (top-level first, then replies). Use lower values for faster runs.", "default": 0 }, "commentDepth": { "title": "Comment Depth", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum depth of nested replies to follow in comment threads. Depth 1 = top-level comments only. Depth 5 = up to 4 levels of nested replies.", "default": 3 }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Search query string for finding stories and comments via the Algolia HN Search API. Required when scrapeType is 'search'. Supports standard search operators." }, "searchTags": { "title": "Search Tags", "enum": [ "story", "comment", "poll", "job" ], "type": "string", "description": "Filter search results by content type. Only applies when scrapeType is 'search'. Leave empty to search all content types." }, "usernames": { "title": "Usernames", "type": "array", "description": "List of HN usernames to look up. Required when scrapeType is 'user'. Returns profile info including karma, about text, and recent submissions.", "items": { "type": "string" } }, "itemIds": { "title": "Item IDs", "type": "array", "description": "List of HN item IDs to fetch directly. Required when scrapeType is 'item'. Accepts story, comment, job, poll, or poll option IDs.", "items": { "type": "integer" } }, "minScore": { "title": "Minimum Score", "minimum": 0, "type": "integer", "description": "Only include items with a score (upvotes) greater than or equal to this value. Useful for filtering out low-quality content." }, "minComments": { "title": "Minimum Comments", "minimum": 0, "type": "integer", "description": "Only include stories with at least this many comments (descendants). Useful for finding highly-discussed topics." }, "sortBy": { "title": "Sort By", "enum": [ "score", "date", "comments" ], "type": "string", "description": "How to sort the output results. 'score' sorts by upvotes (highest first), 'date' sorts by newest first, 'comments' sorts by most-discussed first.", "default": "score" } } }, "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 } } } } } } } } } }