{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper", "description": "Scrapes Hacker News stories, comments, jobs, polls, and user profiles via the official Firebase and Algolia APIs. Supports full-text search, Who's Hiring thread extraction, author karma snapshots, and deep comment trees.", "version": "1.0", "x-build-id": "pRvFdTfxPQRT0wKrZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/constructive_calm~hacker-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-constructive_calm-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/constructive_calm~hacker-news-scraper/runs": { "post": { "operationId": "runs-sync-constructive_calm-hacker-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/constructive_calm~hacker-news-scraper/run-sync": { "post": { "operationId": "run-sync-constructive_calm-hacker-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Scraping mode", "enum": [ "topstories", "newstories", "beststories", "askstories", "showstories", "jobstories", "search", "user", "hiring_threads" ], "type": "string", "description": "What to scrape. 'topstories' / 'newstories' / 'beststories' pull from the official Firebase lists. 'askstories' / 'showstories' / 'jobstories' return only Ask HN / Show HN / jobs. 'search' runs a full-text Algolia query. 'user' returns everything a username has submitted. 'hiring_threads' auto-detects the latest monthly 'Ask HN: Who is hiring?' post and returns its top-level job comments.", "default": "topstories" }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of top-level items to return (stories for list/search/user modes, comments for hiring mode). Firebase list endpoints cap at 500; Algolia search caps at 1000 per page but can paginate further.", "default": 30 }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "If enabled, each story's full comment tree is fetched and attached under the `comments` field (respecting `maxCommentDepth`). Adds latency and per-comment billing.", "default": false }, "maxCommentDepth": { "title": "Max comment depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum nesting depth when expanding comment trees. 1 = top-level replies only, 10 = deepest practical threads. Ignored when `includeComments` is off.", "default": 3 }, "flattenComments": { "title": "Flatten comments", "type": "boolean", "description": "If enabled, comments are returned as a flat array (with a `depth` field) instead of a nested tree. Useful for spreadsheet-friendly output.", "default": false }, "minScore": { "title": "Minimum score", "minimum": 0, "type": "integer", "description": "Skip stories with fewer points than this. 0 = no filter. Example: set to 100 to only get front-page-worthy stories.", "default": 0 }, "minComments": { "title": "Minimum comments", "minimum": 0, "type": "integer", "description": "Skip stories with fewer comments (descendants) than this. 0 = no filter. Useful for filtering to heavily-discussed threads.", "default": 0 }, "dateFromUnix": { "title": "Date from (Unix timestamp)", "type": "integer", "description": "Only return items created after this Unix timestamp (seconds since epoch). Leave empty for no lower bound. Example: 1735689600 = 2025-01-01." }, "dateToUnix": { "title": "Date to (Unix timestamp)", "type": "integer", "description": "Only return items created before this Unix timestamp (seconds since epoch). Leave empty for no upper bound." }, "domainFilter": { "title": "Domain filter", "type": "array", "description": "If set, only stories whose URL domain matches one of these are returned. Example: [\"github.com\", \"arxiv.org\"] for tech-focused scraping.", "default": [], "items": { "type": "string" } }, "searchQuery": { "title": "Search query (Algolia)", "type": "string", "description": "Full-text search query. Required when `mode` is 'search'. Example: \"Claude\" or \"GPT-5 launch\".", "default": "" }, "searchTags": { "title": "Search tags (Algolia)", "type": "array", "description": "Restrict search results by type. Options: 'story', 'comment', 'poll', 'job'. You can also pass 'author_' or 'story_' (advanced). Ignored outside search mode.", "default": [], "items": { "type": "string" } }, "sortSearchBy": { "title": "Sort search results", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort Algolia search results by relevance (best match first) or by date (newest first).", "default": "relevance" }, "username": { "title": "Username", "type": "string", "description": "HN username whose submissions to fetch. Required when `mode` is 'user'. Case-sensitive. Example: \"dang\".", "default": "" }, "includeUserProfiles": { "title": "Include user profiles", "type": "boolean", "description": "If enabled, each story (and comment, if `includeComments` is on) is enriched with the author's karma and account age. Adds one API call per unique author and is billed separately.", "default": false } } }, "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 } } } } } } } } } }