{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper: Stories, Comments, Search, Users (API)", "description": "Get Hacker News data from the official APIs: top, new, best, Ask HN, Show HN and job stories, keyword and date search, full comment threads, and user profiles. Points, comments, authors and dates as clean rows, with an only-new mode for monitoring.", "version": "0.0", "x-build-id": "3vgHoJsYy3G5IVRYT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/charlesmarkette~hacker-news-scraper-stories-comments-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-charlesmarkette-hacker-news-scraper-stories-comments-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/charlesmarkette~hacker-news-scraper-stories-comments-search/runs": { "post": { "operationId": "runs-sync-charlesmarkette-hacker-news-scraper-stories-comments-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/charlesmarkette~hacker-news-scraper-stories-comments-search/run-sync": { "post": { "operationId": "run-sync-charlesmarkette-hacker-news-scraper-stories-comments-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "lists", "search", "items", "users" ], "type": "string", "description": "Lists: the stories on HN's front-page lists. Search: Algolia's HN search by keyword, tag, date and points. Items: specific stories or comments by ID or URL. Users: user profiles, optionally with their latest submissions.", "default": "lists" }, "lists": { "title": "Lists", "type": "array", "description": "Lists mode. One or more of the official story lists. A story on several lists is output once (with its rank in each list in listRanks).", "items": { "type": "string", "enum": [ "top", "new", "best", "ask", "show", "job" ], "enumTitles": [ "Top (front page)", "New", "Best", "Ask HN", "Show HN", "Jobs" ] }, "default": [ "top" ] }, "maxItems": { "title": "Max stories", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Lists mode: how many stories to read from the top of each list (the API gives up to 500 for top, new and best, 200 for Ask, Show and jobs). Search mode: how many search results to read in total (more than 1,000 needs Sort = Date; see the README).", "default": 30 }, "query": { "title": "Search words", "type": "string", "description": "Search mode. Words to look for in titles, URLs, story text and comments (Algolia full-text search). Leave empty to get everything that matches the tags and dates." }, "tags": { "title": "Tags", "type": "array", "description": "Search mode. All must match: story, comment, poll, ask_hn, show_hn, front_page, author_USERNAME, story_ID (comments of one story). An OR group: (story,poll).", "items": { "type": "string" } }, "sort": { "title": "Sort", "enum": [ "date", "relevance" ], "type": "string", "description": "Search mode. Date: newest first, and can read more than 1,000 results (it moves to older time windows automatically). Relevance: Algolia's ranking (text match, then points), at most 1,000 results.", "default": "date" }, "dateFrom": { "title": "Posted after", "type": "string", "description": "Search mode. A date (2026-10-01), a time (2026-10-01T08:00:00Z) or a period back from now ('7 days', '24 hours')." }, "dateTo": { "title": "Posted before", "type": "string", "description": "Search mode. Same formats. A date on its own includes that whole day (UTC)." }, "minPoints": { "title": "Min points", "minimum": 0, "type": "integer", "description": "Search mode. Only stories with at least this many points (comments have no points, so this leaves them out)." }, "minComments": { "title": "Min comments", "minimum": 0, "type": "integer", "description": "Search mode. Only stories with at least this many comments." }, "items": { "title": "Items", "type": "array", "description": "Items mode. Item IDs (8863) or Hacker News URLs (https://news.ycombinator.com/item?id=8863): stories, comments, jobs or polls.", "items": { "type": "string" } }, "users": { "title": "Users", "type": "array", "description": "Users mode. Usernames (case-sensitive) or profile URLs (https://news.ycombinator.com/user?id=pg). Each gives one row: created date, karma, about text and number of submissions.", "items": { "type": "string" } }, "userSubmissions": { "title": "Latest submissions per user", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Users mode. Also output each user's latest N submissions, newest first (0 = profile only, up to 1,000). Each submission is an output row.", "default": 0 }, "userSubmissionTypes": { "title": "Submission types", "enum": [ "stories", "comments", "all" ], "type": "string", "description": "Users mode. Which submissions to list.", "default": "stories" }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Also get each story's comment thread (one Algolia request per story with comments). Each included comment is charged like a row; see the pricing section.", "default": false }, "commentsFormat": { "title": "Comments format", "enum": [ "nested", "flat" ], "type": "string", "description": "Nested: a 'comments' array on the story row, replies inside replies. Flat: one row per comment after its story, with storyId, parentId and depth (best for spreadsheets and filtering).", "default": "nested" }, "maxCommentsPerStory": { "title": "Max comments per story", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Comments are taken in thread order (top-level comments in HN's ranking, each followed by its replies) up to this many.", "default": 200 }, "textFormat": { "title": "Text format", "enum": [ "text", "markdown", "html" ], "type": "string", "description": "Story text, comments and user 'about' come from HN as HTML. Plain text (links written out), Markdown, or the original HTML.", "default": "text" }, "includeDeleted": { "title": "Include deleted and dead items", "type": "boolean", "description": "Off: deleted and dead (flagged or killed) stories are left out, and deleted comments are dropped unless they have replies (then they stay as a free placeholder row so the thread stays connected). On: all are output with deleted / dead set to true.", "default": false }, "onlyNew": { "title": "Only new items", "type": "boolean", "description": "Output only stories (and search results) not output by an earlier run with the same settings. The first run outputs everything it finds. Memory: the last 50,000 IDs, in the key-value store 'hacker-news-scraper-state'.", "default": false }, "stateKey": { "title": "Memory name", "type": "string", "description": "Optional. Runs with the same memory name share their 'only new' memory. By default each saved task has its own memory per set of settings. Letters, digits, '-', '_' and '.'." }, "concurrency": { "title": "Parallel requests (Firebase API)", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many item requests to send to HN's Firebase API at the same time (1–20). Algolia requests are always limited to 2 at a time and spaced out to stay within its public rate limit.", "default": 10 }, "maxResults": { "title": "Max output rows", "minimum": 1, "type": "integer", "description": "Optional cap on output rows for the whole run (stories, users and, in flat mode, comment rows)." } } }, "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 } } } } } } } } } }