{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper - top, new and search stories, comments", "description": "Hacker News stories from the official public APIs: the top, new and best lists, or a full-text search by keyword, tag and date. One row per story with id, title, URL, domain, points, author, comment count, created time and HN link; optionally top comments. For trend trackers and researchers.", "version": "0.1", "x-build-id": "CaxwziqkUXSp77zKT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/retrainmap~hackernews-stories/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-retrainmap-hackernews-stories", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/retrainmap~hackernews-stories/runs": { "post": { "operationId": "runs-sync-retrainmap-hackernews-stories", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/retrainmap~hackernews-stories/run-sync": { "post": { "operationId": "run-sync-retrainmap-hackernews-stories", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "top", "new", "best", "search" ], "type": "string", "description": "top / new / best read the official Firebase lists (500, 500 and 200 ids) in HN's own order. search runs a full-text Algolia query using the fields below.", "default": "top" }, "query": { "title": "Search query (search mode)", "type": "string", "description": "Full-text query for the Algolia API (matches title, URL, author and text). Empty = no term filter (then the tags and date range alone select the rows)." }, "tags": { "title": "Tags (search mode)", "uniqueItems": true, "type": "array", "description": "Algolia item tags; several tags are ORed. story = any story (Ask/Show included), comment = comments, ask_hn / show_hn = those story kinds, front_page = stories currently on the front page. Empty = story.", "items": { "type": "string", "enum": [ "story", "comment", "ask_hn", "show_hn", "front_page" ], "enumTitles": [ "Story", "Comment", "Ask HN", "Show HN", "Front page" ] } }, "search_sort": { "title": "Search order (search mode)", "enum": [ "relevance", "date" ], "type": "string", "description": "relevance uses /search (Algolia relevance, then points and comments); date uses /search_by_date (newest first).", "default": "relevance" }, "date_from": { "title": "Created on or after (YYYY-MM-DD, search mode)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Optional, UTC, inclusive; applied as an Algolia numericFilter on created_at_i." }, "date_to": { "title": "Created on or before (YYYY-MM-DD, search mode)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Optional, UTC, inclusive (through 23:59:59 of that day)." }, "include_comments": { "title": "Include top comments per story", "type": "boolean", "description": "When on, each story row is followed by up to comments_per_story rows of its top-level comments in HN's ranked order (one extra Algolia request per story, plus one Firebase request per story in search mode). Comment rows count towards max_records and are charged as records.", "default": false }, "comments_per_story": { "title": "Comments per story", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum top-level comments written per story when include_comments is on.", "default": 10 }, "max_records": { "title": "Maximum records", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many rows (stories plus comment rows) have been written. The lists hold at most 500 (top, new) or 200 (best) stories; Algolia returns at most 1,000 hits per query.", "default": 200 }, "request_interval_ms": { "title": "Minimum interval between requests (ms)", "minimum": 50, "maximum": 10000, "type": "integer", "description": "Politeness delay towards the two APIs (one request per story in list modes). Floor 50 ms. Algolia's documented limit is 10,000 requests per hour per IP.", "default": 100 }, "contact_email": { "title": "Contact e-mail (From: header)", "type": "string", "description": "Sent in the standard From: request header so the data owner can reach the operator (RFC 9110 s10.1.2).", "default": "info@steelyardclinical.com" } } }, "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 } } } } } } } } } }