{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper", "description": "Scrape Hacker News stories, comments, jobs, and user profiles. Modes: top/new/best/ask/show/jobs/past/item/user/search. Filters: minScore, domainFilter, dateRange, commentMinScore. No proxy, no auth.", "version": "1.0", "x-build-id": "RkbQDT2Z3x4b78DTO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~hackernews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-hackernews-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~hackernews-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-hackernews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~hackernews-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-hackernews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Mode", "enum": [ "topStories", "newStories", "bestStories", "askStories", "showStories", "jobStories", "item", "user", "search" ], "type": "string", "description": "What to scrape. `topStories` / `newStories` / `bestStories` / `askStories` / `showStories` / `jobStories` walk the public feeds. `item` fetches specific item IDs (`itemIds`). `user` fetches profiles (`usernames`). `search` uses the Algolia HN API (`searchQuery`).", "default": "topStories" }, "itemIds": { "title": "Item IDs (mode=item)", "type": "array", "description": "Direct Hacker News item IDs (numeric strings or integers). Used when mode=`item`.", "default": [], "items": { "type": "string" } }, "usernames": { "title": "Usernames (mode=user)", "type": "array", "description": "Hacker News usernames. Used when mode=`user`.", "default": [], "items": { "type": "string" } }, "searchQuery": { "title": "Search query (mode=search)", "type": "string", "description": "Free-text query passed to the Algolia HN search API." }, "startUrls": { "title": "Start URLs (optional)", "type": "array", "description": "Hacker News URLs to scrape directly. Supports `news.ycombinator.com/item?id=N` and `news.ycombinator.com/user?id=USER`. Each URL is converted to an item or user fetch.", "default": [], "items": { "type": "string" } }, "enableCommentHierarchy": { "title": "Build comment tree", "type": "boolean", "description": "When true, attach a nested `comments[]` array to each story (recursive replies). When false, comments are emitted as flat sibling records (one per row, with `parentId` and `depth`).", "default": false }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on emitted records (stories + comments + users combined).", "default": 100 }, "maxComments": { "title": "Max comments per story", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cap on comments fetched per story. 0 = no comments. Default 0 (skip comments).", "default": 0 }, "maxDepth": { "title": "Max comment depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum reply depth when fetching comments (only applies when `maxComments` > 0). Root comments are depth 0.", "default": 5 }, "minScore": { "title": "Min story score", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Drop stories with fewer points than this. Comments are unaffected." }, "domainAllowlist": { "title": "Domain allowlist", "type": "array", "description": "Only emit stories whose URL host contains one of these substrings (case-insensitive). e.g. ['github.com','arxiv.org'].", "default": [], "items": { "type": "string" } }, "domainBlocklist": { "title": "Domain blocklist", "type": "array", "description": "Drop stories whose URL host contains one of these substrings. e.g. ['twitter.com','x.com'].", "default": [], "items": { "type": "string" } }, "excludeDeadOrDeleted": { "title": "Exclude dead/deleted", "type": "boolean", "description": "Drop items flagged `dead: true` or `deleted: true` by Hacker News.", "default": true }, "dateRangeFrom": { "title": "Date range from (ISO YYYY-MM-DD)", "type": "string", "description": "Drop items posted before this date (UTC). Empty = no lower bound." }, "dateRangeTo": { "title": "Date range to (ISO YYYY-MM-DD)", "type": "string", "description": "Drop items posted after this date (UTC). Empty = no upper bound." }, "commentMinScore": { "title": "Min comment score", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Drop comments below this score. (Note: HN exposes comment scores only sporadically; comments without a score are kept.)" }, "commentAuthorFilter": { "title": "Comment author allowlist", "type": "array", "description": "Only emit comments authored by one of these usernames (case-insensitive substring match).", "default": [], "items": { "type": "string" } }, "minCommentCount": { "title": "Min number of comments", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Drop stories with fewer than this many comments." } } }, "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 } } } } } } } } } }