Hacker News Scraper
Pricing
from $1.50 / 1,000 results
Hacker News Scraper
Scrape Hacker News stories, comments, jobs, Ask HN, and Show HN using Algolia Search API and HN Firebase API. Supports full-text search, date/points filters, and live feeds.
Hacker News Scraper
Pricing
from $1.50 / 1,000 results
Scrape Hacker News stories, comments, jobs, Ask HN, and Show HN using Algolia Search API and HN Firebase API. Supports full-text search, date/points filters, and live feeds.
You can access the Hacker News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "x3MYBz3YLWn4i6K6I" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nogards95~hacker-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nogards95-hacker-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/nogards95~hacker-news-scraper/runs": { "post": { "operationId": "runs-sync-nogards95-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/nogards95~hacker-news-scraper/run-sync": { "post": { "operationId": "run-sync-nogards95-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "feed" ], "type": "string", "description": "Search mode: 'search' uses Algolia full-text search, 'feed' fetches live HN feeds via Firebase.", "default": "search" }, "query": { "title": "Search Query", "type": "string", "description": "Keyword to search for. Required when mode is 'search'.", "default": "javascript" }, "type": { "title": "Content Type", "enum": [ "story", "comment", "ask_hn", "show_hn", "job", "all" ], "type": "string", "description": "Type of content to retrieve.", "default": "story" }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort search results by relevance or date (most recent first). Only applies to mode=search.", "default": "relevance" }, "feedType": { "title": "Feed Type", "enum": [ "top", "new", "best", "ask", "show", "job" ], "type": "string", "description": "Which HN live feed to fetch. Only used when mode is 'feed'.", "default": "top" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of results to return.", "default": 100 }, "minPoints": { "title": "Minimum Points", "minimum": 0, "type": "integer", "description": "Filter stories with at least this many points. Only applies to mode=search." }, "minComments": { "title": "Minimum Comments", "minimum": 0, "type": "integer", "description": "Filter items with at least this many comments. Only applies to mode=search." }, "dateFrom": { "title": "Date From", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T.*)?$", "type": "string", "description": "Filter items published after this date. ISO 8601 format (e.g. 2024-01-01). Only applies to mode=search." }, "dateTo": { "title": "Date To", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T.*)?$", "type": "string", "description": "Filter items published before this date. ISO 8601 format (e.g. 2024-12-31). Only applies to mode=search." }, "author": { "title": "Author", "type": "string", "description": "Filter by HN username. Only applies to mode=search." }, "storyId": { "title": "Story ID", "type": "string", "description": "Fetch all comments for a specific story by its HN item ID. When provided with type=comment, overrides the query." }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Fetch comments for each story found. Increases run time and item count. Only applies to mode=search with type=story.", "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Hacker News Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: