{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper — Full Archive | $4/1K", "description": "Search the whole Hacker News archive past the 1000-result cap that stops every other scraper. Stories and comments by keyword, points and date. Front page feeds, comment trees as clean plain text, user profiles. For market research and developer sentiment analysis.", "version": "0.1", "x-build-id": "lSehUPLzIVn74Uci1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datawell~hackernews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datawell-hackernews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/datawell~hackernews-scraper/runs": { "post": { "operationId": "runs-sync-datawell-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/datawell~hackernews-scraper/run-sync": { "post": { "operationId": "run-sync-datawell-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": "What to scrape", "enum": [ "search", "frontPage", "comments", "users" ], "type": "string", "description": "Pick what you want to collect. The fields below apply depending on this choice.", "default": "search" }, "searchQuery": { "title": "Search term", "type": "string", "description": "Keyword or phrase to search for across every Hacker News post since 2007. Leave empty to get everything matching your filters." }, "contentType": { "title": "Stories or comments", "enum": [ "story", "comment", "ask_hn", "show_hn", "poll" ], "type": "string", "description": "What kind of item to search for. 'Ask HN' and 'Show HN' are separate categories on Hacker News.", "default": "story" }, "sortBy": { "title": "Sort order", "enum": [ "date", "relevance" ], "type": "string", "description": "'Newest first' can page through the entire archive. 'Most relevant' stops after 1000 results — a limit of the search backend.", "default": "date" }, "minPoints": { "title": "Minimum points", "minimum": 0, "type": "integer", "description": "Only items with at least this many upvotes. Set to 100 to get only stories that actually landed." }, "minComments": { "title": "Minimum comments", "minimum": 0, "type": "integer", "description": "Only items with at least this many comments — a good proxy for how contested a topic was." }, "since": { "title": "Posted after", "type": "string", "description": "Only items posted after this date. Format: 2026-01-31" }, "until": { "title": "Posted before", "type": "string", "description": "Only items posted before this date. Format: 2026-01-31" }, "listName": { "title": "Which list", "enum": [ "topstories", "newstories", "beststories", "askstories", "showstories", "jobstories" ], "type": "string", "description": "Which curated list to fetch. Used in front page mode.", "default": "topstories" }, "storyIds": { "title": "Story IDs or URLs", "type": "array", "description": "Item IDs (43217891) or Hacker News links (https://news.ycombinator.com/item?id=43217891). Used in comment mode.", "items": { "type": "string" } }, "maxDepth": { "title": "Comment depth", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many levels of replies to follow. Comments are collected breadth-first, so the top levels are complete before deeper ones.", "default": 10 }, "usernames": { "title": "Usernames", "type": "array", "description": "Hacker News usernames to look up. Used in user mode.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Total number of records to collect. With several stories, the budget is split evenly between them.", "default": 100 }, "requestDelaySeconds": { "title": "Delay between requests", "minimum": 0, "maximum": 10, "type": "integer", "description": "Seconds to wait between calls. Raise this for very large runs.", "default": 0 } } }, "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 } } } } } } } } } }