{ "openapi": "3.0.1", "info": { "title": "Hacker News Historical Archive Scraper — Old Stories by Date", "description": "Bulk-export the entire Hacker News archive between any two dates in chronological order. Stories, comments, Ask/Show HN, polls and jobs since 2006 via the keyless Algolia HN API. Time-windowed firehose yields hundreds of thousands of rows. No API key, no login.", "version": "1.0", "x-build-id": "HaFwMFbm9cFpcymYn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~hacker-news-historical-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-hacker-news-historical-archive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~hacker-news-historical-archive-scraper/runs": { "post": { "operationId": "runs-sync-logiover-hacker-news-historical-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~hacker-news-historical-archive-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-hacker-news-historical-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startDate", "endDate" ], "properties": { "contentType": { "title": "Content Type", "enum": [ "story", "comment", "show_hn", "ask_hn", "poll", "job", "front_page", "all" ], "type": "string", "description": "Which kind of Hacker News item to export. 'Stories' = link + text posts (the classic front-page firehose). 'Comments' = every comment body with its parent/story. 'Show HN' / 'Ask HN' = those two dedicated categories. 'Polls', 'Jobs' = those item types. 'All' = stories + comments + polls + jobs combined in one chronological stream.", "default": "story" }, "startDate": { "title": "Start Date (inclusive, UTC)", "type": "string", "description": "The oldest date to include, as YYYY-MM-DD (UTC). Everything created on or after this date is exported. HN launched in 2006, so any date from 2006-10-01 onward is reachable. Example: '2024-01-01'." }, "endDate": { "title": "End Date (inclusive, UTC)", "type": "string", "description": "The newest date to include, as YYYY-MM-DD (UTC). Everything created on or before the END of this day is exported. Combine with Start Date to define your window. Example: '2024-01-08'." }, "query": { "title": "Keyword filter (optional)", "type": "string", "description": "OPTIONAL keyword to narrow the export (matched against titles, text and comment bodies). Leave EMPTY for a pure firehose that returns every item in the date window. Use this only if you want a topic slice, e.g. 'openai', 'rust', 'layoffs'.", "default": "" }, "authors": { "title": "Authors (optional)", "type": "array", "description": "OPTIONAL list of Hacker News usernames to restrict the export to (no @ prefix). Each username is queried separately across the date window. Leave empty to include all authors. Example: ['pg', 'dang', 'patio11'].", "default": [], "items": { "type": "string" } }, "minPoints": { "title": "Minimum Points", "minimum": 0, "type": "integer", "description": "Only include items with at least this many points (upvotes). 0 = no filter. Useful to pull only high-engagement stories. Note: comments and jobs do not carry points, so a non-zero value effectively limits results to stories/polls.", "default": 0 }, "minComments": { "title": "Minimum Comments", "minimum": 0, "type": "integer", "description": "Only include items with at least this many comments. 0 = no filter. Applies to stories/Ask/Show/polls (comments themselves have no comment count).", "default": 0 }, "maxItems": { "title": "Max Items", "minimum": 0, "type": "integer", "description": "Global hard cap on rows returned by the run. Default 5000 is a sane starting point; raise it (e.g. 100000+) to pull a full multi-year corpus. 0 = unlimited (bounded only by the date window and the run timeout).", "default": 5000 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy configuration. The Algolia HN Search API is a fast public CDN endpoint that works over a direct connection, so datacenter proxy (the default) is plenty and keeps cost low. A fresh proxy session is minted per retry to rotate away from any throttled IP.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }