{ "openapi": "3.0.1", "info": { "title": "Hacker News Stories & Comments Scraper", "description": "Hacker News Scraper SD - Hacker News Scraper is a news data tool that extracts Hacker News stories and comments from the front page, new, best, Ask HN, Show HN, jobs and Who is hiring threads, plus full-text search and comment trees via the official APIs.", "version": "1.0", "x-build-id": "AsmSn876r1gMZ74QC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~hacker-news-stories-comments-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-hacker-news-stories-comments-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~hacker-news-stories-comments-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-hacker-news-stories-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~hacker-news-stories-comments-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-hacker-news-stories-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "lists": { "title": "Lists", "type": "array", "description": "Live Hacker News lists. Top = the front page order. Job = YC company job posts. Who is hiring = the top-level job posts of the latest monthly \"Ask HN: Who is hiring?\" thread.", "items": { "type": "string", "enum": [ "top", "new", "best", "ask", "show", "job", "whoishiring" ], "enumTitles": [ "Front page (top)", "New", "Best", "Ask HN", "Show HN", "Jobs (YC companies)", "Who is hiring? (latest thread)" ] } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Full-text search of Hacker News, one term per line. Example: web scraping", "items": { "type": "string" } }, "searchType": { "title": "Search in", "enum": [ "story", "comment", "all" ], "type": "string", "description": "Search terms only.", "default": "story" }, "searchSort": { "title": "Search order", "enum": [ "relevance", "date" ], "type": "string", "description": "Search terms only. Relevance stops at 1,000 results (Algolia's limit); Newest first can go back through all of Hacker News.", "default": "relevance" }, "fuzzyMatching": { "title": "Fuzzy matching (typo tolerance)", "type": "boolean", "description": "Search terms only. Off (recommended) = exact words, complete and stable results. On = Algolia's typo tolerance, which also matches misspellings but answers non-exhaustively (measured: the same query returned between 52 and 175 stories).", "default": false }, "dateFrom": { "title": "Posted on or after", "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$", "type": "string", "description": "Search terms only, optional. Date as YYYY-MM-DD." }, "dateTo": { "title": "Posted on or before", "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$", "type": "string", "description": "Search terms only, optional. Date as YYYY-MM-DD." }, "minPoints": { "title": "Minimum points", "minimum": 0, "type": "integer", "description": "Search terms only, optional. Only stories with at least this many points (comments have no points and are excluded when this is set)." }, "storyUrls": { "title": "Story links (story + comments)", "type": "array", "description": "Optional. Links like https://news.ycombinator.com/item?id=8863 or plain ids. Returns the item and its whole comment tree (depth 0 = the item).", "items": { "type": "string" } }, "maxResults": { "title": "Max results per list, search or story", "minimum": 1, "type": "integer", "description": "How many rows to return for each list, search term and story link.", "default": 30 }, "maxItems": { "title": "Max rows in total", "minimum": 1, "type": "integer", "description": "Optional cap on the whole run. Leave empty for no total cap." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Not needed: the official Hacker News APIs are open.", "default": { "useApifyProxy": 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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }