{ "openapi": "3.0.1", "info": { "title": "Hacker News Scraper – Stories, Comments, Search & Who's Hiring", "description": "Hacker News data from the official API and Algolia HN Search: top/new/best/Ask/Show/job stories, keyword and brand monitoring with only-new alerts, full comment trees flattened with depth, and the monthly Who is hiring thread parsed into job posts.", "version": "0.1", "x-build-id": "6twiFfKaZJ6Q0DBuw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~hacker-news-data/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-hacker-news-data", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~hacker-news-data/runs": { "post": { "operationId": "runs-sync-gazidev-hacker-news-data", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~hacker-news-data/run-sync": { "post": { "operationId": "run-sync-gazidev-hacker-news-data", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 get", "enum": [ "lists", "search", "items", "whoIsHiring" ], "type": "string", "description": "**Story lists**: front page (top), new, best, Ask HN, Show HN or job stories. **Search & monitor**: keyword or brand search in stories and/or comments (Algolia HN Search), with date range and points/comments thresholds. **Items + comments**: one or more stories (IDs or URLs) with the full comment tree. **Who is hiring**: the monthly 'Ask HN: Who is hiring?' thread split into job posts.", "default": "lists" }, "lists": { "title": "Lists", "type": "array", "description": "Used in **Story lists** mode. `top` = the front page ranking.", "items": { "type": "string", "enum": [ "top", "new", "best", "ask", "show", "job" ], "enumTitles": [ "Top (front page)", "New", "Best", "Ask HN", "Show HN", "Jobs (YC companies)" ] }, "default": [ "top" ] }, "maxItemsPerList": { "title": "Stories per list", "minimum": 1, "maximum": 500, "type": "integer", "description": "Top N of each list, in HN ranking order (`rank`). HN keeps up to 500 (top/new/best) or 200 (ask/show/job).", "default": 30 }, "searchQueries": { "title": "Search queries / brands", "type": "array", "description": "Used in **Search & monitor** mode. One query per line, e.g. a brand, product, domain or topic. Use quotes for a phrase (`\"web scraping\"`). Each result has `matchedQuery`.", "items": { "type": "string" } }, "searchTags": { "title": "Search in", "enum": [ "story", "comment", "storyOrComment", "showHn", "askHn", "poll", "frontPage", "any" ], "type": "string", "description": "Which kind of items to search.", "default": "story" }, "sortBy": { "title": "Sort by", "enum": [ "date", "relevance" ], "type": "string", "description": "`date` = newest first, no limit on the number of results (use this for monitoring). `relevance` = Algolia ranking (points, matches), max 1,000 results per query.", "default": "date" }, "createdAfter": { "title": "Created after", "type": "string", "description": "Only items created on or after this date. Absolute (`2026-09-01`) or relative (`7 days`, `24 hours`)." }, "createdBefore": { "title": "Created before", "type": "string", "description": "Only items created before this date." }, "minPoints": { "title": "Min points", "minimum": 0, "type": "integer", "description": "Stories only (comments have no public points). 0 = off.", "default": 0 }, "minComments": { "title": "Min comments", "minimum": 0, "type": "integer", "description": "Stories only. 0 = off.", "default": 0 }, "author": { "title": "Author (HN username)", "type": "string", "description": "Optional. Only items by this user. Can be used without a query to get a user's latest stories or comments." }, "maxResultsPerQuery": { "title": "Max results per query", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Newest first when sorted by date.", "default": 100 }, "exactMatch": { "title": "Strict matching (no typos)", "type": "boolean", "description": "Algolia matches typos by default (`rust` also finds `trust`). On: typo tolerance is switched off and every query word must appear at the start of a word in the title, text, URL or story title (`postgres` still finds `PostgreSQL`). Dropped results are free.", "default": true }, "itemIds": { "title": "Item IDs or URLs", "type": "array", "description": "Used in **Items + comments** mode. HN item IDs (`8863`) or URLs (`https://news.ycombinator.com/item?id=8863`). Returns the item and all its comments.", "items": { "type": "string" } }, "includeComments": { "title": "Also get comments in lists / search", "type": "boolean", "description": "In **Story lists** and **Search** mode, also save the full comment tree of each story (each comment is a row and is charged as an item). Always on in Items mode.", "default": false }, "maxCommentDepth": { "title": "Max comment depth", "minimum": 0, "type": "integer", "description": "1 = top-level comments only, 2 = plus direct replies, 0 = all levels.", "default": 0 }, "maxCommentsPerItem": { "title": "Max comments per item", "minimum": 0, "type": "integer", "description": "0 = all. Comments are taken in thread order (top-level by HN ranking, each followed by its replies).", "default": 0 }, "includeDeletedComments": { "title": "Include deleted / dead comments", "type": "boolean", "description": "Off: deleted and flagged (dead) comments are skipped, their replies are kept.", "default": false }, "commentSource": { "title": "Comment source", "enum": [ "auto", "firebase" ], "type": "string", "description": "`auto`: whole tree from Algolia in one request (fast, top level in HN ranking order, replies by time), falls back to the official API when Algolia is incomplete. `firebase`: official API only (live, exact HN order, one request per comment - slower on big threads).", "default": "auto" }, "hiringMonth": { "title": "Month", "type": "string", "description": "Used in **Who is hiring** mode. `latest`, `2026-09` or `September 2026`.", "default": "latest" }, "hiringKeywords": { "title": "Keywords", "type": "array", "description": "Optional. Keep only job posts containing these words (whole words, case-insensitive), e.g. `python`, `rust`, `Berlin`. Filtered posts are free.", "items": { "type": "string" } }, "hiringKeywordsMode": { "title": "Keyword match", "enum": [ "any", "all" ], "type": "string", "description": "Any keyword or all keywords.", "default": "any" }, "remoteOnly": { "title": "Remote jobs only", "type": "boolean", "description": "Keep only posts detected as remote (`remote: true`).", "default": false }, "onlyNew": { "title": "Only new since the last run", "type": "boolean", "description": "Remembers what was already returned (in a named key-value store derived from this input) and outputs only new stories, search results, comments or job posts. Schedule the Actor hourly or daily for brand alerts, new comments on a thread or new job posts. The first run returns the current results.", "default": false }, "stateKey": { "title": "Monitoring state name", "type": "string", "description": "Optional. By default the memory is tied to this input. Set a name to keep the memory when you edit the input." }, "maxItems": { "title": "Max rows in total", "minimum": 0, "type": "integer", "description": "Stop after this many rows (stories + comments + job posts). 0 = no limit. You pay only for rows saved.", "default": 0 }, "includeHtml": { "title": "Include original HTML", "type": "boolean", "description": "Add `textHtml` with HN's HTML next to the plain `text`.", "default": false }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests to the official API (Algolia is always limited to 4).", "default": 20 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Failed requests are retried 3 times with backoff.", "default": 30 } } }, "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 } } } } } } } } } }