{ "openapi": "3.0.1", "info": { "title": "Astral Codex Ten (ACX) Scraper — Posts & Comments", "description": "Scrape Astral Codex Ten (astralcodexten.com) by Scott Alexander: post title, date, full text, tags, reactions and reader comments. Cross-run caching returns only new posts. Export to JSON, CSV or Excel, or call it as an API.", "version": "1.0", "x-build-id": "Z2ZhEq01dKeVEivgV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/confidential_gnat~astralcodexten-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-confidential_gnat-astralcodexten-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/confidential_gnat~astralcodexten-scraper/runs": { "post": { "operationId": "runs-sync-confidential_gnat-astralcodexten-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/confidential_gnat~astralcodexten-scraper/run-sync": { "post": { "operationId": "run-sync-confidential_gnat-astralcodexten-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Astral Codex Ten archive or post URLs. Accepts the archive (https://www.astralcodexten.com/archive), the home page, and single post URLs (https://www.astralcodexten.com/p/some-post). Old astralcodexten.substack.com links work too. Page type is detected automatically.", "default": [ { "url": "https://www.astralcodexten.com/archive" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max posts per start URL", "minimum": 0, "type": "integer", "description": "Maximum number of posts to scrape per start URL. Set to 0 for no limit.", "default": 5 }, "includePaywalled": { "title": "Include paywalled posts", "type": "boolean", "description": "Subscriber-only posts return only a short public preview rather than the full text. Leave enabled to collect them with an isPaywalled flag, or disable to skip them entirely.", "default": true }, "cacheProjectName": { "title": "Cache project name (scrape only new posts)", "type": "string", "description": "Scrape only new posts. Give this run a name (e.g. \"acx-new-posts\") and reuse it: every later run with the same name skips posts already collected and returns only newly published ones, so the same post is never scraped or billed twice. Ideal for scheduled monitoring. Leave empty to scrape everything every time." }, "scrapeComments": { "title": "Scrape comments", "type": "boolean", "description": "Also collect each post's reader comments and replies.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "type": "integer", "description": "Maximum comments (including replies) to collect per post, best comments first. Set to 0 for all comments.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Astral Codex Ten is reachable without a proxy, so proxies are disabled by default to keep runs cheap.", "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 }, "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 } } } } } } } } } }