{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Newsletter Posts, Likes & Comments", "description": "Scrape posts from any Substack newsletter (subdomain or custom domain): title, subtitle, date, authors, likes, comments, wordcount, paid/free and full text of free posts. Date range, category discovery and a new-posts monitor mode.", "version": "1.0", "x-build-id": "OfKDxJHUCNVT79oCF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sysco32~substack-newsletter-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sysco32-substack-newsletter-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sysco32~substack-newsletter-scraper/runs": { "post": { "operationId": "runs-sync-sysco32-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sysco32~substack-newsletter-scraper/run-sync": { "post": { "operationId": "run-sync-sysco32-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "publications" ], "properties": { "publications": { "title": "Substack publications or post URLs", "type": "array", "description": "One per line. Accepted forms:
• A subdomain: noahpinion
• A Substack URL: https://astralcodexten.substack.com
• A custom domain: https://www.lennysnewsletter.com
• A single post URL: https://www.lennysnewsletter.com/p/some-post or https://open.substack.com/pub/name/p/some-post
• An author profile: @lenny or https://substack.com/@lenny (uses the author's main publication)
Only public data is read; no login is used.", "default": [ "https://www.lennysnewsletter.com", "astralcodexten.substack.com", "noahpinion" ], "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "type": "integer", "description": "Newest-first. Set 0 to get the whole archive (respects the date range).", "default": 10 }, "dateFrom": { "title": "Published on or after", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}.*$|^\\d+\\s*(day|week|month|year)s?(\\s+ago)?$", "type": "string", "description": "Absolute date 2026-01-01 or relative like 30 days, 2 weeks, 6 months. Leave empty for no lower limit." }, "dateTo": { "title": "Published on or before", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}.*$|^\\d+\\s*(day|week|month|year)s?(\\s+ago)?$", "type": "string", "description": "Absolute date 2026-06-30 or relative like 7 days. Leave empty for no upper limit." }, "audience": { "title": "Post access", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter by audience. For paid posts only the public preview text is returned.", "default": "all" }, "includeContent": { "title": "Include post content", "type": "boolean", "description": "Fetch each post's body as plain text (and HTML). Free posts: full text. Paywalled posts: only the public preview that Substack shows to logged-out readers. Turn off for faster metadata-only runs (title, date, likes, comments, wordcount, …).", "default": true }, "includeHtml": { "title": "Include HTML body", "type": "boolean", "description": "Also store content_html (only when content is included).", "default": true }, "onlyNewPosts": { "title": "Only new posts (monitor mode)", "type": "boolean", "description": "Output only posts that previous runs have not output yet. Each run checks the latest posts (up to Max posts per publication) and remembers what it has seen in a named key-value store. Schedule the Actor to get a feed of new posts; you only pay for new ones.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store that remembers seen posts. Use different names for independent monitors.", "default": "substack-scraper-seen" }, "discoverCategory": { "title": "Discover publications by category", "enum": [ "none", "technology", "business", "finance", "culture", "us-politics", "world-politics", "news", "science", "health", "crypto", "food", "sports", "music", "art", "fiction", "literature", "history", "philosophy", "education", "design", "climate", "faith", "parenting", "travel", "humor", "comics", "fashionandbeauty", "film-and-tv", "games", "home-garden", "international", "health-politics", "podcast" ], "type": "string", "description": "Optionally add the top publications of a Substack category (from Substack's public directory) to the list above.", "default": "none" }, "maxDiscoveredPublications": { "title": "Max publications to discover", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many top publications to take from the chosen category.", "default": 10 }, "maxConcurrency": { "title": "Publications in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many publications are scraped at the same time. Requests to any single site are still throttled.", "default": 4 }, "requestIntervalSecs": { "title": "Min seconds between requests to one site", "minimum": 0.2, "maximum": 10, "type": "number", "description": "Politeness delay per host. Requests are also retried with backoff on HTTP 429/5xx.", "default": 0.5 } } }, "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 } } } } } } } } } }