{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Full Text, Comments, Newsletter Data", "description": "Scrape Substack newsletters: posts with likes, comments, restacks, word count and audience, full post text on request, comments as rows, and newsletter details with author and subscriber tier. Custom domains, new posts only; JSON, CSV, API.", "version": "0.1", "x-build-id": "uHK26ysTeCpbbKWOY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deriverge~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deriverge-substack-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/deriverge~substack-scraper/runs": { "post": { "operationId": "runs-sync-deriverge-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/deriverge~substack-scraper/run-sync": { "post": { "operationId": "run-sync-deriverge-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "newsletters": { "title": "Newsletters", "type": "array", "description": "Substack newsletters in any form: a subdomain such as lenny, a substack.com address, a custom domain or a link to any of their posts.", "items": { "type": "string" } }, "sort": { "title": "Archive order", "enum": [ "new", "top" ], "type": "string", "description": "Newest first is what a monitor wants; most liked first finds the classics.", "default": "new" }, "maxPostsPerNewsletter": { "title": "Maximum posts per newsletter", "minimum": 1, "type": "integer", "description": "Newest first. Archives go back years, so this is what keeps a broad run affordable.", "default": 50 }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Drop posts older than this date (YYYY-MM-DD). Dropped posts are never charged." }, "audience": { "title": "Audience", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Substack marks each post as free for everyone or for paying subscribers.", "default": "all" }, "keywords": { "title": "Keywords (any of)", "type": "array", "description": "Keep only posts whose title, subtitle, description or preview contain at least one of these words, case-insensitive. Dropped posts are never charged.", "items": { "type": "string" } }, "includeBody": { "title": "Include post text", "type": "boolean", "description": "Fetch each post and return its text as plain text and as HTML. Paid posts return the free preview and the row says so. One extra request per post, charged as a post detail.", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Return the comments under each post as separate rows with author, date, likes and replies. Charged per comment.", "default": false }, "maxCommentsPerPost": { "title": "Maximum comments per post", "minimum": 1, "type": "integer", "description": "Replies count towards the cap.", "default": 100 }, "commentSort": { "title": "Comment order", "enum": [ "best_first", "newest_first", "oldest_first" ], "type": "string", "description": "The order Substack returns them in; the cap applies after ordering.", "default": "best_first" }, "includeNewsletterInfo": { "title": "Include newsletter header", "type": "boolean", "description": "One row per newsletter with name, author, description, launch date, subscriber tier, language and whether it has paid plans or a podcast. Charged once per newsletter.", "default": true }, "newOnly": { "title": "Return only rows new since the last run", "type": "boolean", "description": "Keeps a snapshot per watch name (or per saved task) and returns only posts, comments and newsletters that were not there before. Schedule it daily and you have a new-post alert that bills only for what is new.", "default": false }, "watchName": { "title": "Watch name", "type": "string", "description": "Name of the snapshot used by the new-only mode, for example \"my-newsletters\". Runs from a saved task get a snapshot automatically even without a name." }, "maxItems": { "title": "Maximum rows", "minimum": 1, "type": "integer", "description": "Hard cap on returned rows in the run.", "default": 10000 } } }, "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 } } } } } } } } } }