{ "openapi": "3.0.1", "info": { "title": "Substack Scraper — Posts, Comments & Newsletter Data", "description": "Scrape Substack newsletters and custom domains: full posts as HTML and plain text, comments, subscriber counts, and topic search. Full archive depth. For research, lead lists and AI pipelines. Export JSON, CSV, Excel, or use the API.", "version": "0.1", "x-build-id": "efx4M5EhRLRNRnQU9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~substack-scraper/runs": { "post": { "operationId": "runs-sync-automation-lab-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~substack-scraper/run-sync": { "post": { "operationId": "run-sync-automation-lab-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Newsletter URLs", "type": "array", "description": "Substack newsletter URLs to scrape. Accepts homepage (e.g. https://newsletter.substack.com), custom domain (e.g. https://www.lennysnewsletter.com), post URLs, or /archive URLs.", "items": { "type": "string" } }, "keywords": { "title": "Discovery Keywords", "type": "array", "description": "Optional topics to search across public Substack posts, for example artificial intelligence or climate policy. Keyword results use the same post output as URL scraping.", "default": [], "items": { "type": "string" } }, "maxSearchResultsPerKeyword": { "title": "Max Search Results per Keyword", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum matching posts to process for each discovery keyword.", "default": 20 }, "maxPostsPerNewsletter": { "title": "Max Posts per Newsletter", "minimum": 0, "type": "integer", "description": "Maximum number of matching posts to deliver per newsletter, after filters. Set to 0 for unlimited (full archive).", "default": 100 }, "includeContent": { "title": "Include Post Content", "type": "boolean", "description": "Include the full body of each post as HTML (bodyHtml) and plain text (bodyText). Disable for metadata-only scraping (faster, cheaper).", "default": true }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Fetch comments for each post. Adds one extra API request per post.", "default": false }, "maxCommentsPerPost": { "title": "Max Comments per Post", "minimum": 0, "type": "integer", "description": "Maximum number of comments to return per post (including replies). Set to 0 for unlimited. Only applies when 'Include Comments' is enabled.", "default": 20 }, "includePublicationInfo": { "title": "Include Publication Info", "type": "boolean", "description": "Include newsletter metadata (subscriber count, description, language, logo, payments flag, author info). One extra request per newsletter.", "default": true }, "contentType": { "title": "Content Type Filter", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Filter by post type.", "default": "all" }, "startDate": { "title": "Start Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only include posts published after this date (YYYY-MM-DD format)." }, "endDate": { "title": "End Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only include posts published before this date (YYYY-MM-DD format)." }, "onlyFree": { "title": "Free Posts Only", "type": "boolean", "description": "Only include free posts. Skip paywalled content.", "default": 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 } } } } } } } } } }