{ "openapi": "3.0.1", "info": { "title": "Substack Scraper to Markdown for AI, RAG & LLMs", "description": "Export Substack newsletter posts as clean Markdown, text or HTML with metadata and ready-made RAG chunks. Works with substack.com and custom domains, skips paywalled content, monitors new posts.", "version": "1.0", "x-build-id": "faLZaeBloFyRmZyfe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mersetti~substack-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mersetti-substack-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mersetti~substack-to-markdown/runs": { "post": { "operationId": "runs-sync-mersetti-substack-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mersetti~substack-to-markdown/run-sync": { "post": { "operationId": "run-sync-mersetti-substack-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 posts", "type": "array", "description": "Publication URLs (https://name.substack.com or a custom domain like https://www.lennysnewsletter.com), bare names (astralcodexten) or single post URLs (https://.../p/post-slug).", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "type": "integer", "description": "Newest posts first.", "default": 50 }, "postedAfter": { "title": "Posted after (date)", "type": "string", "description": "Only posts published after this date, format YYYY-MM-DD. Empty = any date." }, "keywords": { "title": "Keywords (any match)", "type": "array", "description": "Keep only posts whose title, subtitle or tags contain any of these words.", "items": { "type": "string" } }, "includeContent": { "title": "Include full content", "type": "boolean", "description": "Full post body for free posts. Turn off to get metadata only (faster).", "default": true }, "contentFormat": { "title": "Content format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Markdown is best for LLMs and RAG.", "default": "markdown" }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "type": "integer", "description": "Split content into chunks of up to N characters on paragraph boundaries, each with its section heading. 0 = no chunking. 1500–3000 works well for embeddings.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "type": "integer", "description": "Characters repeated from the previous chunk for context.", "default": 200 }, "includePaidPosts": { "title": "Include paywalled posts (metadata only)", "type": "boolean", "description": "Paid posts are returned with metadata and a short public teaser only — never the paywalled body.", "default": false }, "onlyNewPosts": { "title": "Only new posts (monitoring)", "type": "boolean", "description": "Remember posts between runs and return only posts not returned before. Schedule the Actor to build a newsletter feed.", "default": false }, "monitorId": { "title": "Monitor ID", "type": "string", "description": "Name of the saved state. Use different IDs for different feeds.", "default": "default" } } }, "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 } } } } } } } } } }