{ "openapi": "3.0.1", "info": { "title": "Substack Newsletter Scraper: Posts, Archive, Publication Data", "description": "Export any Substack newsletter's public posts, archive and publication details as clean JSON. Body text, engagement counts, comments. Pay per post.", "version": "1.1", "x-build-id": "8tX7tg31PaIUaVsbf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/titian_fluorite~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-titian_fluorite-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/titian_fluorite~substack-scraper/runs": { "post": { "operationId": "runs-sync-titian_fluorite-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/titian_fluorite~substack-scraper/run-sync": { "post": { "operationId": "run-sync-titian_fluorite-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "publications" ], "properties": { "publications": { "title": "Substack publications", "type": "array", "description": "The newsletters to scrape. Paste a full address such as https://www.lennysnewsletter.com, a Substack subdomain such as astralcodexten.substack.com, or just the handle, for example lenny. Custom domains and substack.com addresses both work.", "default": [ "https://www.lennysnewsletter.com", "https://www.astralcodexten.com", "newsletter.pragmaticengineer.com" ], "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Maximum posts per publication", "minimum": 0, "type": "integer", "description": "How many posts to return for each newsletter. Set 0 to take the whole archive. Every post you receive is billed, so start small when you are trying the Actor out.", "default": 50 }, "sort": { "title": "Order", "enum": [ "new", "top" ], "type": "string", "description": "Newest first gives you the latest issues, which is what you want for monitoring. Most popular gives you the newsletter's best performing posts of all time.", "default": "new" }, "postedAfter": { "title": "Only posts published after", "type": "string", "description": "Optional date filter, for example 2026-01-01. Posts published before this date are skipped and never billed. Leave empty to ignore dates." }, "includeBody": { "title": "Include the post body", "type": "boolean", "description": "Fetch the full article for every post and return it as HTML and as plain text. Turn this off for a faster, lighter run that returns titles, dates, authors and engagement counts only.", "default": true }, "includeComments": { "title": "Include public comments", "type": "boolean", "description": "Also return the public comment threads under each post as extra rows. Comments are billed separately, so this can add up on busy newsletters.", "default": false }, "postTypes": { "title": "Post types", "type": "array", "description": "Limit the results to certain kinds of post. Newsletter is a normal written issue. Leave all four selected to get everything.", "items": { "type": "string", "enum": [ "newsletter", "podcast", "thread", "video" ], "enumTitles": [ "Newsletter", "Podcast", "Thread", "Video" ] }, "default": [ "newsletter", "podcast", "thread", "video" ] }, "maxConcurrency": { "title": "Maximum concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many requests to run at once. The default is polite and works for every newsletter. Raise it only if you are scraping many publications and the run feels slow.", "default": 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 } } }, "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 } } } } } } } } } }