{ "openapi": "3.0.1", "info": { "title": "Substack Posts Scraper", "description": "Extract posts from any Substack publication: title, subtitle, authors, date, type, paywall status, reactions, comments, restacks, podcast audio and optionally the full body (HTML and text). Works with custom domains, no login, uses Substack's public JSON endpoints. Export to JSON, CSV or Excel.", "version": "0.1", "x-build-id": "Tt4hMz6J0M2gPYXBS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/davidts~substack-posts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-davidts-substack-posts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/davidts~substack-posts-scraper/runs": { "post": { "operationId": "runs-sync-davidts-substack-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/davidts~substack-posts-scraper/run-sync": { "post": { "operationId": "run-sync-davidts-substack-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Publications", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Substack publications to scrape. Each entry can be a full URL (`https://www.lennysnewsletter.com`), a Substack subdomain (`lenny` or `lenny.substack.com`), or a custom domain (`newsletter.pragmaticengineer.com`). Publications that moved to a custom domain are followed automatically. Tip: copy the address shown in your browser when you open the newsletter.", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "type": "integer", "description": "Maximum number of posts to save for each publication. Use `0` to scrape the whole archive. Each saved post is one dataset item (and one paid result). For a quick sample use 10-20; for a full export use 0.", "default": 100 }, "sort": { "title": "Sort order", "enum": [ "new", "top" ], "type": "string", "description": "`new` returns the newest posts first (chronological). `top` returns posts in Substack's own popularity order, which is not chronological, so `publishedAfter` cannot be combined with it.", "default": "new" }, "includePostBody": { "title": "Include post body", "type": "boolean", "description": "Fetch every post individually and add `bodyHtml` and `bodyText`. Free posts get the full body; paywalled posts get only the public preview (and `paywalled: true`). This roughly doubles the number of requests and makes runs slower. Turn it on when you need the text (for analysis, AI or search); leave it off for titles, dates and engagement only. The price per post is the same.", "default": false }, "publishedAfter": { "title": "Published after", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])(T[0-2]\\d:[0-5]\\d(:[0-5]\\d)?(\\.\\d+)?Z?)?$|^(\\d+)\\s*(minute|hour|day|week|month|year)s?$", "type": "string", "description": "Only save posts published on or after this date and stop paging once older posts are reached. Accepts an absolute date (`2026-01-31` or full ISO 8601 such as `2026-01-31T10:00:00Z`, interpreted in UTC) or a relative period (`7 days`, `2 weeks`, `3 months`). Only valid with the `new` sort order. For a scheduled daily or weekly run, use `1 day` or `7 days` to save only new posts." }, "postTypes": { "title": "Post types", "uniqueItems": true, "type": "array", "description": "Only keep posts of these types. Leave empty to keep all types (newsletter, podcast, video, thread).", "items": { "type": "string", "enum": [ "newsletter", "podcast", "video", "thread" ], "enumTitles": [ "Newsletter (articles)", "Podcast episodes", "Video posts", "Threads (discussions)" ] } }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxies used for requests to Substack. Apify datacenter proxies (the default) work for normal volumes. If you see repeated 403/429 errors in the log, switch to residential proxies, which cost more but are rarely blocked.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }