{ "openapi": "3.0.1", "info": { "title": "Substack Scraper — Newsletters, Posts, Authors & Subscribers", "description": "Discover Substack newsletters by category & leaderboard rank, then pull every post, author and publication. 30+ categories or direct subdomain. Per post: title, audience (free/paid), reactions, restacks. Per pub: subdomain, custom domain, author, subscription tiers. Public Substack API — no auth.", "version": "1.0", "x-build-id": "5FycbOg5Y4R6yJ9RG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~substack-newsletter-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-substack-newsletter-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~substack-newsletter-scraper/runs": { "post": { "operationId": "runs-sync-logiover-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~substack-newsletter-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "categorySlugs": { "title": "Category Slugs to Discover", "type": "array", "description": "Substack categories to enumerate. Slugs: 'technology', 'business', 'finance', 'crypto', 'news', 'us-politics', 'world-politics', 'culture', 'science', 'health', 'design', 'travel', 'parenting', 'literature', 'fiction', 'philosophy', 'history', 'climate', 'art', 'music', 'sports', 'food', 'film-and-tv', 'comics', 'humor', 'fashionandbeauty', 'education', 'faith', 'international', 'home-garden'. Leave empty if you supply newsletter URLs directly.", "default": [], "items": { "type": "string" } }, "categoryRanking": { "title": "Category Ranking Mode", "enum": [ "leaderboard", "paid", "all" ], "type": "string", "description": "How to sort publications within each category. 'leaderboard' = top newsletters (most subscribers + engagement), 'paid' = top paid newsletters, 'all' = all publications sorted by Substack's default ranking.", "default": "leaderboard" }, "newsletterUrls": { "title": "Direct Newsletter URLs", "type": "array", "description": "Specific Substack publications to scrape, regardless of category. Accepts subdomains ('lennysnewsletter.substack.com'), bare names ('lennysnewsletter'), or custom domains ('www.lennysnewsletter.com').", "default": [], "items": { "type": "string" } }, "maxPublicationsPerCategory": { "title": "Max Publications Per Category", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard cap on publications enumerated per category. Substack returns 25 per page, the actor paginates automatically up to this cap.", "default": 25 }, "maxPostsPerPublication": { "title": "Max Posts Per Publication", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Hard cap on posts pulled per publication via the archive API (paginates 12 per page). Set to 0 to skip post fetching entirely (publication-only mode).", "default": 50 }, "audienceFilter": { "title": "Audience Filter", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter posts by audience. 'all' = both free and paid, 'free' = free-only posts (the type any subscriber can read), 'paid' = paid-only posts (premium).", "default": "all" }, "minPostDate": { "title": "Minimum Post Date (ISO)", "type": "string", "description": "Filter posts to those published on or after this date (YYYY-MM-DD). Leave empty for no lower bound.", "default": null }, "maxPostDate": { "title": "Maximum Post Date (ISO)", "type": "string", "description": "Filter posts to those published on or before this date (YYYY-MM-DD). Leave empty for no upper bound.", "default": null }, "keywordFilter": { "title": "Keyword Filter (post title / subtitle)", "type": "array", "description": "Only save posts whose title or subtitle contains any of these terms (case-insensitive substring match, applied client-side after fetch). Examples: ['ai', 'gpt'], ['layoffs'], ['startup']. Leave empty for no filter.", "default": [], "items": { "type": "string" } }, "includePublicationMetadata": { "title": "Include Publication Metadata in Each Record", "type": "boolean", "description": "When enabled, every post record is enriched with parent-publication fields (subdomain, custom domain, author name, hero description, category, language, free / paid subscription benefits, founded date). Disable for smaller per-row records.", "default": true }, "alsoPushPublicationRecord": { "title": "Also Push Publication-Level Records", "type": "boolean", "description": "When enabled, the actor also pushes one record per discovered publication (with `recordType: 'publication'`) in addition to per-post records. Useful when you want a denormalized list of newsletters in the same dataset.", "default": false }, "language": { "title": "Publication Language Filter", "type": "string", "description": "Restrict to publications in a specific language (ISO 639-1). 'en' for English-only. Leave empty for all languages.", "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 } } }, "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 } } } } } } } } } }