{ "openapi": "3.0.1", "info": { "title": "Substack Scraper — Posts, Comments, Notes & Search", "description": "Substack scraper and API: full posts, comments, Notes, keyword search, leaderboards and subscriber counts. Only-new-posts mode for schedules. JSON, CSV, Excel.", "version": "0.2", "x-build-id": "TyfE4KhYpcsxJTf9S" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/innolabs~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-innolabs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/innolabs~substack-scraper/runs": { "post": { "operationId": "runs-sync-innolabs-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/innolabs~substack-scraper/run-sync": { "post": { "operationId": "run-sync-innolabs-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "publications": { "title": "Publications", "type": "array", "description": "Substack newsletters to scrape: subdomains (on, lenny), hosts (on.substack.com, www.lennysnewsletter.com) or full URLs. Duplicates and aliases of the same publication are scraped once.", "items": { "type": "string" } }, "includePosts": { "title": "Include posts", "type": "boolean", "description": "Emit one dataset item per post with full bodyHtml, bodyText, authors, reactions and comment count.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Emit one dataset item per comment, including nested replies (parentId and depth preserved). Applies to publication posts and to posts found by search.", "default": false }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many posts to collect from each publication. Comments are fetched for these posts only. With a query, matching posts are collected up to this number (the actor scans at most 500 posts looking for matches).", "default": 50 }, "query": { "title": "Filter posts by keyword", "type": "string", "description": "Optional case-insensitive filter on post title or body text inside the publications above. To search all of Substack, use Search keywords instead.", "default": "" }, "sort": { "title": "Archive order", "enum": [ "new", "top" ], "type": "string", "description": "Order used for the archive: newest first, or the publication's top posts.", "default": "new" }, "onlyNewPosts": { "title": "Only new posts (incremental)", "type": "boolean", "description": "Push only posts that previous runs have not delivered. The actor remembers the newest post per publication (and the results seen per search keyword) in a named key-value store, so a daily schedule outputs just the new posts. The first run delivers posts normally and saves the state.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Keeps separate 'already seen' memory for different schedules or tasks. Letters, digits, '-' and '_' only. Change it to start fresh.", "default": "default" }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "Keywords or phrases searched across all of Substack, e.g. 'climate tech' or 'AI agents'. Each keyword is searched separately.", "items": { "type": "string" } }, "searchType": { "title": "Search for", "enum": [ "posts", "publications" ], "type": "string", "description": "Return matching posts (full post bodies, billed per post) or matching publications (newsletter profiles with subscriber counts, billed per publication).", "default": "posts" }, "maxSearchResults": { "title": "Max results per keyword", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many posts or publications to return for each keyword.", "default": 50 }, "leaderboardCategories": { "title": "Leaderboard categories", "type": "array", "description": "Category slugs or names (technology, business, culture, finance, us-politics, ...) or leaderboard URLs such as https://substack.com/leaderboard/technology/paid.", "items": { "type": "string" } }, "leaderboardType": { "title": "Leaderboard", "enum": [ "paid", "trending" ], "type": "string", "description": "Bestsellers (ranked by paid subscribers) or Rising (fastest-growing). A leaderboard URL in the list above overrides this.", "default": "paid" }, "maxPublicationsPerLeaderboard": { "title": "Max publications per leaderboard", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many ranked publications to return per category. Substack leaderboards list up to 100.", "default": 100 }, "noteProfiles": { "title": "Notes authors", "type": "array", "description": "Writers whose Notes to collect: @handle, handle, https://substack.com/@handle or https://substack.com/profile/-.", "items": { "type": "string" } }, "maxNotesPerProfile": { "title": "Max notes per author", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many of each writer's most recent Notes to collect.", "default": 50 }, "maxItems": { "title": "Max items", "minimum": 1, "type": "integer", "description": "Hard cap on dataset items across all item types. The run stops cleanly when reached.", "default": 1000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Use a proxy if Substack rate-limits or blocks the actor's IP.", "default": { "useApifyProxy": true } }, "debug": { "title": "Debug logging", "type": "boolean", "description": "Log per-publication progress and diagnostics.", "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 } } } } } } } } } }