{ "openapi": "3.0.1", "info": { "title": "Substack Posts & Newsletters Scraper", "description": "Scrape Substack posts and find newsletters by category leaderboard: titles, dates, likes, comments, free-post text, subscriber counts, prices, author social links and recommendations.", "version": "0.1", "x-build-id": "5eZJcMmYmozHUZ0QL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thisisb3~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thisisb3-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thisisb3~substack-scraper/runs": { "post": { "operationId": "runs-sync-thisisb3-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thisisb3~substack-scraper/run-sync": { "post": { "operationId": "run-sync-thisisb3-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Newsletters to scrape. Paste the address as you see it: name.substack.com, a custom domain such as www.astralcodexten.com, or any link to the publication. You get its latest posts and, unless you switch it off below, one row with the publication's details.", "items": { "type": "string" } }, "categories": { "title": "Categories (find newsletters)", "type": "array", "description": "Discover newsletters by Substack category. Each category returns its top publications as publication rows: name, leaderboard rank, subscriber count, prices, authors and their social links. Posts are not scraped for these; paste the ones you like into Publications.", "items": { "type": "string", "enum": [ "culture", "technology", "business", "us-politics", "finance", "food", "sports", "art", "world-politics", "health-politics", "news", "fashionandbeauty", "music", "faith", "climate", "science", "literature", "fiction", "health", "design", "travel", "parenting", "philosophy", "comics", "international", "crypto", "history", "humor", "education", "film-and-tv", "home-garden", "games" ], "enumTitles": [ "Culture", "Technology", "Business", "U.S. Politics", "Finance", "Food & Drink", "Sports", "Art & Illustration", "World Politics", "Health Politics", "News", "Fashion & Beauty", "Music", "Faith & Spirituality", "Climate & Environment", "Science", "Literature", "Fiction", "Health & Wellness", "Design", "Travel", "Parenting", "Philosophy", "Comics", "International", "Crypto", "History", "Humor", "Education", "Film & TV", "Home & Garden", "Games" ] } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Individual posts to scrape, e.g. https://name.substack.com/p/post-title. Links copied from the Substack app (substack.com/@name/p-123456789) work too.", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Latest posts to scrape from each publication in Publications, newest first. Set to 0 to skip posts and get only the publication rows.", "default": 20 }, "includeFullText": { "title": "Include full text of free posts", "type": "boolean", "description": "Adds the post text (plain text and HTML) for free, public posts. Paywalled and subscriber-only posts never include text. Rows with text are billed as \"post with full text\".", "default": false }, "includePublicationInfo": { "title": "Include publication details", "type": "boolean", "description": "Adds one row per publication in Publications: name, category, leaderboard rank, subscriber count, prices, authors and their public social links.", "default": true }, "includeRecommendations": { "title": "Include recommended newsletters", "type": "boolean", "description": "Adds the newsletters each publication recommends (its recommendation network) to its publication row. One extra request per publication.", "default": false }, "categoryRanking": { "title": "Category list", "enum": [ "bestsellers", "all" ], "type": "string", "description": "Bestsellers is Substack's paid leaderboard for the category (ranked, with the leaderboard rank in each row). All newsletters lists every publication in the category, including free ones, without a leaderboard rank.", "default": "bestsellers" }, "maxPublicationsPerCategory": { "title": "Max publications per category", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many publications to return from each category, from the top of the list. Substack's leaderboard pages show the top 25.", "default": 25 }, "maxItems": { "title": "Maximum results", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop after this many rows in total (posts plus publications). Set to 0 for no limit. You are only charged for rows you receive.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many requests run in parallel; also the most requests started per second. The default is deliberately polite, and the scraper slows down automatically if Substack asks it to.", "default": 4 } } }, "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 } } } } } } } } } }