{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Newsletter Posts, Search & Leaderboards", "description": "Scrape Substack newsletters: posts from any publication (archive, top posts, full text), Substack-wide post search and category leaderboards (bestseller and rising newsletters with paid tier, subscribers, prices and author). No login, no API key.", "version": "0.1", "x-build-id": "GgjuHydPGdYdYqHDN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datadesk-io~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datadesk-io-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datadesk-io~substack-scraper/runs": { "post": { "operationId": "runs-sync-datadesk-io-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datadesk-io~substack-scraper/run-sync": { "post": { "operationId": "run-sync-datadesk-io-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Newsletters (publications)", "type": "array", "description": "Substack newsletters to scrape: subdomain (lenny), substack.com address (lenny.substack.com), custom domain or URL (https://www.lennysnewsletter.com) or an author @handle (@lenny). Leave everything empty to get the latest posts of 2 sample newsletters.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs (optional)", "type": "array", "description": "Single posts to scrape with full text, e.g. https://www.lennysnewsletter.com/p/how-to-tell-if-a-startup-has-a-moat. Paid posts return only the free preview.", "items": { "type": "string" } }, "searchQueries": { "title": "Search Substack posts (optional)", "type": "array", "description": "Keywords to search across all of Substack (the same search as substack.com). Returns matching posts with their newsletter, author and engagement.", "items": { "type": "string" } }, "leaderboardCategories": { "title": "Leaderboard categories (optional)", "type": "array", "description": "Substack leaderboard categories to list newsletters from: technology, business, finance, culture, us-politics, world-politics, news, science, health, food, sports, music, art, crypto, education, history, fiction, literature, design, travel, parenting, philosophy, faith, climate, comics, humor, games, film-and-tv, fashionandbeauty, home-garden, international. One row per newsletter (rank, paid tier, subscribers, prices, author).", "items": { "type": "string" } }, "leaderboardType": { "title": "Leaderboard type", "enum": [ "paid", "trending" ], "type": "string", "description": "Which Substack leaderboard to read for the categories above.", "default": "paid" }, "maxPostsPerSource": { "title": "Max results per source", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Cap per newsletter, per search query and per leaderboard category. Newsletter archives are read 50 posts per page until this cap, the date limit or the first post.", "default": 25 }, "sort": { "title": "Newsletter post order", "enum": [ "new", "top" ], "type": "string", "description": "Order of newsletter archive posts: newest first or Substack's 'top' (most popular) order.", "default": "new" }, "includeContent": { "title": "Include full post text", "type": "boolean", "description": "Add the full post body (plain text and HTML) to every post. Costs one extra request per post (slower), same price. Paid posts only include the free preview part.", "default": false }, "postedAfter": { "title": "Only posts after (optional)", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])(T.*)?$", "type": "string", "description": "Skip posts older than this date (YYYY-MM-DD, UTC). With 'Newest first' the archive stops at the date, so older posts are never fetched or charged. Great for daily monitoring." }, "maxResults": { "title": "Max results in total", "minimum": 1, "type": "integer", "description": "Hard cap on rows (posts + publications) for the whole run. Never exceeded." } } }, "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 } } } } } } } } } }