{ "openapi": "3.0.1", "info": { "title": "Substack Scraper - Posts, Full Text, Search & Newsletter Leads", "description": "Scrape any Substack newsletter: posts with full text & comments, keyword search across Substack, and top newsletters per category with subscriber counts, author socials, paid prices & sponsors. New-post monitoring.", "version": "0.0", "x-build-id": "X6iBYhKMbow7dteIr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pantomath~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pantomath-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pantomath~substack-scraper/runs": { "post": { "operationId": "runs-sync-pantomath-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pantomath~substack-scraper/run-sync": { "post": { "operationId": "run-sync-pantomath-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 (posts & full text)", "type": "array", "description": "Newsletters to scrape posts from. Any format: lennysnewsletter.com, https://example.substack.com, https://substack.com/@handle or just a handle.", "items": { "type": "string" } }, "searchQueries": { "title": "Search Substack by keyword", "type": "array", "description": "Search all of Substack: returns matching posts and authors (with subscriber & follower counts).", "items": { "type": "string" } }, "categories": { "title": "Leaderboard categories (newsletter leads)", "type": "array", "description": "Top newsletters in a category, e.g. technology, business, finance, health, culture, science, crypto, sports, food. Returns author, social links, paid plan prices, bestseller tier and current sponsors.", "items": { "type": "string" } }, "leaderboard": { "title": "Leaderboard", "enum": [ "paid", "trending", "all" ], "type": "string", "description": "Which Substack leaderboard to read for categories.", "default": "paid" }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Newest posts first.", "default": 50 }, "maxResultsPerQuery": { "title": "Max posts per search query", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of posts returned for each search query.", "default": 50 }, "maxNewslettersPerCategory": { "title": "Max newsletters per category", "minimum": 1, "maximum": 500, "type": "integer", "description": "Leaderboards are paginated by 25.", "default": 25 }, "includeContent": { "title": "Include full post text", "type": "boolean", "description": "Adds the full article text (free posts) or the public preview (paywalled posts).", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Adds every comment and reply (with author, date, likes, thread depth) for scraped publication posts.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of comments saved for each post.", "default": 100 }, "postedAfter": { "title": "Only posts published after (YYYY-MM-DD)", "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$", "type": "string", "description": "Skip older posts from publications." }, "onlyNewPosts": { "title": "Monitoring: only new posts since last run", "type": "boolean", "description": "Remembers the newest post of every publication and returns only posts published after it. Schedule the Actor to get alerts for new posts.", "default": false }, "includeAuthorsInSearch": { "title": "Include authors in search results", "type": "boolean", "description": "Search also returns matching author profiles with subscriber and follower counts.", "default": true }, "enrichAuthors": { "title": "Enrich leaderboard authors", "type": "boolean", "description": "Adds follower count, subscriber count (when public) and all social links (X, YouTube, LinkedIn, website...) of each leaderboard author. One extra request per newsletter.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Usually not needed.", "default": { "useApifyProxy": 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 } } } } } } } } } }