{ "openapi": "3.0.1", "info": { "title": "Substack Scraper", "description": "Collect Substack newsletters in three ways. Full post archives, keyword search across all of Substack, and newsletter discovery with subscriber counts. Get title, date, likes, comments, restacks, authors, paywall status and optional full text and reader comments for each post.", "version": "1.0", "x-build-id": "rnBB9WAnTMlJRhhzA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamole~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamole-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamole~substack-scraper/runs": { "post": { "operationId": "runs-sync-datamole-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamole~substack-scraper/run-sync": { "post": { "operationId": "run-sync-datamole-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 newsletter URLs (https://name.substack.com or custom domains) or just the subdomain (name).", "items": { "type": "string" } }, "maxPostsPerSource": { "title": "Max posts per publication or search", "minimum": 1, "type": "integer", "description": "Stop after this many posts for each publication or post search.", "default": 100 }, "maxItems": { "title": "Max results in total", "minimum": 1, "type": "integer", "description": "Hard cap for the whole run. Leave empty for no cap." }, "searchPosts": { "title": "Search posts across Substack", "type": "array", "description": "Keywords to search in posts from every Substack newsletter.", "items": { "type": "string" } }, "searchPublications": { "title": "Search newsletters", "type": "array", "description": "Keywords to find newsletters. Returns one row per newsletter with author, description and subscriber count.", "items": { "type": "string" } }, "maxPublicationsPerSearch": { "title": "Max newsletters per search", "minimum": 1, "type": "integer", "description": "Limit for newsletter search results.", "default": 20 }, "sort": { "title": "Sort publication posts", "enum": [ "new", "top" ], "type": "string", "description": "Order used when reading a publication archive.", "default": "new" }, "audience": { "title": "Post access", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter by free or paywalled posts.", "default": "all" }, "dateFrom": { "title": "Posts from date", "type": "string", "description": "Only posts published on or after this date." }, "dateTo": { "title": "Posts to date", "type": "string", "description": "Only posts published on or before this date." }, "includeContent": { "title": "Include full post content", "type": "boolean", "description": "Adds the full text and HTML of each post. Paid posts only include the free preview.", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Adds reader comments (author, text, likes, replies, date) to each post.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "type": "integer", "description": "Limit for comments added to each post.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Not needed in most cases." } } }, "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 } } } } } } } } } }