{ "openapi": "3.0.1", "info": { "title": "Substack Scraper – Posts, Comments & Notes", "description": "Scrape every Substack surface in one actor — full posts (50+ fields, complete article HTML), nested comment threads, emoji reaction breakdown, Substack Notes, restacker identity, multi-byline authors, custom domains. Direct JSON API + RSS, no browser, no Cloudflare. From $0.30 per 1,000 posts.", "version": "0.4", "x-build-id": "hRh0CvbEXqZpKsCzT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sourabhbgp~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sourabhbgp-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sourabhbgp~substack-scraper/runs": { "post": { "operationId": "runs-sync-sourabhbgp-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/sourabhbgp~substack-scraper/run-sync": { "post": { "operationId": "run-sync-sourabhbgp-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": { "urls": { "title": "Newsletter URLs", "type": "array", "description": "List of Substack newsletter URLs (URL mode). Provide either urls or notesHandles.", "items": { "type": "string" } }, "maxPosts": { "title": "Max Posts per Newsletter", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum number of posts to scrape per newsletter. Set to 0 for all posts.", "default": 50 }, "includeContent": { "title": "Include Full Content", "type": "boolean", "description": "Extract full article HTML and plain text. Disable for faster metadata-only scraping.", "default": true }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Fetch the full nested comment thread for each post. Adds one HTTP call per post and is billed at $0.0003 per comment.", "default": false }, "includeFacepile": { "title": "Include Facepile (Reactor + Restacker Identity)", "type": "boolean", "description": "Fetch the list of users who reacted to and restacked each post. One HTTP call per post; billed at $0.0002 per reactor/restacker.", "default": false }, "contentFormat": { "title": "Content Format", "enum": [ "html", "text", "both" ], "type": "string", "description": "Format for article content output.", "default": "both" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Only include posts published on or after this date (YYYY-MM-DD)." }, "dateTo": { "title": "Date To", "type": "string", "description": "Only include posts published on or before this date (YYYY-MM-DD)." }, "sortBy": { "title": "Sort Order", "enum": [ "newest", "oldest" ], "type": "string", "description": "Sort posts by date.", "default": "newest" }, "searchKeyword": { "title": "Search Keyword (optional)", "pattern": "^.{1,100}$", "type": "string", "description": "If set, scrape only posts whose title or body matches this keyword. Uses Substack's archive search endpoint." }, "audienceFilter": { "title": "Audience Filter", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter posts by audience: all, free (audience=everyone), or paid (audience=only_paid).", "default": "all" }, "typeFilter": { "title": "Post Type Filter", "enum": [ "all", "newsletter", "podcast", "thread", "video" ], "type": "string", "description": "Filter by post type.", "default": "all" }, "notesHandles": { "title": "Notes Handles", "uniqueItems": true, "type": "array", "description": "Substack handles to scrape Notes for (Notes mode). Provide either urls or notesHandles.", "items": { "type": "string", "pattern": "^[a-zA-Z0-9_-]{1,40}$" } }, "maxNotesPerHandle": { "title": "Max Notes per Handle", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Max Notes to return per handle.", "default": 50 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy for outbound requests. Recommended for large runs (>100 posts with includeComments or includeFacepile) to avoid rate-limits. Apify Proxy bandwidth is billed separately by Apify (datacenter ~$0.6/GB, residential ~$8/GB)." } } }, "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 } } }, "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 } } } } } } } } } }