{
"openapi": "3.0.1",
"info": {
"title": "Substack Scraper — Posts, Newsletters, Authors & Free Content",
"description": "Scrape any Substack newsletter (incl. custom domains): post titles, subtitles, authors, dates, free/paid audience, word count, likes, comment counts, cover images and full Markdown/HTML of free posts. Date filters, keyword publication search. Fast HTTP-only, $0.002 per post. Never bypasses paywalls.",
"version": "0.1",
"x-build-id": "BOuMlzYMDVrUK27Vc"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/gazidev~substack-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-gazidev-substack-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/gazidev~substack-scraper/runs": {
"post": {
"operationId": "runs-sync-gazidev-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/gazidev~substack-scraper/run-sync": {
"post": {
"operationId": "run-sync-gazidev-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": "Substack publications",
"type": "array",
"description": "Publications to scrape. Accepts a subdomain (lenny), a substack.com URL (https://lenny.substack.com) or a custom domain (https://www.astralcodexten.com).",
"items": {
"type": "string"
}
},
"postUrls": {
"title": "Individual post URLs",
"type": "array",
"description": "Optional list of specific post URLs (https://<publication>/p/<slug>).",
"items": {
"type": "string"
}
},
"searchQueries": {
"title": "Search publications by keyword",
"type": "array",
"description": "Optional. Find publications by keyword using Substack's public web search. Each found publication is returned as a publication record.",
"items": {
"type": "string"
}
},
"maxSearchResults": {
"title": "Max publications per search query",
"minimum": 1,
"maximum": 200,
"type": "integer",
"description": "Maximum publications returned for each search query.",
"default": 20
},
"scrapeSearchResults": {
"title": "Also scrape posts of found publications",
"type": "boolean",
"description": "If enabled, posts of every publication found by search are scraped too (subject to the post limits below).",
"default": false
},
"maxPostsPerPublication": {
"title": "Max posts per publication",
"minimum": 0,
"type": "integer",
"description": "Newest posts first. 0 = no limit (whole archive).",
"default": 20
},
"dateFrom": {
"title": "Published on or after",
"type": "string",
"description": "Only posts published on/after this date. YYYY-MM-DD or relative, e.g. 30 days, 6 months."
},
"dateTo": {
"title": "Published on or before",
"type": "string",
"description": "Only posts published on/before this date (YYYY-MM-DD)."
},
"audience": {
"title": "Audience",
"enum": [
"all",
"free",
"paid"
],
"type": "string",
"description": "Filter by who can read the post.",
"default": "all"
},
"postTypes": {
"title": "Post types",
"type": "array",
"description": "Leave empty for all types.",
"items": {
"type": "string",
"enum": [
"newsletter",
"podcast",
"thread"
],
"enumTitles": [
"Newsletter / article",
"Podcast",
"Thread"
]
}
},
"includeContent": {
"title": "Include full content (free posts only)",
"type": "boolean",
"description": "Adds the full post body for posts whose audience is everyone. Paywalled posts never include the body — only metadata and Substack's public teaser text.",
"default": true
},
"contentFormat": {
"title": "Content format",
"enum": [
"markdown",
"html",
"both",
"text"
],
"type": "string",
"description": "Format of the free-post body.",
"default": "markdown"
},
"includePublicationInfo": {
"title": "Include publication details on every post",
"type": "boolean",
"description": "Adds publication name, description, author, logo, language, custom domain etc. to each post record.",
"default": true
},
"maxConcurrency": {
"title": "Max concurrent requests",
"minimum": 1,
"maximum": 10,
"type": "integer",
"description": "Keep low to stay polite to Substack (it rate-limits aggressive clients).",
"default": 4
},
"proxyConfiguration": {
"title": "Proxy",
"type": "object",
"description": "Usually not needed. Enable Apify datacenter proxy only if you get blocked.",
"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
}
}
}
}
}
}
}
}
}
}