{
"openapi": "3.0.1",
"info": {
"title": "Substack Scraper – Posts, Comments & Subscribers",
"description": "Substack scraper and Substack API alternative, no login. Scrape newsletter posts with full text, likes, comments and restacks, plus publication profiles: subscriber estimates, paid plan prices, bestseller tier and posting cadence. Custom domains, filters and new-post monitoring.",
"version": "1.0",
"x-build-id": "FKjoTVS3z3v1IusqI"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/signalwharf~substack-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-signalwharf-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/signalwharf~substack-scraper/runs": {
"post": {
"operationId": "runs-sync-signalwharf-substack-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/signalwharf~substack-scraper/run-sync": {
"post": {
"operationId": "run-sync-signalwharf-substack-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"required": [
"publications"
],
"properties": {
"publications": {
"title": "Substack publications",
"type": "array",
"description": "Publication subdomains, Substack URLs, custom domains or profile links, e.g. noahpinion, https://www.astralcodexten.com, lenny.substack.com, https://substack.com/@platformer.",
"items": {
"type": "string"
}
},
"maxPostsPerPublication": {
"title": "Max posts per publication",
"minimum": 1,
"maximum": 100000,
"type": "integer",
"description": "Maximum number of posts to save per publication (after filters). Newest first.",
"default": 50
},
"dateFrom": {
"title": "Posts from date",
"type": "string",
"description": "Only posts published on/after this date (YYYY-MM-DD or ISO, UTC). Scraping stops once older posts are reached."
},
"dateTo": {
"title": "Posts until date",
"type": "string",
"description": "Only posts published on/before this date (whole day included, UTC)."
},
"keywords": {
"title": "Keywords",
"type": "array",
"description": "Keep only posts whose title, subtitle, tags or text contain at least one keyword (case-insensitive).",
"items": {
"type": "string"
}
},
"includeFullText": {
"title": "Include full text",
"type": "boolean",
"description": "Fetch each post's full text (plain text plus outbound links). For paid posts only the free preview is available. No extra charge.",
"default": true
},
"includeHtml": {
"title": "Include HTML",
"type": "boolean",
"description": "Also include the raw post HTML (bigger items).",
"default": false
},
"includePaidPosts": {
"title": "Include paid posts",
"type": "boolean",
"description": "Include subscriber-only posts (metadata plus the public preview). Turn off to save only free posts.",
"default": true
},
"includePublicationProfile": {
"title": "Include publication profile",
"type": "boolean",
"description": "Add one profile item per publication: subscriber estimate, paid plan prices, bestseller tier, posting cadence and engagement averages.",
"default": true
},
"includeComments": {
"title": "Include comments",
"type": "boolean",
"description": "Also save public comments (with replies) for each post.",
"default": false
},
"maxCommentsPerPost": {
"title": "Max comments per post",
"minimum": 1,
"maximum": 5000,
"type": "integer",
"description": "Maximum comments (including replies) saved per post.",
"default": 50
},
"onlyNewPosts": {
"title": "Only new posts (monitoring mode)",
"type": "boolean",
"description": "Return only posts published since the previous run for each publication. Ideal for scheduled runs. Runs with nothing new charge nothing.",
"default": false
},
"stateStoreName": {
"title": "Monitoring state store name",
"type": "string",
"description": "Named key-value store that remembers the last post per publication. Use a different name for each separate monitor.",
"default": "substack-scraper-state"
},
"resetMonitoringState": {
"title": "Reset monitoring state",
"type": "boolean",
"description": "Forget the remembered last post for the given publications before scraping.",
"default": false
},
"maxPagesPerPublication": {
"title": "Max archive pages per publication",
"minimum": 1,
"type": "integer",
"description": "Safety cap; each archive page holds 25 posts.",
"default": 400
},
"requestDelaySecs": {
"title": "Delay between requests (s)",
"minimum": 0.2,
"maximum": 30,
"type": "number",
"description": "Polite delay between HTTP requests.",
"default": 0.8
},
"maxRetries": {
"title": "Max retries",
"minimum": 0,
"maximum": 10,
"type": "integer",
"description": "Retries for 429/5xx responses and network errors.",
"default": 4
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Optional. Usually not needed."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}