{
"openapi": "3.0.1",
"info": {
"title": "Substack Scraper (public newsletter posts)",
"description": "Extract posts from public Substack newsletters as clean JSON: title, date, author byline, likes, comments, word count and tags. Keyword search, date window and optional full text of free posts. No login, no API key. Pay per result, built for monitoring and AI pipelines.",
"version": "0.1",
"x-build-id": "jjbuNc6mK9Ob9MsO4"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/lowlanddata~substack-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-lowlanddata-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/lowlanddata~substack-scraper/runs": {
"post": {
"operationId": "runs-sync-lowlanddata-substack-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/lowlanddata~substack-scraper/run-sync": {
"post": {
"operationId": "run-sync-lowlanddata-substack-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": "Publications",
"type": "string",
"description": "One or more Substack publications, separated by commas or spaces. Use the name (\"astralcodexten\"), the address (\"astralcodexten.substack.com\"), a custom domain (\"https://www.lennysnewsletter.com\") or an author link (\"https://substack.com/@lenny\"). A link to a single post works too: the whole publication is read, not only that post."
},
"searchQuery": {
"title": "Search inside the publications",
"type": "string",
"description": "Optional. Only return posts that match this term, using the publication's own archive search. Results come most relevant first, not by date, and the sort option below is ignored while a search is set. Leave empty to read the whole archive."
},
"sort": {
"title": "Order",
"enum": [
"new",
"top"
],
"type": "string",
"description": "new walks the archive newest-first. top lists the most popular posts first, which is a quick way to the best of a publication. A search term always lists by relevance.",
"default": "new"
},
"audience": {
"title": "Free or paid posts",
"enum": [
"all",
"free",
"paid"
],
"type": "string",
"description": "Keep all posts, only the free ones, or only the paid ones. Paid posts always come back as metadata and the public preview; their text is never read.",
"default": "all"
},
"postedAfter": {
"title": "Posted after",
"pattern": "^\\d{4}-\\d{2}-\\d{2}([T ]\\d{2}:\\d{2}(:\\d{2})?(\\.\\d+)?(Z|[+-]\\d{2}:?\\d{2})?)?$",
"type": "string",
"description": "Only include posts published on or after this date. A newest-first walk stops as soon as it reaches older posts. Format: YYYY-MM-DD (for example 2026-09-08) or a full ISO timestamp such as 2026-09-08T14:30:00Z. Slash dates like 08/09/2026 are refused on purpose: they are read as September in Europe and August in the United States, and this actor will not guess which you meant."
},
"postedBefore": {
"title": "Posted before",
"pattern": "^\\d{4}-\\d{2}-\\d{2}([T ]\\d{2}:\\d{2}(:\\d{2})?(\\.\\d+)?(Z|[+-]\\d{2}:?\\d{2})?)?$",
"type": "string",
"description": "Only include posts published on or before this date. Format: YYYY-MM-DD (for example 2026-09-08) or a full ISO timestamp such as 2026-09-08T14:30:00Z. Slash dates like 08/09/2026 are refused on purpose: they are read as September in Europe and August in the United States, and this actor will not guess which you meant."
},
"includeBody": {
"title": "Include the full text of free posts",
"type": "boolean",
"description": "Adds a bodyText field with the full text of each free post. It needs one extra request per post, so a run takes noticeably longer. Paid posts never get a body, whatever this setting says.",
"default": false
},
"maxItems": {
"title": "Max posts",
"minimum": 1,
"type": "integer",
"description": "Stop after this many posts in total. Free-plan runs are capped at 5 items. The form starts at 25 for a cheap first run - that is the form's prefill, not a cap on your plan; clear it to use the default of 500.",
"default": 500
},
"proxyConfiguration": {
"title": "Proxy",
"type": "object",
"description": "Optional. By default the actor reads Substack directly, which is fastest, and switches to the Apify proxy by itself if Substack blocks the request. Turn on Apify Proxy, or list your own proxy URLs, to route every request through a proxy."
},
"reportFailures": {
"title": "Report failures to the developer",
"type": "boolean",
"description": "When a run fails, send the developer the actor name and build, an error category, the error message (truncated) and a one-way hash of your input - so a bug can be fixed without anyone asking you to reproduce it. Your input itself, your results and your identity are never sent, and successful runs send nothing at all. Switch this off and the actor behaves exactly the same.",
"default": true
}
}
},
"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
}
}
}
}
}
}
}
}
}
}