{ "openapi": "3.0.1", "info": { "title": "Substack Scraper", "description": "Scrape any Substack newsletter — posts with full HTML content, nested comments, and publication metadata including subscriber counts. Unlimited archive depth, custom domains, keyword discovery. Export JSON, CSV, Excel.", "version": "1.0", "x-build-id": "ZHSQHsNuQhFRxfj1W" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parsebird~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parsebird-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parsebird~substack-scraper/runs": { "post": { "operationId": "runs-sync-parsebird-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parsebird~substack-scraper/run-sync": { "post": { "operationId": "run-sync-parsebird-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Substack newsletter URLs. Accepts a homepage (foo.substack.com), a custom domain (www.example.com), an /archive URL, or a single post URL (.../p/slug).", "items": { "type": "string" } }, "keywords": { "title": "Keywords", "type": "array", "description": "Topics to discover across public Substack publications. Each keyword finds matching newsletters and pulls their posts.", "default": [], "items": { "type": "string" } }, "maxSearchResultsPerKeyword": { "title": "Max results per keyword", "minimum": 1, "maximum": 100, "type": "integer", "description": "Matching posts to process per keyword (maximum 100).", "default": 20 }, "maxPostsPerNewsletter": { "title": "Max posts per newsletter", "minimum": 0, "type": "integer", "description": "Max posts per newsletter, newest first. 0 = unlimited (full archive).", "default": 100 }, "includeContent": { "title": "Include full HTML content", "type": "boolean", "description": "Include the full HTML body of each post. Disable for metadata-only (faster, cheaper).", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch comments (with nested replies) for each post. Adds one API call per post and is charged separately per comment.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "type": "integer", "description": "Cap on top-level comment threads kept per post (their replies are always included). 0 = all.", "default": 0 }, "includePublicationInfo": { "title": "Include publication info", "type": "boolean", "description": "Emit newsletter metadata (subscriber count, pricing, author) to a separate `publications` dataset, and merge the key fields into each post.", "default": true }, "contentType": { "title": "Content type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Filter posts by type.", "default": "all" }, "onlyFree": { "title": "Only free posts", "type": "boolean", "description": "Only include free posts. Skip paywalled content.", "default": false }, "proxyConfiguration": { "title": "Proxy for keyword discovery", "type": "object", "description": "Post and comment scraping needs no proxy. Substack's publication SEARCH endpoint, used for keyword discovery, only answers residential IPs — so keywords use this proxy. Ignored when no keywords are given. Default: Apify Proxy, RESIDENTIAL group.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "startDate": { "title": "Start date", "type": "string", "description": "Only posts published on or after this date (YYYY-MM-DD)." }, "endDate": { "title": "End date", "type": "string", "description": "Only posts published on or before this date (YYYY-MM-DD)." } } }, "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 } } } } } } } } } }