{ "openapi": "3.0.1", "info": { "title": "Substack Newsletter Scraper", "description": "Substack newsletters in, clean rows out: posts (title, date, paid/free, reactions, restacks, authors, optional full body), comments (author, reactions, replies), and a per-publication summary with subscriber count, posts/week, paid share and top posts. Custom domains supported. Public API, no login.", "version": "0.0", "x-build-id": "rRwz3cOz2AzCAvsgO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pulselab~substack-newsletter-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pulselab-substack-newsletter-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pulselab~substack-newsletter-scraper/runs": { "post": { "operationId": "runs-sync-pulselab-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pulselab~substack-newsletter-scraper/run-sync": { "post": { "operationId": "run-sync-pulselab-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "array", "description": "Substack newsletters: subdomain (lenny), substack.com URL, custom-domain URL (https://www.lennysnewsletter.com) or a single post URL (…/p/slug).", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit of post rows saved (and charged) per publication.", "default": 50 }, "sortBy": { "title": "Sort", "enum": [ "new", "top" ], "type": "string", "description": "Order of the archive. Use 'new' for monitoring, 'top' for best-of lists.", "default": "new" }, "audience": { "title": "Audience", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter by paywall.", "default": "all" }, "keywords": { "title": "Keywords", "type": "array", "description": "Search terms. Uses Substack's own search (title + body), one query per keyword; results are merged. Leave empty for the full archive.", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "Posted after", "type": "string", "description": "Keep only posts published on/after this date (YYYY-MM-DD). With 'Newest first' the scraper stops early once older posts appear." }, "onlyNewPosts": { "title": "Only new posts (incremental)", "type": "boolean", "description": "Remember the newest post per publication and, on the next run, return only posts published after it. For scheduled monitoring. State is stored in the run's key-value store as SUBSTACK_STATE.", "default": false }, "includeBody": { "title": "Include full post body", "type": "boolean", "description": "Fetch each post's full body (HTML + text). One extra request per post; charged as a separate event. Paywalled posts return only the public preview.", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch comments (with replies) for each saved post that has comments. One extra request per post; each comment is a separate row and event.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit of comment rows per post.", "default": 100 }, "includePublicationInfo": { "title": "Include publication summary", "type": "boolean", "description": "Save one summary row per publication: subscribers (free count + paid-subscriber tier), bestseller tier, author, created date, posts/week, paid share, average reactions, top posts.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Not needed normally." } } }, "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 } } } } } } } } } }