{ "openapi": "3.0.1", "info": { "title": "Substack Scraper — Posts·Comments·Subscribers w/ EMAILS", "description": "Scrape Substack newsletters — full post content, threaded comments, tags, authors, podcast episodes and EXACT subscriber counts. Works with custom domains, date filters, paid-post detection, optional author contact emails. Any publication or post URL. Pure HTTP, JSON/CSV out.", "version": "0.0", "x-build-id": "2IbJV9lMHcRrKlCbb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~substack-scraper/runs": { "post": { "operationId": "runs-sync-memo23-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~substack-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Substack URLs", "type": "array", "description": "Substack URLs to scrape. Newsletter homepages (https://noahpinion.substack.com or custom domains like https://www.noahpinion.blog), /archive or /about pages, and direct post URLs (https://…/p/some-post) are auto-classified.", "items": { "type": "string" } }, "publications": { "title": "Publication shortcuts", "type": "array", "description": "Bare Substack subdomains or domains — each expands to that publication's homepage. E.g. 'noahpinion' expands to https://noahpinion.substack.com. Used in addition to Start URLs.", "items": { "type": "string" } }, "maxPostsPerNewsletter": { "title": "Max posts per newsletter", "minimum": 0, "type": "integer", "description": "Maximum number of posts to scrape per newsletter. Set to 0 for unlimited (full archive).", "default": 50 }, "maxItems": { "title": "Max posts total", "minimum": 1, "type": "integer", "description": "Hard cap on post rows across the whole run (all newsletters combined).", "default": 1000 }, "sortOrder": { "title": "Sort order", "enum": [ "new", "top" ], "type": "string", "description": "Archive ordering. 'new' = newest first (recommended — enables early stop when combined with Start date). 'top' = most popular first.", "default": "new" }, "includeBody": { "title": "Include post content (bodyHtml + bodyText)", "type": "boolean", "description": "Include the full post body as HTML and plain text. Disable for metadata-only scraping — smaller rows, faster runs. Note: paywalled posts return only their free preview portion (flagged via bodyIsPreviewOnly).", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch comments for each post (one extra API call per post that has comments). Emits one rowType:'comment' row per comment with parentCommentId preserved, joinable to posts via postId.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "type": "integer", "description": "Maximum comment rows per post, including nested replies. Set to 0 for unlimited. Only applies when 'Include comments' is on.", "default": 100 }, "includePublicationInfo": { "title": "Include publication info", "type": "boolean", "description": "Emit one rowType:'publication' row per newsletter — name, author (name/handle/bio), description, EXACT free-subscriber count, custom domain, language, created date.", "default": true }, "contentType": { "title": "Content type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Filter by post type.", "default": "all" }, "startDate": { "title": "Start date (YYYY-MM-DD)", "type": "string", "description": "Only posts published on or after this date. With sort order 'Newest first' the scraper stops paginating at the cutoff — fewer API calls, faster and cheaper." }, "endDate": { "title": "End date (YYYY-MM-DD)", "type": "string", "description": "Only posts published on or before this date." }, "onlyFree": { "title": "Free posts only", "type": "boolean", "description": "Skip paywalled posts (audience is 'only_paid' or 'founding'). Paywalled posts otherwise return their free preview portion.", "default": false }, "enrichEmails": { "title": "Enrich with contact emails (experimental, billed per email)", "type": "boolean", "description": "Try to find a contact email for each publication/author by discovering their website and reading its contact/about pages. Adds contactEmail + contactWebsite to the publication row plus a detailed emailEnrichment object. Billed per email found — never charged for misses.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "How many posts to process in parallel. Substack's API tolerates moderate parallelism; raise carefully (429s are auto-retried with back-off).", "default": 5 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Retries for failed API requests.", "default": 5 }, "proxy": { "title": "Proxy configuration (override)", "type": "object", "description": "Explicit proxy override. Leave empty to use the actor's built-in residential routing (recommended)." } } }, "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 } } } } } } } } } }