{ "openapi": "3.0.1", "info": { "title": "Substack Scraper – Newsletters, Creators, Posts & Leads", "description": "Scrape Substack: discover top newsletters by category with author, subscriber count and contact, or pull any publication's posts with full content, reactions, comments and podcast data. Search by category or publication URL. Export to JSON, CSV or Excel.", "version": "1.0", "x-build-id": "B0AZkyKWUYfnWml0A" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/haketa~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-haketa-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/haketa~substack-scraper/runs": { "post": { "operationId": "runs-sync-haketa-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/haketa~substack-scraper/run-sync": { "post": { "operationId": "run-sync-haketa-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "discoverCategories": { "title": "Discover newsletters by category", "type": "array", "description": "Pick one or more categories to find the top newsletters in them — each result includes the author, subscriber count and contact. Great for creator lead generation and research.", "items": { "type": "string", "enum": [ "4", "62", "153", "118", "134", "103", "96", "76739", "355", "34", "11", "109", "18", "114", "223", "339", "94", "13645", "15414", "49692" ], "enumTitles": [ "Technology", "Business", "Finance", "Crypto", "Science", "News", "Culture", "U.S. Politics", "Health & Wellness", "Education", "Music", "Travel", "History", "Philosophy", "Faith & Spirituality", "Literature", "Sports", "Food & Drink", "Climate & Environment", "Humor" ] } }, "publications": { "title": "Publication URLs", "type": "array", "description": "Substack publications to scrape — a subdomain (e.g. 'astralcodexten'), a full URL (e.g. 'https://newsletter.pragmaticengineer.com'), or a custom domain. Their posts are collected.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Optional. Individual Substack post URLs (…/p/…) to fetch directly.", "items": { "type": "string" } }, "scrapePosts": { "title": "Scrape posts from publications", "type": "boolean", "description": "When on, each publication's posts are collected. Turn off to get only the publication's profile (name, author, subscriber count, contact) as a lead.", "default": true }, "includePostContent": { "title": "Include full post content", "type": "boolean", "description": "When on, each post's full text is fetched. Turn off for a faster, lighter list of post metadata only.", "default": true }, "includeHtml": { "title": "Include raw HTML content", "type": "boolean", "description": "Also include the original HTML of each post's content.", "default": false }, "audience": { "title": "Post audience", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter posts by audience.", "default": "all" }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "type": "integer", "description": "Maximum number of posts to collect from each publication. Set 0 for all.", "default": 20 }, "maxPublications": { "title": "Max publications (discovery)", "minimum": 0, "type": "integer", "description": "When discovering by category, the maximum number of publications to return in total.", "default": 50 }, "sinceDate": { "title": "Only posts since (date)", "type": "string", "description": "Optional. Only collect posts published on or after this date, e.g. 2026-01-01." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Datacenter proxies (the default) are more than enough.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 12, "type": "integer", "description": "How many publications/posts to process in parallel. Recommended: 3–8.", "default": 5 } } }, "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 } } } } } } } } } }