{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Full Text & Newsletter Data", "description": "Scrape any Substack newsletter, custom domains too: every post with full text as clean Markdown, likes, comments, restacks, tags, authors, paid/free flag and subscriber counts. Optional comments and Substack-wide keyword search. Fast JSON, no browser. Built for AI/RAG and research.", "version": "1.0", "x-build-id": "Uh9yd4AdZJCQ4ScvP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/green_trousers~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-green_trousers-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/green_trousers~substack-scraper/runs": { "post": { "operationId": "runs-sync-green_trousers-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/green_trousers~substack-scraper/run-sync": { "post": { "operationId": "run-sync-green_trousers-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "publications": { "title": "Substack newsletters", "type": "array", "description": "Newsletter URLs (https://name.substack.com), custom domains (www.lennysnewsletter.com), bare subdomains (lenny), author handles (@lenny) or single post URLs (…/p/post-slug).", "default": [ "https://www.lennysnewsletter.com", "oneusefulthing" ], "items": { "type": "string" } }, "searchQuery": { "title": "Search all of Substack (optional)", "type": "string", "description": "Keyword search across every Substack newsletter (e.g. \"AI agents\", \"creator economy\"). Matching posts are returned in the same format. Leave empty to only scrape the newsletters above.", "default": "" }, "maxSearchResults": { "title": "Max search results", "minimum": 1, "maximum": 500, "type": "integer", "description": "Upper limit of posts returned from the search query.", "default": 20 }, "maxPostsPerPublication": { "title": "Max posts per newsletter", "minimum": 0, "type": "integer", "description": "Newest posts first. 0 = the entire archive.", "default": 50 }, "since": { "title": "Published since", "type": "string", "description": "Only posts published on or after this date (e.g. 2026-01-01) or within a relative window (e.g. 7 days). Great for daily or weekly scheduled runs. Empty = any date." }, "audience": { "title": "Post access", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Keep all posts, only free (public) posts, or only paid/subscriber posts. Paid posts include the free preview only.", "default": "all" }, "includeContent": { "title": "Include full text", "type": "boolean", "description": "Adds the post body as clean Markdown, plain text and HTML. For paid posts you get the public free preview and paywalled: true. Turn off for metadata-only runs.", "default": true }, "includeHtml": { "title": "Include raw HTML", "type": "boolean", "description": "Also return the original body HTML (content_html). Turn off to keep datasets small when you only need Markdown/text.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Adds public comments and replies to each post (charged per comment).", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "type": "integer", "description": "Upper limit of comments (including replies) per post when comments are on.", "default": 100 }, "includePublicationInfo": { "title": "Include newsletter info", "type": "boolean", "description": "Adds the newsletter's author, description and public subscriber count to each post, and saves a PUBLICATIONS record with full newsletter profiles. Free.", "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 } } } } } } } } } }