{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Comments, Reactions + Sentiment", "description": "Scrape any Substack publication: full post text, comments, replies, reactions, restacks. Built-in sentiment scoring on every item. Multi-publication batch, date filter, audience filter (free/paid/founding). For creator economy research, brand monitoring, PR. $3/1K posts + $5/1K comments.", "version": "1.0", "x-build-id": "H2l6dC0q0mBlNsgFk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dltik~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dltik-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dltik~substack-scraper/runs": { "post": { "operationId": "runs-sync-dltik-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/dltik~substack-scraper/run-sync": { "post": { "operationId": "run-sync-dltik-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", "required": [ "publications" ], "properties": { "publications": { "title": "Publications", "type": "array", "description": "Substack publications to scrape. Subdomain ('lennysnewsletter') or custom domain ('www.astralcodexten.com') or full URL.", "items": { "type": "string" }, "default": [] }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of posts to scrape per publication.", "default": 30 }, "fetchFullBodies": { "title": "Fetch full post bodies", "type": "boolean", "description": "Fetch the full body_html for each post. Costs +1 request per post but unlocks full text + sentiment analysis.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch comments for each post. Free posts only — paid posts return no comments. Costs +1 request per post.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Cap comments returned per post (incl. nested replies).", "default": 100 }, "sortBy": { "title": "Sort posts by", "enum": [ "new", "top" ], "type": "string", "description": "new = chronological (newest first), top = most popular.", "default": "new" }, "searchKeyword": { "title": "Search keyword", "type": "string", "description": "Filter posts by keyword (Substack-side search)." }, "sinceDate": { "title": "Since date", "type": "string", "description": "Only posts published after this ISO date (e.g. '2026-01-01'). Skipped posts stop the scrape." }, "audienceFilter": { "title": "Audience filter", "enum": [ "everyone", "only_paid", "founding" ], "type": "string", "description": "Restrict to free / paid / founding posts." }, "computeSentiment": { "title": "Compute sentiment", "type": "boolean", "description": "Run AFINN-165 sentiment analysis on each post and comment. No external API.", "default": true }, "proxyConfig": { "title": "Proxy (rarely needed)", "type": "object", "description": "Optional Apify proxy. Substack rarely blocks — only useful if you hit rate limits on heavy runs.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }