{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Full Text and Comments, No Login", "description": "Substack scraper: posts, full text of free posts, authors, likes, tags and comments from any public newsletter, post URL or search. No login, no API key, no browser. $1.50 per 1,000 posts, $0.30 per 1,000 comments.", "version": "0.1", "x-build-id": "s6UwgWIhmhMQGfGix" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datagleaner~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datagleaner-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/datagleaner~substack-scraper/runs": { "post": { "operationId": "runs-sync-datagleaner-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/datagleaner~substack-scraper/run-sync": { "post": { "operationId": "run-sync-datagleaner-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": "Publications", "type": "array", "description": "Newsletter URLs or subdomains: https://www.lennysnewsletter.com, https://lenny.substack.com or just lenny. Custom domains work. The latest (or top) posts of each are returned.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Single posts, e.g. https://www.lennysnewsletter.com/p/all-of-the-lenny-and-friends-summit.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Search all of Substack by keyword. Returns matching posts, or with Search type = publications, the latest posts of the newsletters that match.", "items": { "type": "string" } }, "searchType": { "title": "Search type", "enum": [ "posts", "publications" ], "type": "string", "description": "posts: return the posts that match the query. publications: find newsletters that match the query and return their latest posts.", "default": "posts" }, "sort": { "title": "Publication sort", "enum": [ "new", "top" ], "type": "string", "description": "Order for publication archives: new (newest first) or top (most popular first).", "default": "new" }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Upper bound on posts returned for each publication. Each returned post is billed, so this is also your cost cap per publication.", "default": 20 }, "maxPostsPerSearch": { "title": "Max posts per search query", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Upper bound on posts returned for each search query (search type = posts).", "default": 20 }, "maxPublicationsPerSearch": { "title": "Max publications per search query", "minimum": 1, "maximum": 200, "type": "integer", "description": "With search type = publications: how many matching newsletters to read for each query (each up to the max posts per publication).", "default": 5 }, "postsSince": { "title": "Only posts newer than", "type": "string", "description": "Optional. A date or datetime such as 2026-10-01 or 2026-10-01T12:00:00Z, or a relative time such as 7 days, 2 weeks, 3 months. Older posts are skipped (and, for newest-first listings, paging stops)." }, "includeBody": { "title": "Include full text", "type": "boolean", "description": "Fetch each post's full text and HTML (one extra request per post, no extra charge). Turn off for a faster metadata-only run; the text is then a short preview. Paywalled posts only ever return their public preview, marked isBodyTruncated.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Also return the comments of each post as separate items (type = comment). Billed per comment. Off by default.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Upper bound on comments returned for each post when comments are on, replies included, best comments first.", "default": 50 }, "requestDelaySeconds": { "title": "Delay between requests (seconds)", "minimum": 0, "maximum": 30, "type": "number", "description": "Base pause between requests to Substack; the actual pause is randomised up to 1.4x. Raise it if Substack answers with rate limits (HTTP 429).", "default": 0.5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The default is no proxy, which works from Apify's servers. Enable Apify Proxy only if Substack rate-limits you." } } }, "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 } } } } } } } } } }