{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Likes, Comments, Full Text", "description": "Scrape any Substack newsletter, custom domains included: title, date, authors, likes, comments, restacks, tags and subscriber count. Optional full text as plain text and Markdown, comment threads, and keyword search across Substack. No login.", "version": "1.0", "x-build-id": "YSLAjKSzRheSkBAzL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fernandosord~substack-scraper-posts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fernandosord-substack-scraper-posts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fernandosord~substack-scraper-posts/runs": { "post": { "operationId": "runs-sync-fernandosord-substack-scraper-posts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fernandosord~substack-scraper-posts/run-sync": { "post": { "operationId": "run-sync-fernandosord-substack-scraper-posts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or post URLs", "type": "array", "description": "Any mix of: a subdomain (noahpinion), a publication URL (https://noahpinion.substack.com), a custom domain (www.lennysnewsletter.com), an author profile (@noahpinion or substack.com/@noahpinion) or a single post URL (https://www.noahpinion.blog/p/some-post).", "items": { "type": "string" } }, "searchQueries": { "title": "Search all of Substack", "type": "array", "description": "Optional. Keywords to search across every Substack publication, using Substack's own search. Each query returns posts from many newsletters.", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "type": "integer", "description": "Newest posts first. The Actor stops at this number for each publication. Set it high (for example 5000) to get the whole archive.", "default": 100 }, "maxPostsPerSearch": { "title": "Max posts per search query", "minimum": 1, "type": "integer", "description": "How many posts to keep for each search query, in Substack's relevance order.", "default": 50 }, "onlyPostsNewerThan": { "title": "Only posts newer than", "type": "string", "description": "Optional. A date (2026-01-31) or a relative period (7 days, 3 months). Older posts are skipped." }, "includeAllSections": { "title": "Include hidden sections", "type": "boolean", "description": "Some newsletters keep sections (podcast notes, guest series, link roundups) out of their main archive. On by default, so you get every post the publication has. Turn off for the main newsletter only.", "default": true }, "includeFullText": { "title": "Include full text", "type": "boolean", "description": "Adds the article as plain text and as Markdown. Costs one extra request per post, so runs take longer. Paid posts only give the free preview, marked with textIsPreview.", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Adds the comment thread (author, date, text, likes, replies) inside each post item. Comments do not add extra items or extra cost per item. Comments on paid posts are hidden by Substack for non-subscribers.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "type": "integer", "description": "Cap on comments (replies included) saved inside each post when comments are on. Best comments come first.", "default": 200 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Substack's public API works without a proxy. Turn on Apify Proxy if you scrape thousands of posts and start seeing HTTP 429 retries in the log.", "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 }, "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 } } } } } } } } } }