{ "openapi": "3.0.1", "info": { "title": "Substack Scraper - Posts, Full Text, Comments & Likes", "description": "Scrape any Substack newsletter (custom domains too): full archive, post text, likes, comments, restacks, word count, authors, plus post and publication search and category leaderboards.", "version": "0.1", "x-build-id": "XR4bHBrh7VbqmNM1S" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/wakachobi~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-wakachobi-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/wakachobi~substack-scraper/runs": { "post": { "operationId": "runs-sync-wakachobi-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/wakachobi~substack-scraper/run-sync": { "post": { "operationId": "run-sync-wakachobi-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 (full archive)", "type": "array", "description": "Newsletters to scrape, as a subdomain ('garymarcus'), a substack.com address ('garymarcus.substack.com') or a custom domain ('https://www.lennysnewsletter.com'). Returns every post in the archive, newest first, up to the limits below.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Direct links to Substack posts, e.g. 'https://www.lennysnewsletter.com/p/some-post' or 'https://substack.com/home/post/p-123456'.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Keywords to search across all of Substack. See 'Search for' to choose posts or publications.", "items": { "type": "string" } }, "searchType": { "title": "Search for", "enum": [ "posts", "publications" ], "type": "string", "description": "What the search queries return.", "default": "posts" }, "categories": { "title": "Category leaderboards", "type": "array", "description": "Substack categories, e.g. 'technology', 'business', 'culture', 'politics', 'finance'. Returns the top newsletters in each category as publication items.", "items": { "type": "string" } }, "categoryRanking": { "title": "Leaderboard", "enum": [ "all", "paid" ], "type": "string", "description": "Which category leaderboard to read.", "default": "all" }, "sort": { "title": "Archive order", "enum": [ "new", "top" ], "type": "string", "description": "Order in which a publication's archive is read.", "default": "new" }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after this many results in total (posts, comments and publications all count).", "default": 50 }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "type": "integer", "description": "Cap per publication so one big archive does not use the whole budget. 0 = no cap.", "default": 0 }, "includeFullText": { "title": "Include post text", "type": "boolean", "description": "Fetch each post and include its body as plain text. Paid posts return only the free public preview.", "default": true }, "includeHtml": { "title": "Include post HTML", "type": "boolean", "description": "Also include the body as HTML (needs 'Include post text').", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Also save the public comments of each post (with replies) as separate 'comment' results.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "type": "integer", "description": "Most-liked comments first. 0 = all.", "default": 50 }, "onlyFree": { "title": "Free posts only", "type": "boolean", "description": "Skip posts for paid subscribers.", "default": false }, "postType": { "title": "Post type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Only keep posts of this type.", "default": "all" }, "startDate": { "title": "Published after", "type": "string", "description": "Only posts published on or after this date (YYYY-MM-DD)." }, "endDate": { "title": "Published before", "type": "string", "description": "Only posts published on or before this date (YYYY-MM-DD)." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Datacenter proxy works for most runs.", "default": { "useApifyProxy": 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 } } } } } } } } } }