{ "openapi": "3.0.1", "info": { "title": "Substack Scraper: Posts, Comments & Newsletter Leaderboards", "description": "Scrape Substack: post archives, full content, comments, author profiles, leaderboards. No login. 6 modes. Half the price of competitors.", "version": "0.1", "x-build-id": "LbMlYXxnfDbSyOZVa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ctkrug~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ctkrug-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ctkrug~substack-scraper/runs": { "post": { "operationId": "runs-sync-ctkrug-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ctkrug~substack-scraper/run-sync": { "post": { "operationId": "run-sync-ctkrug-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "publication", "post", "comments", "author", "category", "search" ], "type": "string", "description": "publication = full post archive; post = single post content; comments = all comments for a post; author = author/publication profile; category = ranked publications; search = keyword search.", "default": "publication" }, "publication": { "title": "Publication", "type": "string", "description": "Publication subdomain (e.g. 'platformer') or full URL (e.g. https://platformer.substack.com). Used by publication, post, comments, and author modes." }, "slug": { "title": "Post slug", "type": "string", "description": "Post slug (the last segment of the post URL, e.g. 'why-platformer-is-leaving-substack') or a full post URL. Required for post and comments modes." }, "handle": { "title": "Author handle", "type": "string", "description": "Substack author handle or publication subdomain (author mode). You can also use the 'publication' field instead." }, "category": { "title": "Category", "type": "string", "description": "Category slug or id (category mode). Valid slugs: technology, business, finance, health, science, culture, sports, news, music, crypto, education, literature, fiction, philosophy, climate, travel, parenting, design, art, humor, comics, history, faith, food, film-and-tv, home-garden, international, podcast." }, "query": { "title": "Search query", "type": "string", "description": "Keywords to search posts/publications (search mode). Note: search results may be sparse without a browser session." }, "limit": { "title": "Max records", "maximum": 1000, "type": "integer", "description": "Maximum number of records to return. For archive/category modes this controls pagination. For comments mode, this is the max number of comments (including replies).", "default": 50 }, "audienceFilter": { "title": "Audience filter", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Filter archive posts by audience type. 'free' returns only posts open to everyone; 'paid' returns only subscriber-exclusive posts.", "default": "all" }, "postType": { "title": "Post type filter", "enum": [ "", "newsletter", "podcast", "thread" ], "type": "string", "description": "Filter archive by content type. Leave blank for all types. Use 'podcast' for audio episodes, 'thread' for Substack Notes.", "default": "" }, "dateFrom": { "title": "Date from", "type": "string", "description": "Only return archive posts published on or after this date (YYYY-MM-DD). Publication mode only." }, "dateTo": { "title": "Date to", "type": "string", "description": "Only return archive posts published on or before this date (YYYY-MM-DD). Publication mode only." }, "includeBody": { "title": "Include full body (bodyHtml + bodyText)", "type": "boolean", "description": "Fetch each post's full public content and clean text (one extra request per post). Paywalled posts return only the public preview. Free posts return the full HTML + extracted plain text.", "default": 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 } } } } } } } } } }