{ "openapi": "3.0.1", "info": { "title": "Substack Scraper - Find Newsletters, Posts & Comments", "description": "[$2.00 / 1K] Find Substack newsletters by category leaderboard or search, then scrape their posts, comments, authors and clean text. Ranked results, no URL list needed, no start fee.", "version": "0.1", "x-build-id": "bKppr5DcepHzx798l" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webdata_labs~substack-intelligence-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webdata_labs-substack-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/webdata_labs~substack-intelligence-scraper/runs": { "post": { "operationId": "runs-sync-webdata_labs-substack-intelligence-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/webdata_labs~substack-intelligence-scraper/run-sync": { "post": { "operationId": "run-sync-webdata_labs-substack-intelligence-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": { "urls": { "title": "Newsletter or post URLs", "type": "array", "description": "Public Substack URLs to collect. Both *.substack.com and custom publication domains are supported. Optional if you use Discovery below.", "default": [], "items": { "type": "string" } }, "categories": { "title": "Substack categories", "type": "array", "description": "Pull the ranked leaderboard for each selected Substack category. Substack serves at most 525 publications per category and ranking.", "items": { "type": "string", "enum": [ "Culture", "Technology", "Business", "U.S. Politics", "Finance", "Food & Drink", "Podcasts", "Sports", "Art & Illustration", "World Politics", "Health Politics", "News", "Fashion & Beauty", "Music", "Faith & Spirituality", "Climate & Environment", "Science", "Literature", "Fiction", "Health & Wellness", "Design", "Travel", "Parenting", "Philosophy", "Comics", "International", "Crypto", "History", "Humor", "Education", "Film & TV", "Home & Garden", "Games" ] }, "default": [] }, "leaderboardRanking": { "title": "Leaderboard ranking", "enum": [ "all", "paid", "free" ], "type": "string", "description": "Which leaderboard ordering to read. 'Paid' is a genuinely different ranking of the same category, not a filter of 'All'.", "default": "all" }, "searchQueries": { "title": "Search phrases", "type": "array", "description": "Find publications by keyword, for topics that do not map onto one category. Each phrase is searched separately.", "default": [], "items": { "type": "string" } }, "maxPublicationsPerSource": { "title": "Maximum publications per category or phrase", "minimum": 1, "maximum": 525, "type": "integer", "description": "How many publications to take from each category or search phrase. The source ceiling is 525 per category and ranking.", "default": 25 }, "discoveryOnly": { "title": "Only return the publication list", "type": "boolean", "description": "Return the ranked publications and stop, without collecting each newsletter's posts. Much faster and cheaper when you only need the list.", "default": false }, "maxPostsPerNewsletter": { "title": "Maximum posts per newsletter", "minimum": 0, "type": "integer", "description": "Maximum matching posts returned for each publication. Use 0 to collect the complete public archive.", "default": 50 }, "sortOrder": { "title": "Archive order", "enum": [ "new", "top" ], "type": "string", "description": "Collect the newest posts first or the publication's top posts first.", "default": "new" }, "contentType": { "title": "Content type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Return every post type or only newsletters, podcasts, or Substack threads.", "default": "all" }, "startDate": { "title": "Published on or after", "type": "string", "description": "Optional ISO date or timestamp. A YYYY-MM-DD value includes that entire UTC day." }, "endDate": { "title": "Published on or before", "type": "string", "description": "Optional ISO date or timestamp. A YYYY-MM-DD value includes that entire UTC day." }, "onlyFree": { "title": "Only free posts", "type": "boolean", "description": "Exclude subscriber-only and paid posts from the result dataset.", "default": false }, "includeKeywords": { "title": "Include keywords", "type": "array", "description": "Keep posts whose title, subtitle, description, preview, or tags contain at least one phrase. Matching is case-insensitive.", "default": [], "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop posts whose title, subtitle, description, preview, or tags contain any listed phrase.", "default": [], "items": { "type": "string" } }, "includeContent": { "title": "Include public post content", "type": "boolean", "description": "Fetch public post pages to extract the body. Paid post bodies are never returned.", "default": true }, "contentFormat": { "title": "Content formats", "enum": [ "html", "text", "markdown", "html_and_text", "all" ], "type": "string", "description": "Choose HTML, clean text, Markdown, or multiple body representations.", "default": "html_and_text" }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch public comments, nested replies, public author handles, reactions, and pinned status for each selected post.", "default": false }, "commentOutput": { "title": "Comment output", "enum": [ "nested", "separate", "both" ], "type": "string", "description": "Nest comments inside each post, emit analytics-friendly comment rows, or return both formats.", "default": "nested" }, "includePublicationInfo": { "title": "Include publication metadata", "type": "boolean", "description": "Attach public publication identity and audience metadata to results.", "default": true }, "publicationOutput": { "title": "Publication output", "enum": [ "embedded", "separate", "both" ], "type": "string", "description": "Embed publication fields in posts, emit one publication row, or return both representations.", "default": "embedded" }, "onlyNew": { "title": "Only new posts since previous runs", "type": "boolean", "description": "Remember emitted post IDs for this source and filter combination and suppress them in later runs.", "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 }, "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 } } } } } } } } } }