{ "openapi": "3.0.1", "info": { "title": "Substack Scraper – Posts, Comments & Newsletter Stats", "description": "Extract Substack newsletter posts (full text or Markdown), comments, publication profiles with subscriber counts and prices, authors, Substack-wide search and category leaderboards. No login. Pay per result: posts from $0.70 per 1,000, no start fee.", "version": "0.1", "x-build-id": "rQkxXEk7zJYENHZJX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phantom-x64~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phantom-x64-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/phantom-x64~substack-scraper/runs": { "post": { "operationId": "runs-sync-phantom-x64-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/phantom-x64~substack-scraper/run-sync": { "post": { "operationId": "run-sync-phantom-x64-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 (newsletters)", "type": "array", "description": "Substack newsletters to scrape: subdomain (astralcodexten), Substack URL (https://lenny.substack.com) or custom domain (https://www.lennysnewsletter.com). You can also paste post URLs (…/p/slug) or profile URLs (substack.com/@handle) here; they are detected automatically.", "default": [ "https://www.astralcodexten.com" ], "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Individual posts: https:///p/, https://open.substack.com/pub//p/ or https://substack.com/home/post/p-.", "items": { "type": "string" } }, "authors": { "title": "Author profiles", "type": "array", "description": "Substack profiles to read: handle (lenny, @lenny) or URL (https://substack.com/@lenny). Returns subscriber and follower counts, bio, links (X/Twitter, LinkedIn, website...), publications and leaderboard rank.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Search all of Substack, like the search box on substack.com. Returns matching posts (semantic search) and/or people & newsletters, depending on \"Search for\".", "items": { "type": "string" } }, "searchType": { "title": "Search for", "enum": [ "posts", "people", "both" ], "type": "string", "description": "\"Posts\" returns matching articles from every publication. \"People & newsletters\" returns writer profiles with their newsletter and subscriber count (great for creator discovery and lead lists). \"Both\" returns both.", "default": "posts" }, "maxSearchResults": { "title": "Max results per search query", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum posts (and, separately, people) saved per search query.", "default": 20 }, "leaderboardCategories": { "title": "Leaderboard categories", "type": "array", "description": "Substack leaderboard categories to export, by name, slug or URL: technology, business, finance, culture, us-politics, news, science, health, crypto, sports, food, music, history, fiction... (https://substack.com/leaderboard/technology/paid also works).", "items": { "type": "string" } }, "leaderboardRanking": { "title": "Leaderboard ranking", "enum": [ "paid", "trending", "both", "all" ], "type": "string", "description": "\"Bestsellers\" = top paid newsletters, \"Rising\" = fastest-growing (trending) newsletters, \"Top\" = the category directory listing.", "default": "paid" }, "maxLeaderboardEntries": { "title": "Max entries per leaderboard", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many ranked publications to save per category and ranking (Substack pages them 25 at a time).", "default": 25 }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Newest (or top) posts to save per publication after filters. Set 0 to get only the publication profile.", "default": 10 }, "postSort": { "title": "Post order", "enum": [ "new", "top" ], "type": "string", "description": "\"Newest first\" walks the archive by date. \"Top (most popular) first\" uses Substack's own popularity ranking of the archive.", "default": "new" }, "archiveSearch": { "title": "Search inside publications", "type": "string", "description": "Optional keyword: only posts of the given publications that match it (Substack's archive search)." }, "dateFrom": { "title": "Oldest post date", "type": "string", "description": "Only posts published on or after this date. YYYY-MM-DD, an ISO date-time, or relative: \"7 days\", \"2 weeks\", \"6 months\", \"1 year\". Leave empty for no limit." }, "dateTo": { "title": "Newest post date", "type": "string", "description": "Only posts published on or before this date (a plain YYYY-MM-DD includes the whole day). Same formats as the oldest date." }, "audience": { "title": "Post audience", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Keep all posts, only free (public) posts, or only paywalled posts. For paywalled posts only the free preview that Substack shows to everyone is returned.", "default": "all" }, "includeContent": { "title": "Include full post content", "type": "boolean", "description": "Fetch the post body (one extra request per post). Off = metadata only (title, date, likes, comments count, authors...), which is cheaper.", "default": true }, "contentFormats": { "title": "Content formats", "type": "array", "description": "Formats of the post body: clean plain text, Markdown (best for AI / RAG / LLM pipelines) and/or the original HTML.", "items": { "type": "string", "enum": [ "text", "markdown", "html" ], "enumTitles": [ "Plain text", "Markdown", "HTML" ] }, "default": [ "text", "markdown" ] }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Also save the public comments (with replies) of every post. Comments on paid-only posts are not public and are skipped.", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum comments (including replies) saved per post.", "default": 100 }, "commentSort": { "title": "Comment order", "enum": [ "best_first", "most_recent_first", "oldest_first" ], "type": "string", "description": "Order in which comments are read (matters when the max comments limit cuts the list).", "default": "best_first" }, "includePublicationInfo": { "title": "Include publication profile", "type": "boolean", "description": "Add one row per publication with name, author, subscriber count, paid plans and prices, bestseller tier, podcast, sections and contributors.", "default": true }, "onlyNewPosts": { "title": "Only new posts since the last run (monitor mode)", "type": "boolean", "description": "Remembers the newest post date of every publication and, on the next run, returns only newer posts. Ideal for scheduled runs: you never pay twice for the same post.", "default": false }, "monitorStateKey": { "title": "Monitor name", "type": "string", "description": "Name of the saved monitor state. Use a different name for each independent monitor or schedule. Only used in monitor mode.", "default": "default" }, "maxConcurrency": { "title": "Inputs in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many publications / searches / categories are processed at the same time.", "default": 3 }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Minimum pause between two requests of the same input, in milliseconds (a small random jitter is added). Raise it if you see HTTP 429 warnings.", "default": 300 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times a failed request (network error, HTTP 429/5xx or anti-bot page) is retried with a new proxy session and exponential backoff.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy spreads requests over many IPs and avoids rate limits on big runs. Datacenter proxies are usually enough for Substack.", "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 } } } } } } } } } }