{ "openapi": "3.0.1", "info": { "title": "Substack Scraper – Posts, Comments, Publications & Authors", "description": "Scrape Substack newsletters without logging in: posts with full HTML and plain text, likes and restacks, flattened comment threads, paywall flags, category leaderboards and author profiles as clean typed rows.", "version": "0.1", "x-build-id": "V1EGxxsmAO1sLNs4H" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/teodor_banea~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-teodor_banea-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/teodor_banea~substack-scraper/runs": { "post": { "operationId": "runs-sync-teodor_banea-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/teodor_banea~substack-scraper/run-sync": { "post": { "operationId": "run-sync-teodor_banea-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "What to scrape", "enum": [ "posts", "postUrls", "publications", "authors" ], "type": "string", "description": "Select the kind of data to collect. Each mode reads its own target field below.", "default": "posts" }, "publicationUrls": { "title": "Publications", "type": "array", "description": "Enter one publication per line for the posts mode: a Substack URL (https://lenny.substack.com), a custom domain (https://www.astralcodexten.com), a bare subdomain (lenny) or any post URL (its publication is used). Up to 200.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Enter post links for the postUrls mode: https:///p/ or https:///i/. Up to 1,000.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "categories": { "title": "Categories", "type": "array", "description": "Enter Substack category slugs or names for the publications mode, e.g. technology, culture, business, finance, science, health. Unknown categories are reported with the list of valid slugs.", "items": { "type": "string" } }, "authorHandles": { "title": "Author handles", "type": "array", "description": "Enter Substack user handles for the authors mode: handle, @handle or https://substack.com/@handle. Up to 500.", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Maximum posts per publication", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many posts for each publication.", "default": 50 }, "sort": { "title": "Sort order", "enum": [ "new", "top" ], "type": "string", "description": "Select the archive order: newest first, or top (most liked) first.", "default": "new" }, "searchTerm": { "title": "Search term", "type": "string", "description": "Only posts matching this term in the publication's own archive search (title and body)." }, "postedAfter": { "title": "Posted after", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T.*)?$", "type": "string", "description": "Only include posts on or after this date (YYYY-MM-DD, UTC). With the newest-first sort, pagination stops at this date, which keeps scheduled runs cheap." }, "postedBefore": { "title": "Posted before", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T.*)?$", "type": "string", "description": "Only include posts on or before this date (YYYY-MM-DD, UTC)." }, "audienceFilter": { "title": "Audience", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Select which posts to keep: all, free posts only, or paid (subscriber-only) posts only.", "default": "all" }, "includeContent": { "title": "Include full post content", "type": "boolean", "description": "Fetch each post (one extra request per post) and add bodyHtml and bodyText. Paid posts return the public preview only.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch each post's comment thread (one extra request per post) and add one row per comment, flattened with parentCommentId and depth. Every comment row is a billed result.", "default": false }, "maxCommentsPerPost": { "title": "Maximum comments per post", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Cap the comment rows per post (best-rated first, replies included).", "default": 25 }, "maxPublicationsPerCategory": { "title": "Maximum publications per category", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after this many publications per category leaderboard, best-ranked first.", "default": 50 } } }, "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 } } } } } } } } } }