{ "openapi": "3.0.1", "info": { "title": "Substack Scraper - Posts, Newsletters & Comments", "description": "Substack scraper for posts, newsletters, authors, subscriber data, full public content, engagement, and nested comments. Search by keyword or scrape any publication.", "version": "2.0", "x-build-id": "BD7e6hWiiKPXQHIu8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scraper_guru~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scraper_guru-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scraper_guru~substack-scraper/runs": { "post": { "operationId": "runs-sync-scraper_guru-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scraper_guru~substack-scraper/run-sync": { "post": { "operationId": "run-sync-scraper_guru-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "substackUrls": { "title": "Publication or post URLs", "type": "array", "description": "Substack publication URLs, custom domains, or direct /p/ post URLs.", "items": { "type": "string" } }, "searchQueries": { "title": "Newsletter search keywords", "type": "array", "description": "Find relevant Substack publications by topic, author, or niche, then scrape their posts.", "items": { "type": "string" } }, "maxSearchResultsPerQuery": { "title": "Publications per keyword", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum publications discovered for each search keyword.", "default": 10 }, "maxPostsPerSubstack": { "title": "Posts per publication", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum matching posts saved from each publication. Set to 0 for the full archive.", "default": 50 }, "includeContent": { "title": "Extract article content", "type": "boolean", "description": "Return available HTML, Markdown, and plain text. Disable for faster metadata-only runs.", "default": true }, "includeComments": { "title": "Extract comment threads", "type": "boolean", "description": "Return public comments and nested replies for each post.", "default": false }, "maxCommentsPerPost": { "title": "Comments per post", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum comments and replies collected per post when comments are enabled.", "default": 20 }, "includePublicationInfo": { "title": "Include publication details", "type": "boolean", "description": "Add publication name, description, logos, subscriber count, payment status, and author details.", "default": true }, "postType": { "title": "Post type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Limit results to newsletters, podcasts, or threads.", "default": "all" }, "startDate": { "title": "Published after", "type": "string", "description": "Only include posts published on or after this date." }, "endDate": { "title": "Published before", "type": "string", "description": "Only include posts published on or before this date." }, "onlyFree": { "title": "Free posts only", "type": "boolean", "description": "Exclude posts marked for paid subscribers.", "default": false }, "minReactions": { "title": "Minimum reactions", "minimum": 0, "type": "integer", "description": "Only include posts with at least this many reactions.", "default": 0 }, "minComments": { "title": "Minimum comments", "minimum": 0, "type": "integer", "description": "Only include posts with at least this many comments.", "default": 0 }, "minWordCount": { "title": "Minimum word count", "minimum": 0, "type": "integer", "description": "Only include posts with at least this many words.", "default": 0 }, "postConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "Number of post requests processed in parallel.", "default": 10 } } }, "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 } } } } } } } } } }