{ "openapi": "3.0.1", "info": { "title": "Substack Publication and Post Scraper", "description": "Extract public Substack posts, authors, publication details, dates, URLs, excerpts, images, tags, visible engagement counts, and public article text for research, competitor tracking, market analysis, and AI workflows. No login and no paywall bypass.", "version": "1.0", "x-build-id": "AyzC2luw4TuTivKi1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/esrok~substack-publication-and-post-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-esrok-substack-publication-and-post-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/esrok~substack-publication-and-post-scraper/runs": { "post": { "operationId": "runs-sync-esrok-substack-publication-and-post-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/esrok~substack-publication-and-post-scraper/run-sync": { "post": { "operationId": "run-sync-esrok-substack-publication-and-post-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "maxPostsPerPublication" ], "properties": { "publicationUrls": { "title": "Publication URLs", "uniqueItems": true, "type": "array", "description": "One or more public Substack publication URLs. The Actor reads the public publication page and public RSS feed, then opens public post pages for metadata and optional article text.", "items": { "type": "string", "minLength": 1 } }, "postUrls": { "title": "Direct post URLs", "uniqueItems": true, "type": "array", "description": "Optional direct public Substack post URLs. Use this when you already know the exact posts to extract.", "items": { "type": "string", "minLength": 1 } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of public posts to collect from each publication feed.", "default": 25 }, "includePostText": { "title": "Include public post text", "type": "boolean", "description": "When enabled, include the publicly visible article body or public preview text. Paid subscriber-only content is not accessed.", "default": true }, "includeExcerpt": { "title": "Include excerpts", "type": "boolean", "description": "Include public excerpts from RSS feeds or page metadata when available.", "default": true }, "includeAuthorInfo": { "title": "Include author info", "type": "boolean", "description": "Include publicly visible author names and author profile URLs when available.", "default": true }, "includePublicationInfo": { "title": "Include publication info", "type": "boolean", "description": "Include publication name, URL, description, logo, and visible topic/category fields when available.", "default": true }, "dateFrom": { "title": "Date from", "type": "string", "description": "Optional start date filter. Posts published before this date are skipped." }, "dateTo": { "title": "Date to", "type": "string", "description": "Optional end date filter. Posts published after this date are skipped." }, "deduplicateResults": { "title": "Deduplicate results", "type": "boolean", "description": "Remove duplicate posts across publication feeds and direct post URLs using normalized post URLs.", "default": true }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of public post pages fetched at the same time. Lower this if a publication responds slowly.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 10, "maximum": 120, "type": "integer", "description": "Maximum seconds to wait for each public Substack page or feed request.", "default": 30 }, "maxRetries": { "title": "Request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of retries for temporary network or HTTP failures.", "default": 2 } } }, "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 } } } } } } } } } }