{ "openapi": "3.0.1", "info": { "title": "Substack Newsletter Scraper", "description": "Substack-Newsletter-Scraper\n\nExtract complete newsletter archives from any Substack publication with advanced filtering, multiple export formats, and engagement analytics.\n\n## Features\n- Scrape entire newsletter archives from Substack\n- Extract full metadata: titles, content, author details etc.", "version": "0.0", "x-build-id": "L1kG0cpdO9uNfHYkh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/opalescent_quintet~substack-newsletter-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-opalescent_quintet-substack-newsletter-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/opalescent_quintet~substack-newsletter-scraper/runs": { "post": { "operationId": "runs-sync-opalescent_quintet-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/opalescent_quintet~substack-newsletter-scraper/run-sync": { "post": { "operationId": "run-sync-opalescent_quintet-substack-newsletter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Substack Newsletter URLs", "type": "array", "description": "URLs of the Substack publications to scrape. Add multiple newsletters to batch process. Examples: https://lennysnewsletter.com, https://stratechery.com", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max Posts to Scrape", "minimum": 0, "type": "integer", "description": "Maximum number of posts to scrape per newsletter. Set to 0 for unlimited.", "default": 100 }, "filterKeywords": { "title": "Filter by Keywords (in Title)", "type": "array", "description": "Only scrape posts that contain ANY of these keywords in the title. Leave empty to get all posts. Case-insensitive.", "default": [], "items": { "type": "string" } }, "filterAfterDate": { "title": "Filter: Posts After Date", "type": "string", "description": "Only scrape posts published AFTER this date. Format: YYYY-MM-DD (e.g., 2024-01-01)" }, "filterBeforeDate": { "title": "Filter: Posts Before Date", "type": "string", "description": "Only scrape posts published BEFORE this date. Format: YYYY-MM-DD (e.g., 2025-12-31)" }, "filterAuthors": { "title": "Filter by Author Names", "type": "array", "description": "Only scrape posts by specific authors. Leave empty for all authors. Partial match, case-insensitive.", "default": [], "items": { "type": "string" } }, "filterPaidOnly": { "title": "Paid Posts Only", "type": "boolean", "description": "Only scrape posts marked as paid/premium content.", "default": false }, "filterFreeOnly": { "title": "Free Posts Only", "type": "boolean", "description": "Only scrape posts that are free (not behind paywall).", "default": false }, "includeComments": { "title": "Include Comments", "type": "boolean", "description": "Scrape top comments for each post. Note: This requires additional requests and increases run time.", "default": false }, "maxCommentsPerPost": { "title": "Max Comments per Post", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of comments to scrape per post (when comments are enabled).", "default": 50 }, "outputFormat": { "title": "Content Output Format", "enum": [ "html", "markdown", "text" ], "type": "string", "description": "Format for the content field. Markdown is perfect for Notion/Obsidian import.", "default": "html" }, "includeFullJson": { "title": "Include Full Raw JSON", "type": "boolean", "description": "Include complete raw JSON data from Substack. Useful for developers needing all metadata.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Use Apify Proxy for reliable scraping.", "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 } } }, "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 } } } } } } } } } }