{ "openapi": "3.0.1", "info": { "title": "Substack Archive Scraper | Public Posts & Clean Text", "description": "Export public Substack newsletter archives and post URLs with dates, authors, engagement and optional public text. Custom domains, filters, deduplication and continuation. Paid posts return metadata and short preview only.", "version": "0.1", "x-build-id": "zu6kAO9G6xndDeZcm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apivault_labs~substack-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apivault_labs-substack-archive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/apivault_labs~substack-archive-scraper/runs": { "post": { "operationId": "runs-sync-apivault_labs-substack-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/apivault_labs~substack-archive-scraper/run-sync": { "post": { "operationId": "run-sync-apivault_labs-substack-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Publication or post URLs", "minItems": 1, "maxItems": 20, "type": "array", "description": "Public HTTPS newsletter homepage, /archive or /p/post-slug. Custom Substack domains are supported; not arbitrary websites.", "items": { "type": "string", "minLength": 8, "maxLength": 1000 }, "default": [ "https://www.experimental-history.com" ] }, "maxItems": { "title": "Maximum delivered posts", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Global output limit across all inputs. Budget, source pages and matching data can stop earlier.", "default": 5 }, "includeContent": { "title": "Include public article text", "type": "boolean", "description": "Public/free body HTML and clean text when source returns it. Paid posts always metadata and short preview only.", "default": false }, "onlyFree": { "title": "Free posts only", "type": "boolean", "description": "Skip posts whose audience is restricted or unlock is required.", "default": false }, "startDate": { "title": "Published on or after", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Inclusive YYYY-MM-DD based on source post_date." }, "endDate": { "title": "Published on or before", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Inclusive YYYY-MM-DD. Filters scan pages; no server-side date index guarantee." }, "maxPages": { "title": "Maximum source pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Global archive/input page cap,20posts per archive page. Requested public content can add one detail request per accepted free post. Filtered and duplicate rows consume archive pages.", "default": 20 }, "cursor": { "title": "Continuation cursor", "required": [ "signature", "offsets", "done", "seenPostIds" ], "type": "object", "description": "Copy only from CONTINUATION.resumeInput, keeping URLs/filters unchanged. Not an immutable snapshot.", "properties": { "signature": { "type": "string", "pattern": "^[a-f0-9]{64}$", "title": "Input signature", "description": "Internal continuation value. Copy from CONTINUATION.resumeInput without editing." }, "offsets": { "type": "array", "maxItems": 20, "items": { "type": "integer", "minimum": 0, "maximum": 10000000 }, "title": "Source offsets", "description": "Internal continuation value. Copy from CONTINUATION.resumeInput without editing." }, "done": { "type": "array", "maxItems": 20, "items": { "type": "boolean" }, "title": "Completed inputs", "description": "Internal continuation value. Copy from CONTINUATION.resumeInput without editing." }, "seenPostIds": { "type": "array", "maxItems": 100000, "items": { "type": "string", "pattern": "^[0-9]+:[0-9]+$" }, "title": "Previously delivered post IDs", "description": "Internal continuation value. Copy from CONTINUATION.resumeInput without editing." } }, "additionalProperties": false } } }, "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 } } } } } } } } } }