{ "openapi": "3.0.1", "info": { "title": "Substack Post Scraper: Newsletter Articles, Full Text & Likes", "description": "Scrape Substack posts and articles of any newsletter by URL (substack.com or a custom domain), or single post URLs: title, subtitle, date, author, full free text as HTML and text, paywall flag, likes, comments and restacks. Whole archives, several newsletters per run, no login.", "version": "0.1", "x-build-id": "XvdMooKsefwvxgMUD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hyperbach~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hyperbach-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hyperbach~substack-scraper/runs": { "post": { "operationId": "runs-sync-hyperbach-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hyperbach~substack-scraper/run-sync": { "post": { "operationId": "run-sync-hyperbach-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Publications or posts (URLs)", "type": "array", "description": "What to read: a publication's URL (`https://noahpinion.substack.com`, a custom domain such as `https://www.lennysnewsletter.com`, its `/archive` page, or a bare substack.com name such as `noahpinion`) for its newest posts, or a post URL (`https://www.astralcodexten.com/p/`, an `open.substack.com/pub//p/` share link) for one post. Up to 1,000 values a run. A value that is not a publication gets a free `invalid` row, a value given twice (or one publication under two addresses) a free `duplicate` row.", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop each publication after its newest posts up to this count (0 = every post its archive lists, back to its first post). A post URL is one post whatever this says.", "default": 100 }, "includeBody": { "title": "Include each post's body", "type": "boolean", "description": "Read each post's body as HTML and plain text (one more request a post): the whole body of a free post, the free preview of a paid one (`body_status` says which). Off: the archive's fields only (title, subtitle, description, date, paywall flag, the paid post's teaser, word count, reactions, comments, authors), at the cheaper metadata price.", "default": true }, "onlyNew": { "title": "Only new posts (memory between runs)", "type": "boolean", "description": "Remember every post delivered under this memory (stateStoreName, or a name derived from the inputs) and skip it free in the next run: a scheduled task delivers only what is new. The publication row counts the skipped (skipped_seen). A post asked by URL is always delivered.", "default": false }, "stateStoreName": { "title": "Memory name", "pattern": "^([a-zA-Z0-9][a-zA-Z0-9._-]{0,63})?$", "type": "string", "description": "The name of the onlyNew memory, so several tasks can share one or keep theirs apart. Empty: a name derived from the inputs.", "default": "" }, "maxItems": { "title": "Max post rows (the whole run)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop the run after this many post rows across every publication (0 = no limit). Publication rows are free and not counted; a publication left unread at the cap gets a free `not_read` row.", "default": 0 } } }, "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 } } } } } } } } } }