{ "openapi": "3.0.1", "info": { "title": "Substack Scraper", "description": "Scrape any Substack newsletter: all posts with likes, comments, authors, paywall status, word count and optional full text as clean Markdown for LLM/RAG. Search posts or newsletters (with subscriber counts) by keyword. No login, fast JSON API.", "version": "0.1", "x-build-id": "yPggMqw1qQOEz9n85" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/exciting_pawpaw~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-exciting_pawpaw-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/exciting_pawpaw~substack-scraper/runs": { "post": { "operationId": "runs-sync-exciting_pawpaw-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/exciting_pawpaw~substack-scraper/run-sync": { "post": { "operationId": "run-sync-exciting_pawpaw-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Newsletter or post URLs", "type": "array", "description": "Substack newsletters to scrape all archive posts from. Accepts newsletter URLs (https://name.substack.com), custom domains (https://www.astralcodexten.com), bare subdomains (name), profile URLs (https://substack.com/@handle) and single post URLs (…/p/post-slug).", "default": [], "items": { "type": "string" } }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "Keywords to search across all of Substack. What is returned depends on 'Search for' below: matching posts, or matching newsletters.", "default": [], "items": { "type": "string" } }, "searchType": { "title": "Search for", "enum": [ "posts", "publications" ], "type": "string", "description": "What a keyword search returns: posts (articles) or publications (newsletters with subscriber counts).", "default": "posts" }, "strictKeywordMatch": { "title": "Strict keyword match (post search)", "type": "boolean", "description": "Substack's post search is semantic and also returns loosely related posts. Enable to keep only posts whose title, subtitle, description, preview text or tags contain every word of your keyword.", "default": false }, "maxItems": { "title": "Max results (total)", "minimum": 1, "type": "integer", "description": "Maximum number of results for the whole run. You pay only for results delivered.", "default": 100 }, "maxItemsPerInput": { "title": "Max results per newsletter / keyword", "minimum": 0, "type": "integer", "description": "Optional cap per newsletter URL or search keyword. 0 = no per-input cap (only the total limit applies).", "default": 0 }, "includeContent": { "title": "Include full text (Markdown)", "type": "boolean", "description": "Add the full post body as clean Markdown (field contentMarkdown) - great for LLM / RAG pipelines. Available for free posts; paywalled posts return no body. Needs one extra request per post, so runs are a bit slower.", "default": false }, "sort": { "title": "Archive order", "enum": [ "new", "top" ], "type": "string", "description": "Order of newsletter archive posts: newest first, or most popular (top) first.", "default": "new" }, "postedAfter": { "title": "Only posts published after", "type": "string", "description": "Optional. Only return posts published after this date. Absolute (2025-01-31) or relative (e.g. '30 days', '6 months', '1 year').", "default": "" }, "onlyFreePosts": { "title": "Only free posts", "type": "boolean", "description": "Skip paywalled (paid-subscriber-only) posts.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Usually not needed - Substack's public JSON API works without proxies. Enable Apify Proxy if you get rate-limited on very large runs.", "default": { "useApifyProxy": 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 } } } } } } } } } }