{ "openapi": "3.0.1", "info": { "title": "Substack Scraper — Posts, Authors & Newsletter Data", "description": "Substack newsletter scraper for any publication. Extract posts: title, subtitle, author, date, reactions, comments, restacks, word count, cover image — plus full article HTML in detail mode. Search by handle, subdomain or custom domain. Clean JSON/CSV, no-code, no API key needed.", "version": "1.0", "x-build-id": "cM2tVoxneGGSjIndP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sian.agency~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sian.agency-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sian.agency~substack-scraper/runs": { "post": { "operationId": "runs-sync-sian.agency-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sian.agency~substack-scraper/run-sync": { "post": { "operationId": "run-sync-sian.agency-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "scrapeMode": { "title": "🧭 Scrape Mode", "enum": [ "overview", "detail" ], "type": "string", "description": "🧭 **Choose what to extract:**\n\n- **📰 Overview (cheap & fast):** paginate a publication's full archive and collect rich post metadata — titles, authors, dates, engagement, cover images. Best for bulk research.\n- **📄 Detail (full content):** fetch each post's complete article HTML (body) on top of all overview fields. Best when you need the actual article text.\n\n**TIP:** Start with Overview to map a publication, then run Detail on the posts you care about.", "default": "overview" }, "publications": { "title": "📚 Publications", "uniqueItems": true, "type": "array", "description": "📚 **Publications to scrape.** Each entry can be:\n\n- a **handle** — `bigtechnology`\n- a **Substack subdomain** — `bigtechnology.substack.com`\n- a **custom domain** — `www.bigtechnology.com`\n\nIn **Overview** mode this is required. In **Detail** mode, leave it empty if you supply Post URLs below, or fill it to auto-discover and fetch the latest posts.\n\n**BULK EDIT:** Click \"Bulk edit\" to paste many publications (one per line).", "default": [ "bigtechnology" ], "items": { "type": "string" } }, "postUrls": { "title": "🔗 Post URLs (Detail mode)", "uniqueItems": true, "type": "array", "description": "🔗 **DETAIL MODE:** specific post URLs to fetch with full article HTML. Use public canonical links of the form `https:///p/`.\n\nLeave empty to instead auto-discover posts from the Publications above. Ignored in Overview mode.\n\n**BULK EDIT:** Click \"Bulk edit\" to paste many URLs (one per line).", "items": { "type": "string" } }, "maxResults": { "title": "🔢 Max Posts Per Run", "minimum": 1, "type": "integer", "description": "🔢 **Cap the number of posts saved per run.**\n\n**TIER-BASED LIMITS:**\n- **FREE users:** up to 25 posts per run\n- **PAID users:** unlimited\n\nDeduplication and tier limits are applied before any post is fetched, so you are never charged for posts beyond your cap.", "default": 100 }, "endpoint": { "title": "🗂️ Archive Endpoint", "enum": [ "archive", "posts" ], "type": "string", "description": "🗂️ Which list endpoint to page through. `archive` is the default and carries the richest top-level fields; `posts` is an interchangeable alternative.", "default": "archive" }, "sort": { "title": "↕️ Sort Order", "enum": [ "new", "top" ], "type": "string", "description": "↕️ Sort the archive by newest first (`new`) or by all-time most popular (`top`).", "default": "new" }, "maxPagesPerPublication": { "title": "📑 Max Pages Per Publication", "minimum": 1, "type": "integer", "description": "📑 Limit how many archive pages to page through per publication (each page is ~12 posts). Leave empty to crawl to the end of the archive (still capped by Max Posts Per Run)." }, "useProxy": { "title": "🌐 Use Residential Proxy", "type": "boolean", "description": "🌐 Route requests through a residential proxy. **Not required** — Substack's public data is reachable directly. Enable this only as a courtesy at very high volume, where it can reduce edge rate-limiting.", "default": 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 } } }, "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 } } } } } } } } } }