{ "openapi": "3.0.1", "info": { "title": "Substack Scraper – Export Posts, Newsletter Archives & Search", "description": "Substack scraper & unofficial Substack API: export all posts from any newsletter archive, single posts or keyword search. Full text (HTML/Markdown), likes, comments, restacks, author & publication data. Export to JSON, CSV, Excel. No login.", "version": "1.0", "x-build-id": "bZ6naiU3arWB1dTRA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeworkshq~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeworkshq-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapeworkshq~substack-scraper/runs": { "post": { "operationId": "runs-sync-scrapeworkshq-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapeworkshq~substack-scraper/run-sync": { "post": { "operationId": "run-sync-scrapeworkshq-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "publications": { "title": "Publications", "type": "array", "description": "Newsletter URLs, custom domains or bare subdomains, e.g. https://www.lennysnewsletter.com, astralcodexten, platformer.news. Post URLs here also work.", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Individual post URLs (…/p/slug).", "items": { "type": "string" } }, "searchKeywords": { "title": "Search keywords", "type": "array", "description": "Search all public Substack posts by keyword (Substack's own search).", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 0, "type": "integer", "description": "0 = full archive.", "default": 50 }, "maxSearchResultsPerKeyword": { "title": "Max search results per keyword", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Posts per keyword.", "default": 20 }, "maxPostsTotal": { "title": "Max posts total", "minimum": 0, "type": "integer", "description": "Hard cap across the whole run (cost control). 0 = no cap.", "default": 0 }, "dateFrom": { "title": "Published from", "type": "string", "description": "Only posts on/after this date (YYYY-MM-DD)." }, "dateTo": { "title": "Published to", "type": "string", "description": "Only posts on/before this date (YYYY-MM-DD)." }, "postTypes": { "title": "Post types", "type": "array", "description": "Empty = all types.", "items": { "type": "string", "enum": [ "newsletter", "podcast", "thread" ], "enumTitles": [ "Newsletter", "Podcast", "Thread" ] } }, "onlyFree": { "title": "Only free posts", "type": "boolean", "description": "Skip paywalled posts entirely (otherwise they are returned with metadata and isPaywalled=true).", "default": false }, "bodyFormat": { "title": "Post body", "enum": [ "none", "html", "markdown", "text", "all" ], "type": "string", "description": "Full body of free posts. Paywalled bodies are never collected.", "default": "none" }, "includeReactions": { "title": "Include reactions breakdown", "type": "boolean", "description": "Per-emoji reaction counts (reactionCount, commentCount and restacks are always included).", "default": true }, "includePublicationMetadata": { "title": "Include publication metadata", "type": "boolean", "description": "Name, author, description, public subscriber-count text, sections/categories, logo. One extra request per publication.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests. Keep low to be polite.", "default": 4 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 10, "maximum": 600, "type": "integer", "description": "Global rate limit.", "default": 90 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed. Enable if you hit rate limits (HTTP 429).", "default": { "useApifyProxy": false } }, "monitorMode": { "title": "Monitor mode (track changes across runs)", "enum": [ "off", "all", "changes", "onlyNew" ], "type": "string", "description": "Remembers items from previous runs (per Monitor key) and adds changeType = new/changed/unchanged plus a field-level diff. In the two 'only' modes, unchanged/old items are not output and not charged.", "default": "off" }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Name of the memory used by Monitor mode. Use a different key per schedule/task (e.g. 'daily-pokemon'), so separate watchlists don't mix.", "default": "default" }, "outputFormat": { "title": "Output format", "enum": [ "full", "flat" ], "type": "string", "description": "Flat makes CSV/Excel/Google Sheets exports one clean column per field.", "default": "full" }, "summaryWebhookUrl": { "title": "Summary webhook URL (optional)", "type": "string", "description": "At the end of the run, POST a compact JSON summary (counts, new/changed, price drops, dataset ID) to this URL – e.g. Zapier/Make/n8n catch hook or Slack workflow. Free." } } }, "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 } } } } } } } } } }