{ "openapi": "3.0.1", "info": { "title": "Substack Scraper (Posts, Publications, Comments)", "description": "Posts from any Substack newsletter, including custom domains: title, authors, date, paywall flag, reactions, comments, restacks and optional full text. Find newsletters by search or category. Bounded retries; failed publications are never charged.", "version": "0.1", "x-build-id": "B3v3bORY0fp1XGawj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/signalclear~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-signalclear-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/signalclear~substack-scraper/runs": { "post": { "operationId": "runs-sync-signalclear-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/signalclear~substack-scraper/run-sync": { "post": { "operationId": "run-sync-signalclear-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One newsletter per line: its Substack name (the part before .substack.com, e.g. example), a name.substack.com address, a custom-domain URL, or any post URL on it.", "items": { "type": "string" } }, "searchQueries": { "title": "Search for publications", "type": "array", "description": "Keywords to find newsletters with Substack's publication search. Each match is scraped like a publication you listed. The number of matches per query is capped by 'Publications per search or category'.", "items": { "type": "string" } }, "categoryIds": { "title": "Category ids", "type": "array", "description": "Substack category ids whose top publications to scrape, e.g. 4 (Technology), 62 (Business), 153 (Finance), 134 (Science), 96 (Culture). Capped by 'Publications per search or category'.", "items": { "type": "string" } }, "maxPublicationsPerQuery": { "title": "Publications per search or category", "minimum": 1, "maximum": 200, "type": "integer", "description": "How many publications each search query or category adds to the run.", "default": 10 }, "maxPostsPerPublication": { "title": "Maximum posts per publication", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Stop after this many posts for each publication. Set 0 with 'Add a publication row' to collect publication info only.", "default": 50 }, "sort": { "title": "Sort posts by", "enum": [ "new", "top" ], "type": "string", "description": "Newest first, or the publication's own 'Top' ranking (most engagement).", "default": "new" }, "publishedSince": { "title": "Published since", "type": "string", "description": "Only posts published on or after this date (YYYY-MM-DD, UTC). With 'Newest' the run stops paging as soon as it passes the date; with 'Top' it scans at most 10x the post cap (at least 500 posts)." }, "includeBody": { "title": "Fetch full post text", "type": "boolean", "description": "One extra request per post. Adds bodyHtml and bodyText. Paid-only posts return just the free preview Substack shows to logged-out readers; those rows have isPreviewOnly set.", "default": false }, "includeComments": { "title": "Fetch comments", "type": "boolean", "description": "One extra request per post that has comments. Adds a row per comment (type: comment), replies included, up to 'Maximum comments per post'.", "default": false }, "maxCommentsPerPost": { "title": "Maximum comments per post", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Cap on comment rows per post, counting replies, in Substack's 'best first' order.", "default": 100 }, "includePublicationInfo": { "title": "Add a publication row", "type": "boolean", "description": "Adds one row per publication (type: publication) with its name, description, author, subscriber tier as Substack displays it, language and dates.", "default": false }, "maxItems": { "title": "Maximum rows in total", "minimum": 1, "type": "integer", "description": "Hard cap on dataset rows (posts, comments and publication rows together) for the whole run. Leave empty for no cap." }, "maxConcurrency": { "title": "Publications in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "Publications fetched at the same time. Higher is faster but more likely to be rate-limited.", "default": 3 }, "maxAttempts": { "title": "Attempts per publication", "minimum": 1, "maximum": 5, "type": "integer", "description": "Each attempt uses a fresh proxy session and resumes where the last one stopped. Publications that still fail are listed in FAILED_PUBLICATIONS and are not charged. Unknown publications fail at once.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for a single HTTP response before the attempt counts as failed and is retried on a fresh session.", "default": 30 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Substack's public JSON endpoints answer datacenter IPs, so the default Apify proxy is usually enough. Switch to residential if you see many retries.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }