{ "openapi": "3.0.1", "info": { "title": "Substack Insights Scraper", "description": "Scrape Substack publications, posts (HTML + markdown for AI/RAG), comments, Notes feeds, author profiles and contact info from bios. Input-time filters (paywall, reactions, words, keywords, subscribers). Historical subscriber-growth tracking across scheduled runs.", "version": "1.0", "x-build-id": "gOEvW94Ne9ph6fmYI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~substack-insights-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-substack-insights-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~substack-insights-scraper/runs": { "post": { "operationId": "runs-sync-brilliant_gum-substack-insights-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~substack-insights-scraper/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-substack-insights-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Substack URLs", "type": "array", "description": "Publication or post URLs (e.g. https://example.substack.com or https://example.substack.com/p/some-post). Bare handles and @usernames also accepted. Leave empty if you use 'Publication handles', 'User handles' or 'Search queries' instead.", "items": { "type": "string" } }, "publicationHandles": { "title": "Publication handles", "type": "array", "description": "Bare publication handles (e.g. 'noahpinion'). Convenient for CSV lists.", "items": { "type": "string" } }, "userHandles": { "title": "User handles (for author profile + Notes)", "type": "array", "description": "User handles to fetch author profile and Notes feed.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries (publication discovery)", "type": "array", "description": "Keywords to search Substack's global publication directory.", "items": { "type": "string" } }, "maxSearchResults": { "title": "Max results per search query", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many top publications to return per search query.", "default": 10 }, "includePosts": { "title": "Include posts", "type": "boolean", "description": "For each publication, fetch the post archive.", "default": true }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap on posts fetched per publication.", "default": 25 }, "includeFullBody": { "title": "Include full post body", "type": "boolean", "description": "Fetch the full body of each post (extra request per post). Disable to skip and rely on archive snippets only.", "default": true }, "bodyFormat": { "title": "Body format", "enum": [ "both", "html", "markdown", "none" ], "type": "string", "description": "Which body format(s) to keep. 'markdown' is the AI/RAG-friendly form.", "default": "both" }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch nested comments per post (extra request per post that has comments).", "default": false }, "maxCommentsPerPost": { "title": "Max comments per post", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on comments fetched per post.", "default": 100 }, "includeNotes": { "title": "Include Notes feed (per user handle)", "type": "boolean", "description": "For each user handle, pull their Notes/restacks feed.", "default": false }, "maxNotesPerAuthor": { "title": "Max notes per author", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap on notes/restacks fetched per author handle.", "default": 50 }, "paywallFilter": { "title": "Paywall filter", "enum": [ "any", "free-only", "paid-only" ], "type": "string", "description": "Keep all posts, only free ones, or only paid ones.", "default": "any" }, "minReactions": { "title": "Min reactions per post (filter applied before billing — no charge for filtered entities)", "minimum": 0, "type": "integer", "description": "Skip posts below this reaction count.", "default": 0 }, "minComments": { "title": "Min comments per post", "minimum": 0, "type": "integer", "description": "Skip posts below this comment count.", "default": 0 }, "minRestacks": { "title": "Min restacks per post", "minimum": 0, "type": "integer", "description": "Skip posts below this restack count.", "default": 0 }, "minWordCount": { "title": "Min word count per post", "minimum": 0, "type": "integer", "description": "Useful for AI/RAG to filter out short announcements.", "default": 0 }, "maxWordCount": { "title": "Max word count per post (0 = unlimited)", "minimum": 0, "type": "integer", "description": "Drop posts longer than this. 0 means no upper limit.", "default": 0 }, "dateFrom": { "title": "Earliest post date", "type": "string", "description": "ISO date or YYYY-MM-DD. Drop posts older than this." }, "dateTo": { "title": "Latest post date", "type": "string", "description": "ISO date or YYYY-MM-DD. Drop posts newer than this." }, "keywordsInclude": { "title": "Must contain keywords", "type": "array", "description": "Drop posts whose title + subtitle + body text doesn't include at least one of these (case-insensitive).", "items": { "type": "string" } }, "keywordsExclude": { "title": "Must NOT contain keywords", "type": "array", "description": "Drop posts whose text contains any of these keywords.", "items": { "type": "string" } }, "hasPodcast": { "title": "Has podcast filter", "enum": [ "any", "yes", "no" ], "type": "string", "description": "Keep only posts with (or without) an attached podcast.", "default": "any" }, "postType": { "title": "Post type allow-list", "type": "array", "description": "Keep only certain post types (newsletter, podcast, thread). Empty = all.", "items": { "type": "string" } }, "minSubscribers": { "title": "Min subscribers per publication", "minimum": 0, "type": "integer", "description": "Skip publications below this subscriber count. Note: ~50% of publications hide subscriber counts — those are also skipped when this filter is on.", "default": 0 }, "paymentsEnabledOnly": { "title": "Payments-enabled publications only", "type": "boolean", "description": "Skip publications that don't offer paid subscriptions.", "default": false }, "includeContactInfo": { "title": "Extract contact info (lead-gen)", "type": "boolean", "description": "Parse emails, phones, payment links and categorise social/website links from bios.", "default": true }, "includeAnalytics": { "title": "Compute analytics block", "type": "boolean", "description": "Per-publication engagement rate, virality index, publish cadence, paid-post ratio, momentum (when history is on).", "default": true }, "outputMarkdownFiles": { "title": "Export per-post .md files (AI/RAG mode)", "type": "boolean", "description": "Write each post body as a separate .md file to the 'substack-markdown' key-value store, with YAML front matter. Useful for LlamaIndex/LangChain ingestion.", "default": false }, "enableHistory": { "title": "Enable historical tracking (subscriber growth & post velocity)", "type": "boolean", "description": "Persist a timestamped snapshot every run into a named store, then compute deltas (subscriber growth per day, posts added, trend) vs the previous run. Schedule the actor daily/weekly to build a time-series.", "default": false }, "historyDatasetName": { "title": "History store name", "type": "string", "description": "Named key-value store to persist snapshots into. Reused across scheduled runs.", "default": "substack-history" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Proxies are included and configured automatically — leave empty unless overriding." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel workers.", "default": 5 }, "minDelayMs": { "title": "Min delay between requests (ms)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Per-request throttle.", "default": 1000 } } }, "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 } } } } } } } } } }