{ "openapi": "3.0.1", "info": { "title": "Substack Scraper - Posts, Full Text, Comments & Rankings", "description": "Scrape Substack newsletters: every post of a publication with full text, comments and replies, keyword search across all of Substack, and category leaderboards with subscriber counts. No login, no API key.", "version": "1.0", "x-build-id": "865L4c9HAicdbDdeo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pipiagent~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pipiagent-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pipiagent~substack-scraper/runs": { "post": { "operationId": "runs-sync-pipiagent-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pipiagent~substack-scraper/run-sync": { "post": { "operationId": "run-sync-pipiagent-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to scrape", "enum": [ "posts", "postDetails", "comments", "search", "publications" ], "type": "string", "description": "Posts: every post of the publications you list. Post details: full text of single posts. Comments: comments and replies of posts. Search: posts that match keywords, across all of Substack. Publications: category leaderboards, or profiles of the publications you list, with subscriber counts.", "default": "posts" }, "publications": { "title": "Publications", "type": "array", "description": "For Posts and Publications modes. Publication URLs (https://www.lennysnewsletter.com, https://noahpinion.substack.com), subdomains (noahpinion) or author handles (@lenny).", "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "type": "array", "description": "For Post details and Comments modes. Links to posts, for example https://www.lennysnewsletter.com/p/how-to-tell-if-a-startup-has-a-moat .", "items": { "type": "string" } }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "For Search mode. Each keyword is searched across all of Substack, like the search box on substack.com.", "items": { "type": "string" } }, "categories": { "title": "Categories", "type": "array", "description": "For Publications mode. Substack leaderboard categories. Each gives up to about 500 ranked publications.", "items": { "type": "string", "enum": [ "96", "4", "62", "76739", "153", "13645", "podcast", "94", "15417", "76740", "76741", "103", "49715", "11", "223", "15414", "134", "339", "284", "355", "61", "109", "1796", "114", "387", "51282", "118", "18", "49692", "34", "76782", "76866", "76863" ], "enumTitles": [ "Culture", "Technology", "Business", "U.S. Politics", "Finance", "Food & Drink", "Podcasts", "Sports", "Art & Illustration", "World Politics", "Health Politics", "News", "Fashion & Beauty", "Music", "Faith & Spirituality", "Climate & Environment", "Science", "Literature", "Fiction", "Health & Wellness", "Design", "Travel", "Parenting", "Philosophy", "Comics", "International", "Crypto", "History", "Humor", "Education", "Film & TV", "Home & Garden", "Games" ] } }, "ranking": { "title": "Ranking", "enum": [ "paid", "all" ], "type": "string", "description": "For categories: Substack's bestseller list of paid newsletters, or the list of all newsletters (free and paid).", "default": "paid" }, "includeSubscriberCounts": { "title": "Add subscriber counts", "type": "boolean", "description": "For Publications mode. Adds the subscriber count, follower count and paid subscriber range from the author's profile. One extra request per publication.", "default": true }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of results to save in this run. You are only charged for saved results.", "default": 100 }, "maxItemsPerQuery": { "title": "Max results per input", "minimum": 1, "type": "integer", "description": "Optional. Limits the results of each publication, post, keyword or category, so one big input does not use up the whole run." }, "sortBy": { "title": "Sort by", "enum": [ "new", "top" ], "type": "string", "description": "Posts mode: newest posts first, or the most popular. Comments mode: newest comments first, or the best ones.", "default": "new" }, "postKeyword": { "title": "Only posts about", "type": "string", "description": "Posts mode, optional. Keeps only posts of the publication that match this word, using the publication's own archive search." }, "dateFrom": { "title": "Published from", "type": "string", "description": "Optional. Keeps only posts published on or after this date (YYYY-MM-DD). Works in Posts and Search modes." }, "dateTo": { "title": "Published to", "type": "string", "description": "Optional. Keeps only posts published on or before this date (YYYY-MM-DD)." }, "includeContent": { "title": "Add full text", "type": "boolean", "description": "Posts and Search modes: also loads the full text and HTML of every post (one extra request per post). Paid posts give only the free preview part. Post details mode always includes it.", "default": false }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Comments mode: also saves the replies under each comment. Every reply counts as one result.", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Substack works without a proxy. Set one only if runs keep failing.", "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 } } } } } } } } } }