{ "openapi": "3.0.1", "info": { "title": "Mastodon Scraper", "description": "Scrapes public data from any Mastodon instance via its REST API, including accounts, posts, threads, hashtags, and public timelines. No authentication required. Returns structured data with author details, post content, engagement metrics, media URLs, timestamps, and source URLs.", "version": "0.0", "x-build-id": "CJLBCvvdFXmHikOWR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~mastodon-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-mastodon-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~mastodon-scraper/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-mastodon-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~mastodon-scraper/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-mastodon-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "instance": { "title": "Instance", "type": "string", "description": "Default Mastodon instance URL used for hashtags, the public timeline, and local-only account lookups." }, "accounts": { "title": "Accounts", "type": "array", "description": "Handles to scrape. Use 'user' (looked up on the instance) or 'user@home.instance' (looked up on its own server, more reliable).", "items": { "type": "string" } }, "includeProfiles": { "title": "Include profile records", "type": "boolean", "description": "Also push an account/profile row for each scraped account.", "default": true }, "hashtags": { "title": "Hashtags", "type": "array", "description": "Hashtags (with or without #) to pull from the instance's tag timeline.", "items": { "type": "string" } }, "statusUrls": { "title": "Status URLs (threads)", "type": "array", "description": "Full status URLs (e.g. https://mastodon.social/@user/123). Each one's thread context is scraped.", "items": { "type": "string" } }, "includePublicTimeline": { "title": "Include public timeline", "type": "boolean", "description": "Scrape the instance public timeline. Many large instances (e.g. mastodon.social) restrict this to logged-in users and will error.", "default": false }, "local": { "title": "Local only", "type": "boolean", "description": "For hashtag/public timeline: restrict to posts from the instance's own users.", "default": false }, "excludeReplies": { "title": "Exclude replies", "type": "boolean", "description": "When scraping account statuses, skip replies.", "default": true }, "maxPostsPerTarget": { "title": "Max posts per target", "minimum": 1, "type": "integer", "description": "Max statuses to pull per account, hashtag, or timeline.", "default": 40 }, "maxItems": { "title": "Max total records", "minimum": 1, "type": "integer", "description": "Hard cap on total records pushed to the dataset across all modes.", "default": 5000 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Off by default — Mastodon's public API is open and rarely needs a proxy." } } }, "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 } } } } } } } } } }