{ "openapi": "3.0.1", "info": { "title": "Fediverse Scraper (Mastodon + Bluesky)", "description": "Scrape Mastodon and Bluesky profiles, posts and hashtag timelines through the platforms' official public APIs. One normalized schema across both networks. No login required.", "version": "1.0", "x-build-id": "Rams9atircaMiIclf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/astraedus~fediverse-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-astraedus-fediverse-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/astraedus~fediverse-scraper/runs": { "post": { "operationId": "runs-sync-astraedus-fediverse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/astraedus~fediverse-scraper/run-sync": { "post": { "operationId": "run-sync-astraedus-fediverse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "targets": { "title": "Targets", "type": "array", "description": "What to scrape, one entry per line. The platform is detected automatically.\n\nMastodon: `@user@instance`, `#hashtag@instance`, a profile URL (`https://mastodon.social/@Gargron`), or a post permalink. Works on any Mastodon instance, not just mastodon.social.\n\nBluesky: a handle (`bsky.app`, `alice.bsky.social`), a `did:plc:...`, a profile or post URL (`https://bsky.app/profile/bsky.app`), or an `at://` URI. People search: `bsky:actors:climate`.\n\nNot supported: Bluesky keyword/hashtag search. Bluesky refuses unauthenticated search requests from datacenter IPs and this Actor never asks for your password. Use a Mastodon hashtag target instead.", "items": { "type": "string" }, "default": [ "@astraedus@mastodon.social", "@Gargron@mastodon.social", "#opensource@mastodon.social", "bsky.app" ] }, "mode": { "title": "What to collect", "enum": [ "both", "profiles", "posts" ], "type": "string", "description": "`both` (default) returns a profile row for every account target plus post rows for everything. `profiles` returns account rows only - for a hashtag target, that means the accounts posting under it. `posts` returns post rows only.", "default": "both" }, "maxPostsPerTarget": { "title": "Max posts per target", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper bound on post rows collected for each target. Pagination stops as soon as this is reached, so a lower number is a cheaper, faster run. Raise it for a full backfill.", "default": 20 }, "since": { "title": "Only posts since", "type": "string", "description": "Optional ISO date (`2026-01-01`) or timestamp. Posts older than this are skipped and pagination stops early once the feed passes the cut-off. Leave empty for no date limit." }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Include posts that are replies to someone else. Off by default, because most users want original posts.", "default": false }, "includeReposts": { "title": "Include boosts / reposts", "type": "boolean", "description": "Include content the account boosted (Mastodon) or reposted (Bluesky) rather than wrote. Such rows are flagged with `isRepost: true` and credited to the original author.", "default": false }, "resolveMedia": { "title": "Include media", "type": "boolean", "description": "Populate the `media` array with image, video and link-card URLs plus their alt text. Turn off for a smaller, text-only dataset.", "default": true }, "includeRaw": { "title": "Include raw API response", "type": "boolean", "description": "Attach the untouched API object to every row as `raw`. Useful when you need a field this Actor does not normalize; makes the dataset several times larger.", "default": false }, "defaultMastodonInstance": { "title": "Default Mastodon instance", "type": "string", "description": "Instance used for targets written without one, such as a bare `#hashtag`.", "default": "mastodon.social" }, "maxConcurrency": { "title": "Max concurrent targets", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many targets to work on at once. Requests to any single server are paced regardless, to stay well inside published rate limits.", "default": 4 } } }, "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 } } } } } } } } } }