{ "openapi": "3.0.1", "info": { "title": "Mastodon & Lemmy Scraper: Fediverse Posts, Profiles, Comments", "description": "Scrape Mastodon and Lemmy with no login or API key: hashtag posts across many servers, account posts, profiles, followers, trending posts & hashtags, replies, Lemmy keyword search, community posts, comments and communities. Bio email/website extraction. JSON, CSV, Excel.", "version": "1.0", "x-build-id": "hpeeYZaB7h3NasZbb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spriggs-data~fediverse-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spriggs-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spriggs-data~fediverse-scraper/runs": { "post": { "operationId": "runs-sync-spriggs-data-fediverse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spriggs-data~fediverse-scraper/run-sync": { "post": { "operationId": "run-sync-spriggs-data-fediverse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "What to scrape", "enum": [ "hashtagPosts", "accountPosts", "profiles", "followers", "following", "searchAccounts", "trendingPosts", "trendingHashtags", "postReplies", "lemmySearch", "lemmyCommunityPosts", "lemmyPostComments", "lemmyCommunities" ], "type": "string", "description": "Mastodon modes use 'Hashtags', 'Accounts', 'Search terms' or 'URLs' plus 'Mastodon servers'. Lemmy modes use 'Search terms', 'Communities' or 'URLs' plus 'Lemmy servers'.", "default": "hashtagPosts" }, "hashtags": { "title": "Hashtags", "type": "array", "description": "Without or with #, e.g. tattoo, opensource. Used by 'posts with a #hashtag'.", "default": [ "tattoo" ], "items": { "type": "string" } }, "instances": { "title": "Mastodon servers", "type": "array", "description": "Servers to read from, e.g. mastodon.social, fosstodon.org, hachyderm.io, mstdn.social. Each server shows the hashtag posts it knows about; adding more servers finds more posts (duplicates are removed). Also used for account search and trends.", "default": [ "mastodon.social" ], "items": { "type": "string" } }, "accounts": { "title": "Mastodon accounts", "type": "array", "description": "@user@server, user@server or a profile URL like https://mastodon.social/@Gargron. Used by account posts, profiles, followers and following.", "items": { "type": "string" } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Mastodon: people search (names, bios). Lemmy: full-text search of posts, comments or communities. (Logged-out Mastodon has no full-text post search; use hashtags.)", "items": { "type": "string" } }, "urls": { "title": "Post URLs", "type": "array", "description": "Mastodon post URL (https://server/@user/123...) for 'replies'; Lemmy post URL (https://lemmy.world/post/123) for 'comments'.", "items": { "type": "string" } }, "lemmyInstances": { "title": "Lemmy servers", "type": "array", "description": "e.g. lemmy.world, lemmy.ml, sh.itjust.works, lemm.ee. Search runs on each server (duplicates removed).", "default": [ "lemmy.world" ], "items": { "type": "string" } }, "communities": { "title": "Lemmy communities", "type": "array", "description": "!technology@lemmy.world, technology@lemmy.world or https://lemmy.world/c/technology.", "items": { "type": "string" } }, "maxItemsPerInput": { "title": "Max items per input", "minimum": 1, "type": "integer", "description": "Upper limit for each hashtag / account / search term / community / URL (per server for trends).", "default": 100 }, "maxItems": { "title": "Max total items", "minimum": 0, "type": "integer", "description": "Hard cap for the whole run (keeps cost predictable). 0 = no cap.", "default": 1000 }, "since": { "title": "Posted since (YYYY-MM-DD)", "type": "string", "description": "Only posts/comments created on or after this date." }, "until": { "title": "Posted before (YYYY-MM-DD)", "type": "string", "description": "Only posts/comments created before this date." }, "language": { "title": "Language (Mastodon)", "type": "string", "description": "ISO code like en, de, ja. Keeps only Mastodon posts in that language." }, "excludeReplies": { "title": "Exclude replies (Mastodon)", "type": "boolean", "description": "Skip posts that are replies.", "default": false }, "excludeBoosts": { "title": "Exclude boosts (Mastodon)", "type": "boolean", "description": "Skip boosts (reposts) in account posts.", "default": false }, "onlyMedia": { "title": "Only posts with media (Mastodon)", "type": "boolean", "description": "Hashtag and account posts with images/video only.", "default": false }, "lemmySort": { "title": "Lemmy sort", "enum": [ "New", "Hot", "Active", "TopDay", "TopWeek", "TopMonth", "TopYear", "TopAll", "MostComments", "NewComments", "Old" ], "type": "string", "description": "Order for Lemmy search and community posts. 'New' lets the date filter stop early.", "default": "New" }, "lemmySearchType": { "title": "Lemmy search returns", "enum": [ "Posts", "Comments", "Communities" ], "type": "string", "description": "For 'Lemmy: keyword search'.", "default": "Posts" }, "lemmyCommunity": { "title": "Limit Lemmy search to one community", "type": "string", "description": "Optional, e.g. technology@lemmy.world." }, "extractContacts": { "title": "Extract emails & websites from bios", "type": "boolean", "description": "Adds emails[] and websites[] to Mastodon profiles (from the bio and profile links).", "default": false }, "skipNsfw": { "title": "Skip NSFW", "type": "boolean", "description": "Skip Lemmy posts/communities marked NSFW and Mastodon posts whose media is marked sensitive.", "default": true }, "respectNoIndex": { "title": "Respect search opt-outs", "type": "boolean", "description": "Skip Mastodon accounts that opted out of search-engine indexing (noindex).", "default": 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 } } } } } } } } } }