{ "openapi": "3.0.1", "info": { "title": "Threads Scraper | 25 Fields, 4 Modes, No Login, Monitor", "description": "Scrape Meta Threads (threads.com) posts, profiles, hashtags & search. No login, no cookies. Get text, media, likes, replies & reposts. Pay only per post delivered. Works in Claude, ChatGPT & any MCP agent.", "version": "0.4", "x-build-id": "AM9nww65Dn8BSkgyJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/themineworks~threads-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-themineworks-threads-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/themineworks~threads-scraper/runs": { "post": { "operationId": "runs-sync-themineworks-threads-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/themineworks~threads-scraper/run-sync": { "post": { "operationId": "run-sync-themineworks-threads-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Mode", "enum": [ "profile", "post", "search", "hashtag" ], "type": "string", "description": "Which type of scrape to run. IMPORTANT for volume: search and hashtag mode return posts at scale (tens to hundreds per run). Profile mode returns only the handful of recent posts Threads exposes to a logged-out visitor, typically 4 to 5 per profile, regardless of how high you set Max posts. If you need many posts about a person or topic, use search.", "default": "profile" }, "profileUsernames": { "title": "Profile usernames", "maxItems": 20, "type": "array", "description": "Threads usernames (without @) to scrape, used when mode=profile. Example: [\"zuck\", \"mosseri\"]. Expect roughly 4 to 5 recent posts PER USERNAME: that is Threads' own logged-out limit, not a cap we set, and one profile's timeline stops returning new posts beyond it. To reach a higher maxPosts, add MORE usernames rather than raising maxPosts alone — the run pulls from each in turn and keeps going until the total is met or the list runs out. A username that returns nothing (blocked, private, wrong handle) is skipped, not fatal to the run. Verified live: 6 usernames, maxPosts=20, returned exactly 20, spread 5/4/4/4/2/1 across 5 of the 6 (one returned nothing).", "default": [ "zuck" ], "items": { "type": "string" } }, "postUrls": { "title": "Post URLs", "maxItems": 50, "type": "array", "description": "List of full Threads post URLs to scrape. Used when mode=post. Example: [\"https://www.threads.net/@zuck/post/Cuc1234\"]", "default": [], "items": { "type": "string" } }, "searchQuery": { "title": "Search query", "type": "string", "description": "Search keyword. Used when mode=search.", "default": "" }, "hashtag": { "title": "Hashtag", "type": "string", "description": "Hashtag to scrape, without the leading #. Used when mode=hashtag.", "default": "" }, "maxPosts": { "title": "Max posts", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum posts to return across the whole run. This is a ceiling, not a target: the actor stops as soon as it has enough or every target is exhausted. In search and hashtag mode a high value is usually reached from one query. In profile mode, ONE username caps around 4 to 5 posts (Threads' own logged-out limit) — to actually reach a high maxPosts here, list several usernames in Profile usernames above; the run draws from each until the total is met. You are never charged for posts that do not exist.", "default": 25 }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "If true, include reply posts in the output.", "default": false }, "includeReposts": { "title": "Include reposts", "type": "boolean", "description": "If true, include reposts in the output.", "default": false }, "includeTagWindow": { "title": "Include the tag window (search mode)", "type": "boolean", "description": "Search mode also reads the tag feed for the query, which can surface posts that carry the tag without spelling out the words. Posts that do not mention the tag are dropped and never charged, so this is safe to leave on. Turn it OFF if you want results only from the search windows for your exact query.", "default": true }, "resultType": { "title": "Result type", "enum": [ "recent", "top" ], "type": "string", "description": "For search and hashtag modes: 'recent' or 'top'.", "default": "recent" }, "monitorMode": { "title": "Monitor mode (only new results)", "type": "boolean", "description": "Run on a schedule and deliver ONLY results not seen in a previous run. You are charged per new result, not for the whole feed each time. Ideal for daily monitoring. Requires the same input across runs.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy. Defaults to datacenter with a fresh rotating session per request, which clears Threads' IP throttling. Switch to residential only if you see persistent blocks.", "default": { "useApifyProxy": 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 } } } } } } } } } }