{ "openapi": "3.0.1", "info": { "title": "Threads Scraper: Posts, Threads Replies, Profile Scraper, API", "description": "Meta Threads scraper API, no login: threads posts by link, a profile's posts with exact counts and views, threads replies and comment trees, a threads search scraper for keywords and tags, threads profiles with the exact follower count. One row per post, reply or profile; free rows for misses.", "version": "0.1", "x-build-id": "utkN0iBQhIo3WPb4K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hyperbach~threads-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hyperbach-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hyperbach~threads-scraper/runs": { "post": { "operationId": "runs-sync-hyperbach-threads-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hyperbach~threads-scraper/run-sync": { "post": { "operationId": "run-sync-hyperbach-threads-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "profiles": { "title": "Profiles: usernames or links", "type": "array", "description": "Threads profiles, one per line, in any form: `zuck`, `@zuck`, `https://www.threads.com/@zuck`, `https://www.threads.net/@zuck`, or a tab link such as `https://www.threads.com/@zuck/replies`. Each gives one `profile` row (the exact follower count, bio, links, tags, the shown threads count) and up to `maxPostsPerProfile` `post` rows from the tabs in `profileTabs`. The same user given several ways is one row. A value that is not a Threads profile comes back as a free row that says why.", "default": [], "items": { "type": "string" } }, "posts": { "title": "Posts: links or codes", "type": "array", "description": "Threads posts, one per line: `https://www.threads.com/@zuck/post/DdZ7sQvkTFn`, the same on threads.net, `https://www.threads.com/t/DdZ7sQvkTFn`, or the 11-character code `DdZ7sQvkTFn`. Each gives one `post` row with its five exact counts and its view count, and up to `maxRepliesPerPost` `post` rows of replies. One row per post: the same post given several ways is one row. A post that does not exist is a free row that says so.", "default": [], "items": { "type": "string" } }, "keywords": { "title": "Keywords or #tags", "type": "array", "description": "Search terms, one per line. A word or phrase reads the Top surface (about 20 posts, the page a visitor sees; `searchSurfaces` adds the Tags surface and the accounts the search box offers); `#tag` reads the Tags surface for that tag; a search link `https://www.threads.com/search?q=…&serp_type=tags` is read as given. Threads shows a visitor one page per surface, no Recent sort and no date window: every row says so (`list_note`) and whether it holds the keyword (`keyword_match`).", "default": [], "items": { "type": "string" } }, "maxPostsPerProfile": { "title": "Posts per profile", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many posts to read for each profile, newest first, from each tab in `profileTabs`; 0 = the profile row only. The Threads tab is read to the list's end (168 of 168 shown in our test, 1,400+ for a busy account); the replies and reposts tabs give their first page (about 30 posts, all Threads shows a visitor). With `onlyNew` or the filters, fewer rows are delivered than read: the cap bounds the depth, so a scheduled run reads the same newest posts every time.", "default": 25 }, "profileTabs": { "title": "Profile tabs", "type": "array", "description": "Which tabs of each profile to read for its posts; empty = `threads`. A tab given in a profile link (`…/@zuck/replies`) applies to that profile. Needs `maxPostsPerProfile` above 0.", "items": { "type": "string", "enum": [ "threads", "replies", "reposts" ], "enumTitles": [ "Threads (the profile's own posts; to the end)", "Replies (the profile's replies; first page)", "Reposts (what the profile reposted; first page)" ] }, "default": [] }, "postedAfter": { "title": "Posted after", "pattern": "^([0-9]{4}-[0-9]{2}-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?)?)?$", "type": "string", "description": "A UTC date (`2026-10-01`) or time (`2026-10-01T12:00:00Z`): on the Threads tab, the walk stops at the first post older than this (pinned posts excepted), so a scheduled run reads only the recent posts. Empty = no date floor. Search has no date window (Threads shows a visitor none).", "default": "" }, "includeProfileRow": { "title": "Profile row with the posts", "type": "boolean", "description": "Deliver each profile's own row (exact followers, bio, links; charged as a profile) with its posts. Off: the posts only, so 10 posts asked are 10 charged rows (the posts still carry the author's follower count from the profile page). A profile asked with `maxPostsPerProfile` 0 always gives its row.", "default": true }, "maxRepliesPerPost": { "title": "Replies per post", "minimum": 0, "maximum": 2000, "type": "integer", "description": "How many replies to read under each post in `posts`, as `post` rows with `reply_level`, `parent_post_code` and `root_post_code`; 0 = the post row only. Read to the list's end: Threads serves a visitor most but not all of a post's replies (231 + 33 nested of 318 in our test), and the post row says how many (`replies_note`). With the filters, fewer rows are delivered than read.", "default": 0 }, "repliesOrder": { "title": "Replies order", "enum": [ "top", "recent" ], "type": "string", "description": "The order Threads lists the replies in.", "default": "top" }, "includeNestedReplies": { "title": "Nested replies", "type": "boolean", "description": "Also read the conversation under each reply that has replies (one request per such reply), as `post` rows with `reply_level` 2 and deeper. Counted in `maxRepliesPerPost`.", "default": false }, "searchSurfaces": { "title": "Search surfaces", "type": "array", "description": "The surfaces read for each plain keyword, one page each; empty = `top`. A `#tag` keyword always reads the Tags surface. A post found on both surfaces is one row. `accounts` gives the accounts Threads' search box offers for the keyword (up to 10), each as an exact profile row charged as a profile.", "items": { "type": "string", "enum": [ "top", "tags", "accounts" ], "enumTitles": [ "Top (posts ranked for the keyword)", "Tags (posts under the matching topic tag)", "Accounts (the profiles the search box offers, as exact profile rows)" ] }, "default": [] }, "searchPasses": { "title": "Passes per surface", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many times to load each post surface of a keyword. Threads gives a visitor one page with no cursor, but the page changes between loads: each pass after the first loads it again on a fresh exit and adds the posts not seen yet, charged once (a second pass added 43 posts to 58 for starbucks and #coffee; 6 passes added 5 to 21 for a rare word). 1 = the page a visitor sees.", "default": 1 }, "maxPostsPerKeyword": { "title": "Posts per keyword", "minimum": 0, "maximum": 300, "type": "integer", "description": "The most posts read per keyword over its post surfaces (0 = every post of the pages read: about 20 a surface), and the most accounts from the `accounts` surface. With `keywordMatchOnly`, `onlyNew` or the filters, fewer rows are delivered than read.", "default": 0 }, "keywordMatchOnly": { "title": "Keyword matches only", "type": "boolean", "description": "Deliver only the search rows whose text, topic tag, quoted post or author holds the keyword (`keyword_match` true). Threads' Top surface ranks related posts too (about half hold the word in our test); off, every row is delivered with its flag.", "default": false }, "includeViews": { "title": "View counts on list rows", "type": "boolean", "description": "Read the view count of every profile post, search hit and reply (one request per row: Threads serves views only on a post's own page). A post you name in `posts` carries its views at no extra cost. Charged per row that gets one (`post_views`).", "default": false }, "includeAuthorProfiles": { "title": "Author profiles", "type": "boolean", "description": "One exact `profile` row per distinct author of the posts delivered (the exact follower count; one small request per author), charged as a profile; the post rows then carry `author_followers` and `engagement_rate`. Every post row already carries the author's username, id, name, verification and picture.", "default": false }, "includeRaw": { "title": "Raw Threads object", "type": "boolean", "description": "Keep Threads' own JSON object on each row (`raw`), for fields this Actor does not name.", "default": false }, "minLikes": { "title": "Minimum likes", "minimum": 0, "type": "integer", "description": "Leave out profile posts, search hits and replies with fewer likes than this; 0 = no floor. A post you name in `posts` is always delivered.", "default": 0 }, "verifiedOnly": { "title": "Verified authors only", "type": "boolean", "description": "Keep only list rows whose author is verified.", "default": false }, "onlyNew": { "title": "Only new posts", "type": "boolean", "description": "Deliver only posts no earlier run of the same task delivered (profile tabs and search rows); turns the memory on. With the memory on, a profile row says how its followers moved since the last run and a post read again carries its engagement change.", "default": false }, "stateStoreName": { "title": "Memory name", "pattern": "^([A-Za-z0-9._-]{1,100})?$", "type": "string", "description": "Name of the memory between runs. Given, it turns the memory on: profile rows get `followers_previous` and `followers_change`, post rows read again get `engagement_change`; with `onlyNew`, posts delivered before are skipped. Empty = derived from the inputs when `onlyNew` is on.", "default": "" }, "maxItems": { "title": "Max charged rows", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "The most charged rows this run delivers, profiles, posts and replies together. 0 = no limit. Free rows (not found, invalid, empty, duplicate) do not count.", "default": 0 }, "proxyUrl": { "title": "Your own proxy (optional)", "type": "string", "description": "`http://user:pass@host:port` — a proxy of yours to read Threads through, tried before the Actor's own exits. Leave empty: the Actor brings its own." }, "runTag": { "title": "Run tag", "maxLength": 100, "type": "string", "description": "A label copied onto every row (`run_tag`), to tell runs apart in a shared dataset.", "default": "" } } }, "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 } } } } } } } } } }