{ "openapi": "3.0.1", "info": { "title": "X (Twitter) Tweet Scraper — browserless", "description": "Scrapes public tweets from X without a browser engine, using guest-token GraphQL over plain HTTP. Free runs return up to 10 results.", "version": "0.1", "x-build-id": "wj4iT8pgxQKYZrlWc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/arthurvianna~x-tweet-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-arthurvianna-x-tweet-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/arthurvianna~x-tweet-scraper/runs": { "post": { "operationId": "runs-sync-arthurvianna-x-tweet-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/arthurvianna~x-tweet-scraper/run-sync": { "post": { "operationId": "run-sync-arthurvianna-x-tweet-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "fromUsers": { "title": "From these accounts", "type": "array", "description": "Handles without '@'. When supplied, the Actor makes no third-party call at all: these accounts are crawled directly on X. This is the fastest and most deterministic path — clear it to discover accounts from `searchTerms`/`hashtags` instead.", "items": { "type": "string" } }, "tweetIds": { "title": "Tweet IDs", "type": "array", "description": "Specific tweet ids to hydrate, one request each. This is a target in its own right: a run may supply only tweetIds and no accounts. An id that names a deleted or unreachable tweet is counted and skipped, never fatal.", "items": { "type": "string" } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Keywords to match against tweet text (case-insensitive). Multiple terms are OR'd. X's search timeline is closed to guest tokens, so this is the stretch surface: with no `fromUsers` supplied these keywords also seed account discovery via one search-engine lookup. Recall is seed-bounded — see the README.", "items": { "type": "string" } }, "hashtags": { "title": "Hashtags", "type": "array", "description": "Without '#'. A post-filter over the timelines a target produced, matched case-insensitively against the tweet's hashtag entities — not a target on its own.", "items": { "type": "string" } }, "since": { "title": "Since (inclusive)", "type": "string", "description": "ISO date or datetime, e.g. 2026-08-01. Inclusive. Applied to the tweet's Snowflake ID, so it is exact." }, "until": { "title": "Until (inclusive)", "type": "string", "description": "ISO date or datetime. Inclusive — a bare date covers the whole day up to 23:59:59.999 UTC." }, "language": { "title": "Language", "type": "string", "description": "ISO-639-1 code, matched against X's own language detection (e.g. en, pt, es)." }, "minLikes": { "title": "Minimum likes", "minimum": 0, "type": "integer", "description": "Inclusive floor." }, "minRetweets": { "title": "Minimum retweets", "minimum": 0, "type": "integer", "description": "Inclusive floor." }, "minReplies": { "title": "Minimum replies", "minimum": 0, "type": "integer", "description": "Inclusive floor." }, "onlyVerified": { "title": "Only verified authors", "type": "boolean", "description": "X conflates paid Blue with legacy verification, so this matches either. Leave unset for no constraint — it never excludes verified authors." }, "mediaType": { "title": "Media type", "enum": [ "images", "video", "links", "text_only" ], "type": "string", "description": "images = has at least one photo; video = has video or GIF (X stores GIFs as MP4); links = has at least one URL; text_only = no media and no links." }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Excluded by default.", "default": false }, "includeRetweets": { "title": "Include retweets", "type": "boolean", "description": "Excluded by default. When included, a retweet carries the original's full text and metrics — the retweet wrapper's counters are structurally zero.", "default": false }, "sortBy": { "title": "Sort order", "enum": [ "latest", "top" ], "type": "string", "description": "latest = newest first, exact (tweet IDs are monotonic). top = ranked by likes + retweets within the collected set; X's own relevance ranking is not reproducible from the logged-out surface.", "default": "latest" }, "maxResults": { "title": "Maximum results", "minimum": 1, "type": "integer", "description": "How many tweets to return. Free runs are capped at 10 results regardless of this value; the cap is enforced server-side. Paid runs receive the full amount.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxies are recommended: X rate-limits per guest token and per IP, and the Actor pins one token to one IP for the life of a session.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Concurrent accounts", "minimum": 1, "maximum": 20, "type": "integer", "description": "Advanced. A single timeline's cursor chain is sequential, so parallelism happens across accounts.", "default": 4 }, "maxAccounts": { "title": "Maximum accounts to crawl", "minimum": 1, "type": "integer", "description": "Advanced. Upper bound on how many accounts a single run will crawl, including accounts found by seed expansion.", "default": 50 }, "maxPagesPerAccount": { "title": "Maximum pages per account", "minimum": 1, "type": "integer", "description": "Advanced. One page is ~20 tweets on a paginated timeline.", "default": 25 }, "expansionDepth": { "title": "Seed expansion depth", "minimum": 0, "maximum": 2, "type": "integer", "description": "Advanced. 0 disables snowball expansion. Mentions and retweeted authors are harvested from pages already fetched, so expansion costs no extra requests — but precision decays with depth.", "default": 1 }, "maxSessions": { "title": "Guest token pool size", "minimum": 1, "maximum": 50, "type": "integer", "description": "Advanced. Each token is worth ~50 requests per 15 minutes. Tokens are free and instant to mint.", "default": 5 }, "maxRequests": { "title": "Request budget", "minimum": 1, "type": "integer", "description": "Advanced. Hard ceiling on requests to X for the whole run — the cost control. Low-selectivity keyword filters can otherwise fetch thousands of tweets for a handful of matches.", "default": 500 } } }, "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 } } } } } } } } } }