{ "openapi": "3.0.1", "info": { "title": "🦅 X/Twitter Scraper & Data Extractor", "description": "Extract high-quality data from X (formerly Twitter) with our advanced, auto-routing scraping engine. Pay only for the data you need at an unbeatable price of $0.20 per 1,000 tweets.", "version": "0.0", "x-build-id": "yZx8ixRCwVFzdicXj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/x402~x-twitter-scraper-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-x402-x-twitter-scraper-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/x402~x-twitter-scraper-data-extractor/runs": { "post": { "operationId": "runs-sync-x402-x-twitter-scraper-data-extractor", "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/x402~x-twitter-scraper-data-extractor/run-sync": { "post": { "operationId": "run-sync-x402-x-twitter-scraper-data-extractor", "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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional mixed X/Twitter URLs. Supports profile timelines, `/with_replies`, `/media`, list URLs, and search URLs. Tweet URLs are currently skipped with a warning because this build focuses on timeline and search routes." }, "urls": { "title": "URLs", "type": "array", "description": "Alias for Start URLs. Accepts strings or `{ \"url\": \"...\" }` objects." }, "profileUrls": { "title": "Profile URLs", "type": "array", "description": "Optional profile URL alias for timeline, `/with_replies`, and `/media` targets." }, "twitterHandles": { "title": "X Handles", "type": "array", "description": "Usernames to scrape. Accepts handles with or without the `@` prefix. These route through the fast profile timeline path unless you enable replies or media mode.", "items": { "type": "string" } }, "usernames": { "title": "Usernames", "type": "array", "description": "Alias for X Handles.", "items": { "type": "string" } }, "listUrls": { "title": "List URLs", "type": "array", "description": "X list URLs to scrape through the dedicated list timeline route.", "items": { "type": "string" } }, "listIds": { "title": "List IDs", "type": "array", "description": "Numeric X list IDs. Each ID is converted to `https://x.com/i/lists/` and routed through the dedicated list scraper.", "items": { "type": "string" } }, "searchTerms": { "title": "Search Terms", "type": "array", "description": "Run multiple searches in one Actor run. If `searchType` is `profile_tweets` and you provide profile targets, each term is searched inside each profile. Otherwise the terms route to global tweet or user search.", "items": { "type": "string" } }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Single-query alias for Search Terms. Useful for API users who want one search string." }, "query": { "title": "Query", "type": "string", "description": "Alias for Search Query." }, "searchType": { "title": "Search Type", "enum": [ "tweets", "users", "profile_tweets" ], "type": "string", "description": "Choose how `searchTerms`, `searchQuery`, and `query` should route when they are not encoded in start URLs.", "default": "tweets" }, "contentFilters": { "title": "Structured Content Filters", "type": "object", "description": "Optional content-level filters that are compiled into a fallback search query only when no explicit search term is provided." }, "userFilters": { "title": "Structured User Filters", "type": "object", "description": "Optional user filters such as `fromUser`, `toUser`, `mentionUser`, and `listId`. These also help build a fallback query when no direct search term is provided." }, "timeFilters": { "title": "Structured Time Filters", "type": "object", "description": "Optional structured time filters. `sinceDate` and `untilDate` are used as aliases for Start Date and End Date." }, "geoFilters": { "title": "Structured Geo Filters", "type": "object", "description": "Optional structured location filters. `nearPlace` is used as an alias for Location." }, "engagementFilters": { "title": "Structured Engagement Filters", "type": "object", "description": "Optional structured engagement thresholds used as aliases for the top-level minimum metrics." }, "mediaFilters": { "title": "Structured Media Filters", "type": "object", "description": "Optional structured media filters used as aliases for image, video, and link filtering when present." }, "tweetTypeFilters": { "title": "Structured Tweet Type Filters", "type": "object", "description": "Optional structured tweet-type filters used as aliases for quote-only, verified-only, and safe-search controls." }, "fromUser": { "title": "From User", "type": "string", "description": "Fallback search builder input. When no explicit search term is provided, this compiles into a `from:` query fragment." }, "toUser": { "title": "To User", "type": "string", "description": "Fallback search builder input. When no explicit search term is provided, this compiles into a `to:` query fragment." }, "mentionedUser": { "title": "Mentioned User", "type": "string", "description": "Fallback search builder input. When no explicit search term is provided, this compiles into an `@username` query fragment." }, "mentionUser": { "title": "Mention User Alias", "type": "string", "description": "Alias for Mentioned User." }, "listIdFilter": { "title": "List ID Filter", "type": "string", "description": "Fallback search builder input. When no explicit search term is provided, this compiles into a `list:` query fragment." }, "includeReplies": { "title": "Include Replies", "type": "boolean", "description": "Route manual profile targets through the profile-with-replies tab.", "default": false }, "mediaOnly": { "title": "Media Only", "type": "boolean", "description": "Route manual profile targets through the profile media tab.", "default": false }, "scrapeProfileInfo": { "title": "Scrape Profile Info", "type": "boolean", "description": "Push a free profile row alongside tweet results when profile metadata is available.", "default": true }, "respectProfileSubpages": { "title": "Respect Profile Subpages", "type": "boolean", "description": "When enabled, `.../with_replies` and `.../media` URLs keep their explicit route instead of inheriting the global profile mode.", "default": true }, "includeRetweets": { "title": "Include Retweets", "type": "boolean", "description": "Return retweets in profile-based results when available.", "default": true }, "includeNativeRetweets": { "title": "Include Native Retweets In Search", "type": "boolean", "description": "Include native retweets in search-based tweet results.", "default": true }, "maxItems": { "title": "Max Items Per Target", "minimum": 0, "type": "integer", "description": "Maximum number of rows to attempt per target or search term. Set `0` for no cap.", "default": 100 }, "startDate": { "title": "Start Date (YYYY-MM-DD)", "type": "string", "description": "Optional inclusive start date in `YYYY-MM-DD` format." }, "sinceDate": { "title": "Since Date Alias (YYYY-MM-DD)", "type": "string", "description": "Alias for Start Date." }, "endDate": { "title": "End Date (YYYY-MM-DD)", "type": "string", "description": "Optional inclusive end date in `YYYY-MM-DD` format." }, "untilDate": { "title": "Until Date Alias (YYYY-MM-DD)", "type": "string", "description": "Alias for End Date." }, "latestTweets": { "title": "Latest Tweets Only", "type": "boolean", "description": "Shortcut for setting the search start date to the last 7 days when `startDate` is empty.", "default": false }, "location": { "title": "Location", "type": "string", "description": "Optional location filter for supported search routes." }, "nearPlace": { "title": "Near Place Alias", "type": "string", "description": "Alias for Location." }, "onlyImages": { "title": "Only Images", "type": "boolean", "description": "Keep only rows that contain image media.", "default": false }, "onlyVideos": { "title": "Only Videos", "type": "boolean", "description": "Keep only rows that contain video media.", "default": false }, "onlyVerified": { "title": "Only Verified Authors", "type": "boolean", "description": "Keep only rows from verified authors.", "default": false }, "onlyQuotes": { "title": "Only Quote Tweets", "type": "boolean", "description": "Keep only quote tweets.", "default": false }, "includeLinks": { "title": "Only Tweets With Links", "type": "boolean", "description": "Keep only rows that contain external URLs.", "default": false }, "safeSearch": { "title": "Safe Search", "type": "boolean", "description": "Enable the source's safe-search flag when available.", "default": false }, "minLikes": { "title": "Minimum Likes", "minimum": 0, "type": "integer", "description": "Drop tweets below this like threshold.", "default": 0 }, "minReplies": { "title": "Minimum Replies", "minimum": 0, "type": "integer", "description": "Drop tweets below this reply threshold.", "default": 0 }, "minRetweets": { "title": "Minimum Retweets", "minimum": 0, "type": "integer", "description": "Drop tweets below this retweet threshold.", "default": 0 }, "tweetLanguage": { "title": "Tweet Language", "enum": [ "", "en", "es", "fr", "de", "it", "pt", "ja", "ko", "zh-cn", "ar", "hi", "tr" ], "type": "string", "description": "Best-effort language filter using the source language code when the HTML exposes it.", "default": "" }, "useResidentialProxy": { "title": "Use Residential Proxy", "type": "boolean", "description": "Enable Apify residential proxy for better reliability.", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify proxy configuration override.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "proxyCountryCode": { "title": "Proxy Country Code", "type": "string", "description": "Optional 2-letter country code to pin the proxy country.", "default": "" }, "maxRetries": { "title": "Max Retries Per Request", "minimum": 1, "maximum": 5, "type": "integer", "description": "Bounded retry count for network requests.", "default": 3 } } }, "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 } } } } } } } } } }