{ "openapi": "3.0.1", "info": { "title": "All-in-One X/Twitter Scraper", "description": "X/Twitter scraper — 10 modes: tweets, profiles, followers, comments, timelines, lists, search & more. From $0.09/1K — up to 90% cheaper than alternatives. Premium residential proxy (~95% success rate). apidojo-compatible output. MCP-ready for AI agents.", "version": "0.1", "x-build-id": "VqIJP7HisaudhmXuG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/get-leads~all-in-one-x-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-get-leads-all-in-one-x-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/get-leads~all-in-one-x-scraper/runs": { "post": { "operationId": "runs-sync-get-leads-all-in-one-x-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/get-leads~all-in-one-x-scraper/run-sync": { "post": { "operationId": "run-sync-get-leads-all-in-one-x-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": [ "scrapeMode" ], "properties": { "scrapeMode": { "title": "Scrape Mode", "enum": [ "x-post-scraper", "x-profile-scraper", "x-search-scraper", "x-hashtag-scraper", "x-timeline-scraper", "x-follower-scraper", "x-following-scraper", "x-comment-scraper", "x-list-scraper", "x-data-extractor", "x-scraper", "x-user-search-scraper" ], "type": "string", "description": "Choose which X/Twitter scraper to run.", "default": "x-post-scraper" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "X/Twitter URLs — automatically detects if tweet URL or profile URL and routes to the right scraper. Supports: tweet URLs (x.com/user/status/123), profile URLs (x.com/username), search URLs, list URLs.", "items": { "type": "string" }, "default": [] }, "searchQueries": { "title": "Search Queries", "type": "array", "description": "X/Twitter search queries using advanced search syntax. Supports: keywords, #hashtags, from:user, to:user, since:YYYY-MM-DD, until:YYYY-MM-DD, lang:xx, filter:media, filter:images, filter:videos, min_retweets:N, min_faves:N, -filter:retweets, conversation_id:ID. Used by: x-search-scraper, x-hashtag-scraper.", "items": { "type": "string" }, "default": [] }, "profiles": { "title": "Profiles / Handles", "type": "array", "description": "X/Twitter handles, @usernames, or profile URLs. Duplicates removed. Used by: x-profile-scraper, x-timeline-scraper, x-follower-scraper, x-following-scraper. Note: 'twitterHandles' is the preferred field name; 'profiles' is kept for backward compatibility.", "items": { "type": "string" }, "default": [] }, "twitterHandles": { "title": "Twitter Handles", "type": "array", "description": "X/Twitter handles to scrape. This is the preferred field name for usernames. Same as 'profiles' field (both are read). Used by: x-profile-scraper, x-timeline-scraper, x-follower-scraper, x-following-scraper.", "items": { "type": "string" }, "default": [] }, "tweetURLs": { "title": "Tweet URLs", "type": "array", "description": "X/Twitter post URLs or tweet IDs. Supports x.com and twitter.com URLs. Used by: x-post-scraper, x-comment-scraper, x-data-extractor.", "items": { "type": "string" }, "default": [] }, "listURLs": { "title": "List URLs", "type": "array", "description": "X/Twitter list URLs. Must use full URL format: https://x.com/i/lists/1234567890 (bare list IDs are not supported). Used by: x-list-scraper.", "items": { "type": "string" }, "default": [] }, "conversationIds": { "title": "Conversation IDs", "type": "array", "description": "Tweet/conversation IDs to scrape replies from. Adds 'conversation_id:' prefix to search queries automatically. Requires login cookies.", "items": { "type": "string" }, "default": [] }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum results per query/profile/tweet. Controls how many tweets, followers, or comments to return per input item.", "default": 100 }, "sort": { "title": "Sort Order", "enum": [ "Latest", "Top", "Latest + Top" ], "type": "string", "description": "How to sort search results. 'Latest' for chronological, 'Top' for most relevant, 'Latest + Top' runs both and deduplicates.", "default": "Latest" }, "followerMode": { "title": "Follower Mode", "enum": [ "followers", "following" ], "type": "string", "description": "Whether to scrape followers or following list. Applies to x-follower-scraper. For a dedicated following-list mode, use x-following-scraper instead.", "default": "followers" }, "includeReplies": { "title": "Include Replies", "type": "boolean", "description": "Include reply tweets in profile timelines. Adds '-filter:replies' to queries when disabled.", "default": false }, "languageFilter": { "title": "Language Filter", "type": "string", "description": "Filter tweets by language code (ISO 639-1). Examples: en, es, fr, ja, de, pt, ar. Leave empty for all languages.", "default": "" }, "tweetLanguage": { "title": "Tweet Language (alias)", "type": "string", "description": "Alias for 'Language Filter'. Same as languageFilter — provided for compatibility with apidojo format. ISO 639-1 code.", "default": "" }, "start": { "title": "Start Date", "type": "string", "description": "Only return results after this date. Format: YYYY-MM-DD. Only works with search queries. Adds 'since:' to search query automatically.", "default": "" }, "end": { "title": "End Date", "type": "string", "description": "Only return results before this date. Format: YYYY-MM-DD. Only works with search queries. Adds 'until:' to search query automatically.", "default": "" }, "minimumFavorites": { "title": "Minimum Likes", "minimum": 0, "type": "integer", "description": "Only return tweets with at least this many likes. Adds 'min_faves:' to search queries." }, "minimumRetweets": { "title": "Minimum Retweets", "minimum": 0, "type": "integer", "description": "Only return tweets with at least this many retweets. Adds 'min_retweets:' to search queries." }, "minimumReplies": { "title": "Minimum Replies", "minimum": 0, "type": "integer", "description": "Only return tweets with at least this many replies. Adds 'min_replies:' to search queries." }, "includeSearchTerms": { "title": "Include Search Terms", "type": "boolean", "description": "If enabled, adds a 'searchTerm' field to each result showing which search query produced it.", "default": false }, "hydrateFullUser": { "title": "Hydrate Full User (follower / following / user-search)", "type": "boolean", "description": "OFF (default): follower, following, and user-search modes return X's list-endpoint user object — core identity + counts + bio, but without highlights_info / verification_info (X trims those fields on list endpoints). ON: after the list call, make a follow-up UserByScreenName request for each user in parallel to fill canHighlightTweets, verifiedSince, fuller professional data. Doubles the GraphQL call count for those three modes; use when you need Q10 fields on enumerated users. Off-by-default keeps pricing unchanged.", "default": false }, "fields": { "title": "Output Fields (sparse)", "type": "array", "description": "Optional allow-list of top-level output fields to keep on every result. Leave empty (default) to return the full object shape. Example: [\"tweetId\",\"text\",\"likeCount\",\"createdAt\",\"author\"]. Use this to shrink dataset payloads for Google Sheets / HubSpot / CSV integrations. The fields `type`, `input`, `error`, `message` are always preserved so error items are never truncated.", "items": { "type": "string" }, "default": [] }, "useCrossRunCache": { "title": "Cross-run response cache (24h TTL)", "type": "boolean", "description": "Cache parsed tweets + profiles in a named KV store for 24 hours. When the same tweet URL or username is scraped again within the TTL, the cached result is returned without hitting X — lower cost, faster, and lighter load on your proxy pool. Great for polling integrations (e.g. hourly monitoring). The cache is per-actor and keyed by tweetId / handle; it is automatically bypassed for authenticated-only fields that require fresh data.", "default": false }, "ignoreCrossRunCache": { "title": "Ignore cross-run cache (bypass hits, still write)", "type": "boolean", "description": "When useCrossRunCache is on, force a MISS on every key for this run but still write fresh values back to the cache. Useful for debugging stale output without clearing the KV store manually.", "default": false }, "dryRun": { "title": "Dry run — validate without scraping", "type": "boolean", "description": "Parse inputs, check cookies, validate the GraphQL doc IDs, and exit WITHOUT making any network calls. Emits a single `{type: 'dry-run', ...}` item summarising what would have happened. Use for pre-production smoke tests and CI validation.", "default": false }, "completionWebhookUrl": { "title": "Completion webhook URL", "type": "string", "description": "When the run finishes, POST a JSON body `{event, runId, actorId, datasetId, summary}` to this URL. Non-blocking: webhook failures are logged but never fail the run. Great for Slack/Teams/n8n notifications without polling the Apify API.", "default": "" }, "onlyIfChangedSince": { "title": "Only emit tweets/users newer than", "type": "object", "description": "Two forms: (a) {since: 'ISO 8601 date'} — drops items with createdAt ≤ cutoff; (b) {dataset: 'DATASET_ID'} — loads all tweetIds + latest createdAt from a prior dataset and filters against that; (c) both (takes the newer of the two cutoffs). Cuts cost dramatically for hourly / daily polling integrations.", "default": {} }, "inputCsv": { "title": "Bulk input CSV URL", "type": "string", "description": "Optional HTTPS URL of a CSV file; each non-empty row is routed into the matching input array based on its shape: tweet URLs → tweetURLs, profile URLs / @handles → profiles, everything else → searchQueries. Header row is auto-detected. Lets you bypass Apify's input-size limit when batching thousands of handles.", "default": "" }, "jsonLogs": { "title": "Structured JSON logs", "type": "boolean", "description": "Emit newline-delimited JSON log lines to stdout (one event per line) with fields {t, lvl, runId, actorId, build, message, ...extra}. Pipes straight into Cloudwatch / Datadog / Loki / any JSON-aware log sink. Default off — human-readable Apify text logs still appear in the console.", "default": false }, "emitPerInputLedger": { "title": "Per-input ledger in summary", "type": "boolean", "description": "When true, adds a `perInput: [{input, status, itemsEmitted, errorCategory}]` array to the run summary and to the KV store's `summary` key. Shows which of your inputs actually produced results and which failed — useful when batching 100s of handles. Capped at 500 entries to keep the summary small.", "default": false }, "onlyVerifiedUsers": { "title": "Only Verified Users", "type": "boolean", "description": "Only return tweets by verified users. Adds 'filter:verified' to search queries.", "default": false }, "onlyTwitterBlue": { "title": "Only Twitter Blue", "type": "boolean", "description": "Only return tweets by X Premium (Twitter Blue) subscribers. Adds 'filter:blue_verified' to search queries.", "default": false }, "onlyImage": { "title": "Only Images", "type": "boolean", "description": "Only return tweets with attached photos. Appends 'filter:images' to the query AND applies a client-side post-filter that drops tweets whose match was only a card thumbnail (e.g. YouTube embed previews). Strict: every returned item has at least one photo in its media array.", "default": false }, "onlyVideo": { "title": "Only Videos", "type": "boolean", "description": "Only return tweets with attached videos or GIFs. Appends 'filter:videos' to the query AND applies a client-side post-filter that drops tweets matching only via a video card (e.g. broadcast player links). Strict: every returned item has at least one video/GIF in its media array.", "default": false }, "onlyQuote": { "title": "Only Quotes", "type": "boolean", "description": "Only return tweets that are quote tweets. Adds 'filter:quote' to search queries.", "default": false }, "author": { "title": "From User", "type": "string", "description": "Only return tweets from this user. Adds 'from:' to search query. Enter handle without @.", "default": "" }, "inReplyTo": { "title": "In Reply To", "type": "string", "description": "Only return tweets that are replies to this user. Adds 'to:' to search query.", "default": "" }, "mentioning": { "title": "Mentioning User", "type": "string", "description": "Only return tweets mentioning this user. Adds '@' mention to search query.", "default": "" }, "geotaggedNear": { "title": "Geotagged Near", "type": "string", "description": "Only return tweets geotagged near this location. Example: 'San Francisco'. Adds 'near:' to search query.", "default": "" }, "withinRadius": { "title": "Within Radius", "type": "string", "description": "Maximum distance from geotagged location. Examples: '10km', '25mi'. Use with 'Geotagged Near'.", "default": "" }, "loginCookies": { "title": "Your X/Twitter cookies (REQUIRED for 7 of 12 modes)", "type": "string", "description": "Customer-supplied: paste your OWN X/Twitter cookies from a logged-in browser session. Format: 'auth_token=xxx; ct0=yyy'. Get them from DevTools → Application → Cookies → x.com — copy `auth_token` (HttpOnly) and `ct0` into a single semicolon-separated string. Multi-cookie pool supported via `|||` separator (e.g. 'auth_token=A; ct0=1|||auth_token=B; ct0=2') for hot-rotation across runs.\n\n**REQUIRED for**: x-search-scraper, x-hashtag-scraper, x-timeline-scraper, x-follower-scraper, x-following-scraper, x-comment-scraper, x-list-scraper.\n**Not needed for**: x-post-scraper, x-profile-scraper, x-data-extractor.\n\n**Important: this actor does NOT include any X/Twitter cookies for customer runs.** When a mode requires authentication, you must paste **your own** cookies into this field. There is no shared cookie pool, no built-in fallback, and no operator-side cookie injection — every authenticated run uses the cookies you provide, attributing the activity to *your* X account. (Operator daily-tests use the same `loginCookies` input field, with cookies passed by the daily-test orchestrator.)\n\nMigration note (2026-05-08): the `X_LOGIN_COOKIES` environment-variable fallback has been removed. Earlier versions of this actor would silently fall back to the env var if `loginCookies` was empty; that path is closed for the customer-vs-operator cookie boundary." }, "customMapFunction": { "title": "Custom Map Function", "type": "string", "description": "JavaScript function to transform each result. Receives the result object and should return the transformed object. Example: (item) => ({ id: item.tweetId, text: item.text, likes: item.likeCount }). Not for filtering — return the object or it won't be saved.", "default": "" }, "resumeFromDataset": { "title": "Resume From Dataset", "type": "string", "description": "Dataset ID from a previous run to skip already-scraped items. Useful for resuming failed runs without duplicates.", "default": "" }, "proxyTier": { "title": "Proxy Tier", "enum": [ "none", "residential", "custom" ], "type": "string", "description": "Choose your proxy setup. 'None' works for most requests. 'Residential (built-in)' routes all requests through Evomi residential IPs — helps avoid rate limits and account flags when using login cookies at scale. Bandwidth cost is negligible in practice (<$0.0001 per result at typical response sizes, included in pricing). 'Bring your own' lets you supply your own residential proxy URL in proxyConfiguration below (DataImpulse ~$1/GB, Evomi ~$0.49/GB). NOTE: Apify Proxy is not supported — this actor guarantees Evomi-only traffic.", "default": "residential" }, "proxyConfiguration": { "title": "Proxy Configuration (Option A — bring your own)", "type": "object", "description": "Supply your own proxy URL(s) via the 'proxyUrls' array. Used when proxyTier is 'Bring your own'. Recommended providers for residential: DataImpulse (https://dataimpulse.com, ~$1/GB) or Evomi (https://evomi.com, ~$0.49/GB). IMPORTANT: Apify Proxy is NOT supported — selecting 'Use Apify Proxy' in this picker will cause the run to fail with a clear error message. This actor is Evomi-only by policy.", "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 } } }, "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 } } } } } } } } } }