{ "openapi": "3.0.1", "info": { "title": "X/Twitter Intelligence Scraper Pro", "description": "Scrape public X/Twitter posts and profiles from search terms, handles, tweet URLs, and lists. Export clean tweet, author, media, engagement, and monitoring data for research, marketing, and social listening.", "version": "1.0", "x-build-id": "Fd6xWeIbeN1xvE5E4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/qaseemiqbal~x-twitter-intelligence-scraper-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-qaseemiqbal-x-twitter-intelligence-scraper-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/qaseemiqbal~x-twitter-intelligence-scraper-pro/runs": { "post": { "operationId": "runs-sync-qaseemiqbal-x-twitter-intelligence-scraper-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/qaseemiqbal~x-twitter-intelligence-scraper-pro/run-sync": { "post": { "operationId": "run-sync-qaseemiqbal-x-twitter-intelligence-scraper-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "scrapeMode": { "title": "Scrape mode", "enum": [ "auto", "search", "profiles", "urls", "lists", "tweetDetails", "conversation", "monitoring", "userDiscovery" ], "type": "string", "description": "How the Actor routes the input.", "default": "auto" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Raw X/Twitter search queries.", "items": { "type": "string" } }, "twitterHandles": { "title": "Twitter/X handles", "type": "array", "description": "Profile handles to scrape.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Tweet, profile, list, or search URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "title": "URL", "description": "X/Twitter tweet, profile, list, or search URL.", "type": "string" } } } }, "tweetIds": { "title": "Tweet IDs", "type": "array", "description": "Tweet/status IDs to enrich.", "items": { "type": "string" } }, "userIds": { "title": "User IDs", "type": "array", "description": "Public numeric user IDs for future user-based routing.", "items": { "type": "string" } }, "queryWizard": { "title": "Query Wizard", "type": "object", "description": "Structured fields converted into X/Twitter search syntax." }, "sort": { "title": "Sort", "enum": [ "latest", "top", "latest_and_top", "auto_fallback" ], "type": "string", "description": "Result ordering strategy for search requests.", "default": "latest" }, "maxItems": { "title": "Maximum items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of records to plan and push for the run.", "default": 100 }, "maxItemsPerQuery": { "title": "Maximum items per query", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of records to collect for each query, URL, handle, or list.", "default": 100 }, "maxItemsPerProfile": { "title": "Maximum items per profile", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of records to collect for each profile timeline.", "default": 100 }, "filters": { "title": "Post-processing filters", "type": "object", "description": "Filters applied after extraction, such as language, engagement, media, and verification filters." }, "profileMode": { "title": "Profile mode", "enum": [ "tweets", "tweets_and_replies", "media", "likes_if_public", "profile_only" ], "type": "string", "description": "Which public profile timeline view to scrape for handles and profile URLs.", "default": "tweets" }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Include reply posts where the selected mode supports replies.", "default": false }, "includeRetweets": { "title": "Include retweets", "type": "boolean", "description": "Include retweets where they are visible and supported by the selected mode.", "default": false }, "includePinnedTweet": { "title": "Include pinned tweet", "type": "boolean", "description": "Include a profile's pinned tweet when it is present and visible.", "default": true }, "conversationOptions": { "title": "Conversation options", "type": "object", "description": "Controls for replies, parent context, quoted tweets, reply limits, and reply depth." }, "conversationOutputMode": { "title": "Conversation output mode", "enum": [ "flat", "nested" ], "type": "string", "description": "Whether conversation records are emitted as flat rows or nested conversation data.", "default": "flat" }, "dateSplitStrategy": { "title": "Date split strategy", "enum": [ "none", "daily", "weekly", "monthly", "auto" ], "type": "string", "description": "How date ranges are split into smaller search windows.", "default": "none" }, "maxDaysPerWindow": { "title": "Maximum days per window", "minimum": 1, "maximum": 366, "type": "integer", "description": "Maximum number of days in each generated date window.", "default": 7 }, "authorDetailLevel": { "title": "Author detail level", "enum": [ "minimal", "standard", "full" ], "type": "string", "description": "Amount of author profile metadata to include in tweet records.", "default": "standard" }, "includeMedia": { "title": "Include media metadata", "type": "boolean", "description": "Include media metadata such as media URLs, previews, dimensions, and alt text when available.", "default": true }, "downloadMedia": { "title": "Download media", "type": "boolean", "description": "Download media files into key-value storage. This increases runtime and storage cost.", "default": false }, "mediaDownloadMode": { "title": "Media download mode", "enum": [ "metadata_only", "download_images", "download_videos", "download_all" ], "type": "string", "description": "Which media types to download when media downloading is enabled.", "default": "metadata_only" }, "flattenOutput": { "title": "Flatten output", "type": "boolean", "description": "Flatten selected nested output fields for easier CSV and spreadsheet exports.", "default": false }, "outputFields": { "title": "Output fields", "type": "array", "description": "Optional list of fields to keep in the final output records.", "items": { "type": "string" } }, "includeRawData": { "title": "Include raw data", "type": "boolean", "description": "Include raw extracted page data in output records. This increases dataset size.", "default": false }, "cleanText": { "title": "Clean text", "type": "boolean", "description": "Normalize whitespace in tweet text and store it as cleanText.", "default": true }, "includeRagFields": { "title": "Include RAG fields", "type": "boolean", "description": "Add AI/RAG-friendly content and metadata fields to tweet records.", "default": false }, "deduplicateBy": { "title": "Deduplicate by", "enum": [ "none", "tweetId", "url", "contentHash" ], "type": "string", "description": "Field or strategy used to detect duplicate tweet records.", "default": "tweetId" }, "deduplicateScope": { "title": "Deduplicate scope", "enum": [ "run", "query", "persistent" ], "type": "string", "description": "Whether deduplication applies within the run, per query, or across monitoring runs.", "default": "run" }, "monitoring": { "title": "Monitoring options", "type": "object", "description": "Stateful monitoring settings for repeated scheduled runs." }, "crawlStrategy": { "title": "Crawl strategy", "enum": [ "http_only", "http_first", "browser_only" ], "type": "string", "description": "Use HTTP-only for the lowest cost. Browser modes cost more but may recover data from pages that need JavaScript.", "default": "http_only" }, "browserFallbackOnEmpty": { "title": "Use browser fallback on empty HTTP pages", "type": "boolean", "description": "Only applies to HTTP first mode. Enabling this increases compute cost.", "default": false }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of requests to process at the same time.", "default": 1 }, "minConcurrency": { "title": "Minimum concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Minimum crawler concurrency for browser-based runs.", "default": 1 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Number of retry attempts for failed requests.", "default": 0 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum time to spend on a single request before treating it as failed.", "default": 20 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration for requests and browser fallback.", "default": { "useApifyProxy": true } }, "customMapFunction": { "title": "Custom map function", "type": "string", "description": "Advanced JavaScript function body receiving record and helpers." }, "allowCustomFilter": { "title": "Allow custom function to filter", "type": "boolean", "description": "Allow customMapFunction to remove records by returning null.", "default": false }, "externalWebhookUrl": { "title": "External webhook URL", "type": "string", "description": "Optional endpoint that receives pushed output records as JSON." }, "debugMode": { "title": "Debug mode", "type": "boolean", "description": "Enable extra logging and diagnostic output.", "default": false }, "saveHtmlSnapshots": { "title": "Save HTML snapshots", "type": "boolean", "description": "Save HTML snapshots for debugging. This increases storage usage.", "default": false }, "saveFailedPages": { "title": "Save failed pages", "type": "boolean", "description": "Save failed pages for troubleshooting. This increases storage usage.", "default": false } } }, "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 } } } } } } } } } }