{ "openapi": "3.0.1", "info": { "title": "X (Twitter) Ads Transparency [$5💰] Archive Scraper", "description": "Scrape X (Twitter)'s public ad-transparency archives — commercial, US political & issue ads — into structured rows with spend, impressions, targeting, billing and agency. Filter by advertiser, keyword, date or spend. Hydrate commercial tweets into full creatives. No login. JSON, CSV or Excel.", "version": "0.0", "x-build-id": "R9ZgpDBOKUgGrB9n2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~x-ads-transparency-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-x-ads-transparency-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~x-ads-transparency-scraper/runs": { "post": { "operationId": "runs-sync-memo23-x-ads-transparency-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/memo23~x-ads-transparency-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-x-ads-transparency-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": { "sources": { "title": "Ad archives to scrape", "type": "array", "description": "One or more of: political (US Political Campaigning ads), issue (US Issue ads), commercial (commercial communications / promoted tweets). Defaults to political.", "items": { "type": "string", "enum": [ "political", "issue", "commercial" ], "enumTitles": [ "Political — US political-campaigning ads (spend + targeting + billing)", "Issue — US issue ads (spend + targeting + billing)", "Commercial — promoted-tweet archive (Dec 2023, hydratable)" ] }, "default": [ "political" ] }, "advertisers": { "title": "Advertisers", "type": "array", "description": "Filter to specific advertisers. Case-insensitive; matches the account handle AND the full account name. e.g. [\"emilyslist\", \"Cory 2020\"] for political, or [\"anemone_tar\"] for commercial. For the commercial archive, note the CSV isn't sorted by advertiser, so an advertiser filter streams the whole 1.37 GB file.", "items": { "type": "string" } }, "search": { "title": "Keyword search", "type": "string", "description": "Free-text filter. Case-insensitive; matches tweet text, account name, handle and reported/landing URLs." }, "startDate": { "title": "Start date (YYYY-MM-DD)", "type": "string", "description": "Only keep ads dated on/after this date. Commercial uses the creative's recorded date; political/issue use the earliest campaign start date." }, "endDate": { "title": "End date (YYYY-MM-DD)", "type": "string", "description": "Only keep ads dated on/before this date." }, "minSpend": { "title": "Minimum spend (USD)", "minimum": 0, "type": "integer", "description": "political/issue only: keep ads whose total spend is at least this many US dollars." }, "minImpressions": { "title": "Minimum impressions", "minimum": 0, "type": "integer", "description": "political/issue only: keep ads with at least this many total impressions." }, "hydrateTweets": { "title": "Hydrate commercial tweets (adds text, media, author, engagement)", "type": "boolean", "description": "Commercial archive only. For each ad, fetch the public tweet via X's syndication endpoint and add tweetText, mediaUrls, authorName/Handle, like/reply counts, language and creation time. Adds network calls and time; deleted/suspended tweets come back un-hydrated. No extra charge.", "default": false }, "liveCheck": { "title": "Also check for LIVE promoted tweets (usually empty)", "type": "boolean", "description": "Best-effort: resolve each advertiser in the Advertisers filter and query X's live promoted-tweets endpoint. In practice this returns nothing for essentially every advertiser (political ads are banned; the commercial live surface is empty), so it's off by default and included only for completeness.", "default": false }, "maxItems": { "title": "Maximum ad records", "minimum": 1, "type": "integer", "description": "Hard cap on output rows across all selected sources. One row = one ad (promoted tweet).", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency (hydration / live check)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests when hydrating commercial tweets or running the live check.", "default": 10 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Optional. The archives are plain public CDN files and rarely need a proxy, but hydrating many commercial tweets can benefit from a residential pool.", "default": { "useApifyProxy": 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 } } } } } } } } } }