{ "openapi": "3.0.1", "info": { "title": "CNN Article Scraper", "description": "Extract CNN articles by category or search query with date filtering. Scrape news from politics, business, world, tech, sports, and more. Get structured data: title, author, publication date, full content. Perfect for media monitoring, research, and content analysis.", "version": "1.0", "x-build-id": "ccbp3ZIsa4PYPFfuZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/filip_cicvarek~cnn-article-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-filip_cicvarek-cnn-article-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/filip_cicvarek~cnn-article-scraper/runs": { "post": { "operationId": "runs-sync-filip_cicvarek-cnn-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/filip_cicvarek~cnn-article-scraper/run-sync": { "post": { "operationId": "run-sync-filip_cicvarek-cnn-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "category", "startDate", "endDate", "categoryMode" ], "properties": { "category": { "title": "News Category", "enum": [ "world", "politics", "business", "health", "entertainment", "sports", "tech", "travel", "style", "opinion" ], "type": "string", "description": "Select the CNN news category to scrape" }, "searchQuery": { "title": "Search Query", "maxLength": 200, "type": "string", "description": "When provided, the actor will search CNN for this query and scrape matching articles within the date range and selected category." }, "startDate": { "title": "Start Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Start date for the publication time window (YYYY-MM-DD format)" }, "endDate": { "title": "End Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "End date for the publication time window (YYYY-MM-DD format)" }, "maxArticles": { "title": "Maximum Articles", "minimum": 0, "type": "integer", "description": "Maximum number of articles to scrape (set to 0 for no limit; runtime may increase)" }, "concurrency": { "title": "Concurrency Level", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of concurrent requests (higher = faster but more resource intensive)", "default": 5 }, "categoryMode": { "title": "Category Coverage Mode", "enum": [ "auto", "latest", "archive" ], "type": "string", "description": "Choose how deep to scan category pages. 'latest' only scrapes the landing page, 'archive' uses CNN's monthly sitemaps for the full range (slower), and 'auto' picks based on your date window." }, "archiveMonthLimit": { "title": "Archive Month Limit", "minimum": 1, "maximum": 120, "type": "integer", "description": "Maximum number of monthly CNN archive files to load when archive mode runs. Increase for long date ranges, but expect longer runtimes.", "default": 12 } } }, "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 } } } } } } } } } }