{ "openapi": "3.0.1", "info": { "title": "News & Article Scraper: 100+ Global Sources & API", "description": "News API & Scraper: Extract articles from 100+ global sources including BBC, NYT, and Times of India. Filter by category (Tech, Crypto, Business), country, or keywords. High-speed, Python-powered data extraction for sentiment analysis, market research, and content aggregation.", "version": "0.0", "x-build-id": "zMJFshalnffaLeaNE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/complex_intricate_networks~news-article-scraper-100-global-sources-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-complex_intricate_networks-news-article-scraper-100-global-sources-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/complex_intricate_networks~news-article-scraper-100-global-sources-api/runs": { "post": { "operationId": "runs-sync-complex_intricate_networks-news-article-scraper-100-global-sources-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/complex_intricate_networks~news-article-scraper-100-global-sources-api/run-sync": { "post": { "operationId": "run-sync-complex_intricate_networks-news-article-scraper-100-global-sources-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "category": { "title": "News Category", "enum": [ "Business", "Cars", "Celebrities", "Crypto", "Culture", "Education", "Entertainment", "Fashion", "Film and TV", "Food", "Fun", "Gaming", "Health", "Home", "Lifestyle", "Music", "Politics", "Science", "Sports", "Technology", "Top news", "Top sources", "Travel", "US news", "Weather", "World news" ], "type": "string", "description": "Select the primary news category you want to fetch.", "default": "Top news" }, "countries": { "title": "Target Countries", "type": "array", "description": "Select one or multiple countries to target specific news regions.", "items": { "type": "string", "enum": [ "USA", "UK", "Canada", "Australia", "India", "Ireland", "New Zealand", "South Africa", "Singapore", "Philippines" ] }, "default": [ "USA", "India" ] }, "sources": { "title": "Select News Sites", "type": "array", "description": "Choose specific websites. If left empty, the actor will scan all available sources.", "items": { "type": "string", "enum": [ "The Times of India", "GeeksforGeeks", "Fandom", "Hindustan Times", "Economic Times", "Moneycontrol", "The Indian Express", "Mint", "The Hindu", "Investopedia", "India Today", "ESPN Cricinfo", "NDTV", "Healthline", "Forbes", "MakeUseOf", "TechTarget", "BBC World News", "Business Standard", "The Guardian World News", "News18", "Gadgets 360", "Business Today", "ABP News", "GSMArena", "The New York Times", "HowToGeek", "XDA Developers", "TechRadar", "IGN Reviews", "Nature", "SamMobile", "India.com", "Lifewire", "Screenrant", "Bloomberg", "Gadgets Now", "PCMag UK", "Tech Advisor", "CNET News", "Business Insider", "Game Rant", "Times Now", "Techspot", "India TV", "Filmibeat", "Al Jazeera", "Collider", "CNBC", "Techopedia", "CBR", "Tom's Guide", "Windows Report", "CNN", "Amar Ujala", "Prokerala", "Android Authority", "Oneindia", "Beebom", "Deccan Herald", "Anime News Network India", "WSJ World News", "Zee Business", "Variety", "Goodreturns", "CNBCTV18", "Windows Central", "Very Well Mind", "Harvard Business Review", "The New Indian Express", "Very Well Health", "Wired", "Tom's Hardware", "Washington Post World News", "Analytics India Magazine", "Cosmopolitan", "TheGamer", "Myupchar", "YourStory", "Firstpost", "Games Radar", "Scroll.in", "The Windows Club", "ThePrint", "Financial Times", "TIME", "TechCrunch", "Vogue India", "PC Gamer", "DNA India", "The Quint", "Deccan Chronicle", "Polygon", "The Hollywood Reporter", "It's FOSS", "Pocket-lint", "Pinkvilla", "Mashable", "CBS News", "Bollywood Hungama", "Digit", "Webdunia English", "Dot Esports", "Help Desk Geek", "Eurogamer", "The New Yorker", "TecMint", "Rolling Stone", "Ars Technica", "CoinDesk", "Search Engine Land", "GQ India", "Onmanorama", "Republic World", "Fextralife", "Free Press Journal", "Daily Mail India", "Vox", "Rock Paper Shotgun", "ArchDaily", "Deadline", "Billboard", "The Economist", "Make Tech Easier", "The Week", "The Atlantic", "The News Minute", "Welcome to Good Food", "Condé Nast Traveller India", "Sportstar", "Independent Asia", "ANI", "Brave Blog", "ESPN India" ] } }, "maxArticles": { "title": "Max Articles per Source", "type": "integer", "description": "The number of recent articles to pull from each selected site.", "default": 100 }, "keywordFilter": { "title": "Keyword Filter", "type": "string", "description": "Optional: Only include articles that mention these words (e.g., AI, Bitcoin). Separate by commas.", "default": "Ai, Stock, Tesla, OpenAi, Business, etc " }, "proxyConfiguration": { "title": "Proxy Settings", "type": "object", "description": "Standard proxy settings to prevent rate limiting." } } }, "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 } } } } } } } } } }