{ "openapi": "3.0.1", "info": { "title": "📰 Extract Google News Articles — AI & RAG Ready", "description": "Extract Google News articles by keyword, topic, or URL with full-text extraction for AI/RAG pipelines. Get headlines, sources, snippets, images, authors, and clean article text in structured JSON. Export scraped data, run the scraper via API, or integrate with other tools.", "version": "1.0", "x-build-id": "vCCbrXUaKwela4j3o" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/muhammadafzal~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-muhammadafzal-google-news-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/muhammadafzal~google-news-scraper/runs": { "post": { "operationId": "runs-sync-muhammadafzal-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/muhammadafzal~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-muhammadafzal-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search Queries", "type": "array", "description": "List of keyword searches to run on Google News. Supports Google search operators: use OR for multiple terms, minus sign to exclude words, quotes for exact match, site: to filter by source. Use this field when the user wants to find news about a topic, brand, person, or event. Do NOT use this when the user provides a direct URL — use startUrls instead.", "default": [ "technology" ], "items": { "type": "string" } }, "topics": { "title": "News Topics", "type": "array", "description": "Select Google News topic pages to browse. Use this when the user wants to browse top headlines by category, not search for a specific keyword.", "items": { "type": "string", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "🌍 World", "🏛️ Nation", "💼 Business", "💻 Technology", "🎬 Entertainment", "⚽ Sports", "🔬 Science", "🏥 Health" ] }, "default": [] }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Direct Google News URLs to scrape. Use this field when the user provides a specific Google News URL. Do NOT use this when the user describes a topic or wants to search by keyword — use searchQueries or topics instead.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of news articles to extract per search query or topic. Each article counts as one result for billing. Lower values complete faster.", "default": 50 }, "country": { "title": "Country", "enum": [ "US", "GB", "CA", "AU", "IN", "DE", "FR", "JP", "BR", "IT", "ES", "MX", "KR", "RU", "CN", "SA", "AE", "ZA", "NG", "AR", "NL", "PL", "TR", "SE", "NO" ], "type": "string", "description": "Country code for localized Google News results. Affects which regional edition of Google News is scraped.", "default": "US" }, "language": { "title": "Language", "enum": [ "en", "es", "fr", "de", "pt", "it", "ja", "ko", "zh-CN", "ar", "hi", "ru", "nl", "pl", "tr", "sv", "no" ], "type": "string", "description": "Language code for Google News results. Affects the interface language and may affect which articles are shown.", "default": "en" }, "timePeriod": { "title": "Time Period", "enum": [ "1h", "1d", "7d", "30d", "1y", "all" ], "type": "string", "description": "Filter news articles by publication date. Only applies to keyword searches — topic pages show their own curated results.", "default": "1d" }, "extractFullText": { "title": "Extract Full Article Text", "type": "boolean", "description": "Visit each article URL and extract the full text content. Essential for AI/RAG pipelines and sentiment analysis. Increases runtime and cost per result. When disabled, returns headline, snippet, source, and metadata only.", "default": false }, "decodeUrls": { "title": "Decode Google News URLs", "type": "boolean", "description": "Resolve Google News redirect URLs to the original article URLs. When enabled, each article URL is decoded to show the real publisher link instead of the Google redirect. Recommended for most use cases.", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Select proxy to use for scraping. Datacenter proxies work well for Google News RSS feeds. Switch to residential proxies if you encounter blocks.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }