{ "openapi": "3.0.1", "info": { "title": "Google News Scraper (Pay Per Event)", "description": "Scrape Google News in real time, including images and descriptions. This tool extracts complete structured data: high-resolution visuals, full, titles, sources, dates, and direct URLs.", "version": "2.4", "x-build-id": "eDAG4OAdtkZfr4VxT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data_xplorer~google-news-scraper-fast/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data_xplorer-google-news-scraper-fast", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/data_xplorer~google-news-scraper-fast/runs": { "post": { "operationId": "runs-sync-data_xplorer-google-news-scraper-fast", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/data_xplorer~google-news-scraper-fast/run-sync": { "post": { "operationId": "run-sync-data_xplorer-google-news-scraper-fast", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Search Keywords", "minItems": 0, "maxItems": 50, "uniqueItems": true, "type": "array", "description": "List of keywords to search for. You can use Google News search operators:\n- Use '-' to exclude words (e.g. 'bitcoin -ethereum')\n- Use 'site:' to filter by specific website (e.g. 'bitcoin site:cnn.com')\n- Use 'OR' to search for multiple terms (e.g. 'bitcoin OR ethereum')\n- Use quotes for exact match (e.g. '\"bitcoin price\"')", "default": [], "items": { "type": "string" } }, "topics": { "title": "News Topics", "type": "array", "description": "Select one or more predefined Google News topics to scrape.", "items": { "type": "string", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "🌍 World", "🏛️ Nation", "💼 Business", "💻 Technology", "🎬 Entertainment", "⚽ Sports", "🔬 Science", "🏥 Health" ] }, "default": [] }, "topicUrls": { "title": "Custom Topic / Section URLs", "minItems": 0, "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Provide custom Google News topic or section URLs to scrape. Useful for niche topics not in the predefined list.\nExample: https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx1YlY4U0FtVnVHZ0pWVXlnQVAB", "default": [], "items": { "type": "string" } }, "maxArticles": { "title": "Maximum News", "minimum": 0, "type": "integer", "description": "Maximum number of news to extract per keyword or topic (0 = no limit)", "default": 20 }, "timeframe": { "title": "Time Period (Only for keywords)", "enum": [ "1h", "1d", "7d", "30d", "1y", "all" ], "type": "string", "description": "Time period for the news search. Note: this filter applies mainly to keyword searches. Topic pages return their own curated results.", "default": "1h" }, "region_language": { "title": "Region and Language", "enum": [ "US:en", "SK:sk", "AU:en", "BW:en", "CA:en", "ET:en", "GH:en", "IN:en", "ID:en", "IE:en", "IL:en", "KE:en", "LV:en", "MY:en", "NA:en", "NZ:en", "NG:en", "PK:en", "PH:en", "SG:en", "ZA:en", "TZ:en", "UG:en", "GB:en", "ZW:en", "ID:id", "CZ:cs", "DE:de", "AT:de", "CH:de", "AR:es-419", "CL:es-419", "CO:es-419", "CU:es-419", "ES:es", "US:es-419", "MX:es-419", "PE:es-419", "VE:es-419", "BE:fr", "CA:fr", "FR:fr", "MA:fr", "SN:fr", "CH:fr", "IT:it", "LV:lv", "LT:lt", "HU:hu", "BE:nl", "NL:nl", "NO:no", "PL:pl", "BR:pt-419", "PT:pt-150", "RO:ro", "SI:sl", "SE:sv", "VN:vi", "TR:tr", "GR:el", "BG:bg", "RU:ru", "UA:ru", "RS:sr", "UA:uk", "IL:he", "AE:ar", "SA:ar", "LB:ar", "EG:ar", "IN:mr", "IN:hi", "BD:bn", "IN:bn", "IN:ta", "IN:te", "IN:ml", "TH:th", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "JP:ja", "KR:ko" ], "type": "string", "description": "Region and language for news search", "default": "US:en" }, "decodeUrls": { "title": "Decode Google News URLs", "type": "boolean", "description": "If enabled, decodes Google News URLs to get the original article URLs. Note: This will significantly slow down the scraping process as each URL needs to be decoded individually.", "default": false }, "extractDescriptions": { "title": "Extract Article Descriptions", "type": "boolean", "description": "If enabled, extracts the meta description from each article page. Note: This will significantly slow down the scraping process.", "default": false }, "extractImages": { "title": "Extract Article Images", "type": "boolean", "description": "Fetches the og:image from each article page when no image is available (mainly for RSS/topic results). When this option is not explicitly set, images are extracted by default. Toggle OFF to skip image extraction and speed up scraping.", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure Apify Proxy. Residential proxies recommended for best results.", "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 } } } } } } } } } }