{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Articles by Keyword, Real URLs", "description": "Google News API alternative, no API key. Scrape Google News RSS feeds and export articles to CSV/JSON with real publisher URLs across 50+ countries.", "version": "1.0", "x-build-id": "aaWuobdrSKW9tAYwx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~google-news-scraper/runs": { "post": { "operationId": "runs-sync-logiover-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search keywords / topics to monitor", "type": "array", "description": "List of search queries. Each query becomes a separate Google News RSS feed. Supports Google's search operators: \"exact phrase\" for exact match, OR for boolean OR (default is AND between words), -word to exclude, site:domain.com to filter by source, intitle:word to match in title only.\n\nLeave empty if using 'topic' or 'geoLocation' mode instead.", "default": [ "openai", "claude ai" ], "items": { "type": "string" } }, "topic": { "title": "Topic category (optional, instead of queries)", "enum": [ "", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "type": "string", "description": "Browse top stories by topic instead of searching keywords. Use this OR queries, not both. Returns curated top headlines from Google News in that category.", "default": "" }, "geoLocation": { "title": "Location-based news (optional)", "type": "string", "description": "Get news for a specific city, state, or region instead of search/topic. Use city or country name in English (e.g. 'New York', 'London', 'Berlin', 'Tokyo'). Leave empty if using queries or topic.", "default": "" }, "topHeadlines": { "title": "Or get top headlines (overrides everything)", "type": "boolean", "description": "If true, fetches the main Google News top headlines feed for the selected language/country and ignores queries/topic/geoLocation. Useful for daily news digests.", "default": false }, "language": { "title": "Language", "enum": [ "en-US", "en-GB", "en-CA", "en-AU", "en-IN", "fr", "de", "es", "es-419", "it", "pt-BR", "pt-PT", "nl", "pl", "sv", "da", "fi", "no", "cs", "sk", "hu", "ro", "el", "ru", "uk", "tr", "ar", "he", "fa", "hi", "bn", "id", "ms", "th", "vi", "ja", "ko", "zh-CN", "zh-TW" ], "type": "string", "description": "Google News interface language (hl parameter). Determines the language of the returned headlines. Leave on the default (English US) for the broadest coverage.", "default": "en-US" }, "country": { "title": "Country / region", "enum": [ "US", "GB", "CA", "AU", "IN", "IE", "NZ", "ZA", "SG", "PH", "NG", "FR", "DE", "ES", "IT", "NL", "BE", "PT", "PL", "SE", "DK", "FI", "NO", "AT", "CH", "CZ", "SK", "HU", "RO", "GR", "UA", "RU", "TR", "BR", "MX", "AR", "CL", "CO", "PE", "JP", "KR", "CN", "TW", "HK", "ID", "MY", "TH", "VN", "SA", "AE", "EG", "IL" ], "type": "string", "description": "Geographic region for news (gl parameter). Google News tailors story selection to this region. Leave on the default (United States) for broad global coverage.", "default": "US" }, "maxArticles": { "title": "Max articles per query/feed", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum articles to return per query (or per topic/geo feed). Google News RSS caps at ~100 per single feed; if set higher than 100, the actor automatically stitches multiple time-windowed feeds (when:1h, when:1d, when:7d, when:30d) and deduplicates to deliver more results.", "default": 100 }, "timeWindow": { "title": "Time window", "enum": [ "", "1h", "12h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Restrict results to a recent time window using Google's 'when:' operator. Ignored when maxArticles > 100 (the actor stitches multiple windows automatically in that case).", "default": "" }, "fromDate": { "title": "From date (ISO 8601, optional)", "type": "string", "description": "Filter out articles published BEFORE this date. Format: YYYY-MM-DD or full ISO (2026-05-01T00:00:00Z). Applied post-fetch on the publication date in the RSS feed.", "default": "" }, "toDate": { "title": "To date (ISO 8601, optional)", "type": "string", "description": "Filter out articles published AFTER this date. Format: YYYY-MM-DD or full ISO. Applied post-fetch.", "default": "" }, "includeSources": { "title": "Include only these sources (optional)", "type": "array", "description": "Whitelist of publisher domains. If set, only articles from these sources are returned. Example: ['reuters.com', 'bloomberg.com', 'ft.com']. Matched against the source URL host.", "default": [], "items": { "type": "string" } }, "excludeSources": { "title": "Exclude these sources (optional)", "type": "array", "description": "Blacklist of publisher domains. Articles from these sources are filtered out. Example: ['clickbait.com', 'spam-news.net'].", "default": [], "items": { "type": "string" } }, "resolveUrls": { "title": "Resolve final article URLs (recommended)", "type": "boolean", "description": "Google News links go through a redirect (news.google.com/articles/CBMi...). When enabled, the actor follows the redirect once per article via a fast HEAD request and returns the canonical publisher URL. Adds ~50ms per article but gives clean URLs for downstream use (CRM, content extraction, SEO analysis).", "default": true }, "extractThumbnails": { "title": "Extract thumbnail images", "type": "boolean", "description": "Include the thumbnail image URL from each article's media:content tag when available. No extra cost.", "default": true }, "proxyConfiguration": { "title": "Proxy (optional, usually not needed)", "type": "object", "description": "Google News RSS rarely rate-limits, so most users don't need a proxy. If your account hits rate limits with very high volumes, enable Apify Proxy here.", "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 } } } } } } } } } }