{ "openapi": "3.0.1", "info": { "title": "Google News Scraper – Headlines, Real Article URLs & Alerts", "description": "Scrape Google News headlines by keyword, topic, location, language and country. Resolves original publisher URLs, optional og:image/description metadata, monitor mode for new articles only, dedupe. Fast HTTP-only RSS scraper, $1 per 1,000 articles. Headlines, links and metadata only.", "version": "0.1", "x-build-id": "xaG32jpvxcNgGMHpb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gazidev~google-news-scraper/runs": { "post": { "operationId": "runs-sync-gazidev-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/gazidev~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-gazidev-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 queries", "type": "array", "description": "Keywords to search on Google News, one per line. Google News operators work: \"exact phrase\", OR, -exclude, site:reuters.com, intitle:, before:/after:, when:1d.", "default": [ "artificial intelligence" ], "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Google News topic sections: WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH (one per line). You can also paste a topic ID or a news.google.com/topics/... URL.", "items": { "type": "string" } }, "locations": { "title": "Locations (local news)", "type": "array", "description": "City, region or country names for local headlines, e.g. \"Berlin\", \"Texas\".", "items": { "type": "string" } }, "includeTopStories": { "title": "Include top stories", "type": "boolean", "description": "Also scrape the edition's front-page top stories.", "default": false }, "language": { "title": "Language", "type": "string", "description": "Google News language code, e.g. en, de, fr, es, tr, ja, pt-419, zh-Hans.", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code of the edition, e.g. US, GB, DE, FR, TR, IN, JP, BR.", "default": "US" }, "timeWindow": { "title": "Time window", "enum": [ "any", "1h", "1d", "7d", "30d" ], "type": "string", "description": "Only articles published within this period (adds Google's when: operator to searches and filters all feeds by date).", "default": "any" }, "maxItemsPerQuery": { "title": "Max articles per query / feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "Google News RSS returns up to ~100 articles per feed. Use narrower queries or time windows for more coverage.", "default": 50 }, "dedupe": { "title": "Remove duplicates across queries", "type": "boolean", "description": "Skip articles already returned by another query/feed in this run (same article ID, same headline+source, or same publisher URL).", "default": true }, "resolveOriginalUrl": { "title": "Resolve original publisher URL", "type": "boolean", "description": "Decode Google News redirect links into the real article URL (best-effort; if it fails the Google News URL is kept and url_resolved=false).", "default": true }, "fetchArticleMetadata": { "title": "Fetch article metadata (og:image, description, published time)", "type": "boolean", "description": "Visit each publisher page and read its og:title, og:description, og:image and published time. Never the article text. Extra $0.002 per article where metadata is found.", "default": false }, "includeRelatedCoverage": { "title": "Include related coverage", "type": "boolean", "description": "For clustered top stories, include the related articles (title, source, link) Google groups with the headline.", "default": true }, "monitorMode": { "title": "Monitor mode (only new articles)", "type": "boolean", "description": "Only return articles not seen in previous runs. State is kept in the named key-value store 'google-news-monitor'. Ideal for scheduled runs / alerts.", "default": false }, "monitorStateKey": { "title": "Monitor state key", "type": "string", "description": "Name of this monitor. Leave empty to derive it from your queries, topics, language and country. Use different keys for independent monitors." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel HTTP requests. Lower it if URL resolution gets rate-limited.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed normally. Enable Apify datacenter proxy if Google starts rate-limiting (e.g. very large runs).", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }