{ "openapi": "3.0.1", "info": { "title": "Google News Scraper: Search, Topics, Any Country", "description": "Google News articles for any search, topic or section, any language and country: headline, original article URL, publisher, date, related coverage, plus description and image on request. Built to beat data_xplorer's Google News Scraper: same original URLs at half its price. From $2 per 1,000.", "version": "0.1", "x-build-id": "E1fZbQR4dafwP9tI1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyharvest~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyharvest-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidyharvest~google-news-scraper/runs": { "post": { "operationId": "runs-sync-tidyharvest-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/tidyharvest~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-tidyharvest-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": "One search per line, exactly as you would type it into Google News. Operators work: \"exact phrase\", OR, -exclude, site:reuters.com, intitle:earnings. Each query returns up to ~100 articles (more with a date range below).", "default": [ "artificial intelligence" ], "items": { "type": "string" } }, "topics": { "title": "Topic sections", "type": "array", "description": "Optional: also pull Google News topic sections (or Top stories) for the chosen language and country.", "items": { "type": "string", "enum": [ "TOP_STORIES", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SCIENCE", "SPORTS", "HEALTH" ], "enumTitles": [ "Top stories", "World", "Nation (your country)", "Business", "Technology", "Entertainment", "Science", "Sports", "Health" ] } }, "topicUrls": { "title": "Custom topic or section links", "type": "array", "description": "Optional: any Google News topic or section page link copied from your browser (e.g. a sub-topic like Artificial intelligence, a city, a team or a company page).", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Google News interface language code, e.g. en-US, en-GB, de, fr, es-419, ja, pt-BR.", "default": "en-US" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country edition, e.g. US, GB, IN, DE, FR, JP, BR.", "default": "US" }, "timeframe": { "title": "Published within", "enum": [ "any", "1h", "6h", "12h", "1d", "2d", "7d", "14d", "30d", "1y" ], "type": "string", "description": "Only articles from the last hour/day/week etc. Applies to search queries. Ignored when a date range is set.", "default": "any" }, "dateFrom": { "title": "From date", "type": "string", "description": "Optional start date (YYYY-MM-DD). With a date range each query is split into day-sized windows, so you can collect far more than 100 articles per query (one feed request per window, up to 60 windows)." }, "dateTo": { "title": "To date", "type": "string", "description": "Optional end date (YYYY-MM-DD, inclusive). Defaults to today when only a start date is set." }, "maxItemsPerQuery": { "title": "Max articles per query", "minimum": 0, "maximum": 6000, "type": "integer", "description": "Cap per query or topic. 0 = no per-query cap.", "default": 100 }, "maxItems": { "title": "Max articles in total", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Hard cap on results for the whole run (also caps your cost). Duplicates across queries are removed before counting.", "default": 50 }, "decodeUrls": { "title": "Original article URLs", "type": "boolean", "description": "Return each article's real publisher URL in `url` and `publisherUrl` instead of a Google News redirect link. On by default; turn off for the fastest runs.", "default": true }, "extractDetails": { "title": "Article description and image", "type": "boolean", "description": "Also read each article's own page for its description (summary) and main image (`description`, `imageUrl`). Slower; some publishers refuse automated visits, and those rows keep null.", "default": 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 } } } } } } } } } }