{ "openapi": "3.0.1", "info": { "title": "Google News Scraper | Real Article URLs, Only New", "description": "Scrape Google News by keyword or topic in 50 country and language editions: headline, publisher, publication time and the real article URL instead of a Google redirect. Go past the 100-result limit with date ranges. Turn on 'Only new articles' to monitor news on a schedule.", "version": "0.1", "x-build-id": "whgffhKrwuen5nl2A" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/akatra~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-akatra-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/akatra~google-news-scraper/runs": { "post": { "operationId": "runs-sync-akatra-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/akatra~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-akatra-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 in Google News, one per line. Google search operators work: \"exact phrase\", site:reuters.com, intitle:tesla, OR, -exclude.", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Optional. Also collect the current headlines of these Google News sections for the chosen edition. Use this with or without search queries.", "items": { "type": "string", "enum": [ "TOP", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "Top stories", "World", "Nation", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "edition": { "title": "Country and language", "enum": [ "US:en", "GB:en", "CA:en", "AU:en", "IN:en", "IE:en", "NZ:en", "SG:en", "ZA:en", "PH:en", "NG:en", "DE:de", "AT:de", "CH:de", "FR:fr", "BE:fr", "CA:fr", "ES:es", "MX:es-419", "AR:es-419", "CO:es-419", "US:es-419", "IT:it", "PT:pt-150", "BR:pt-419", "NL:nl", "BE:nl", "PL:pl", "SE:sv", "NO:no", "TR:tr", "GR:el", "CZ:cs", "HU:hu", "RO:ro", "UA:uk", "RU:ru", "IL:he", "AE:ar", "SA:ar", "EG:ar", "JP:ja", "KR:ko", "TW:zh-Hant", "HK:zh-Hant", "CN:zh-Hans", "ID:id", "TH:th", "VN:vi", "IN:hi" ], "type": "string", "description": "Which Google News edition to read. It decides the language and the country the results are ranked for.", "default": "US:en" }, "maxItemsPerQuery": { "title": "Max articles per query", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many articles for each query. Google returns at most 100 per search; when you ask for more, the scraper splits the time range into single days and searches each day.", "default": 100 }, "timeRange": { "title": "Published within", "enum": [ "", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Only articles from this time window. Ignored when you set the dates below.", "default": "" }, "dateFrom": { "title": "From date", "type": "string", "description": "Optional. Only articles published on or after this date." }, "dateTo": { "title": "To date", "type": "string", "description": "Optional. Only articles published on or before this date." }, "resolveUrls": { "title": "Get the real article URL", "type": "boolean", "description": "Google News links point to a Google redirect. Keep this on to get the publisher's own article URL. Turn off for a faster run that returns the Google News link only.", "default": true }, "onlyNew": { "title": "Only new articles", "type": "boolean", "description": "The first run is your baseline. Later runs with the same query and edition return only articles published since your previous run that you have not received yet. Ideal for an hourly or daily schedule.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy is recommended. The scraper spreads requests over several IPs automatically.", "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 }, "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 } } } } } } } } } }