{ "openapi": "3.0.1", "info": { "title": "Google News Scraper & Google News API with Full Article Text", "description": "Google News scraper and news API for news and media monitoring. Search by keyword or topic in any country/language edition, filter by date and split by day to go past Google's ~100-result limit. Get real publisher URLs and optional full article text. $1 per 1,000 articles, $3 with full text.", "version": "0.1", "x-build-id": "HWcbs7vyPIFw9XN6e" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/magenta_waterwheel~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-magenta_waterwheel-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/magenta_waterwheel~google-news-scraper/runs": { "post": { "operationId": "runs-sync-magenta_waterwheel-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/magenta_waterwheel~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-magenta_waterwheel-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": "Google News search phrases, one per line. Supports Google operators like site:reuters.com or \"exact phrase\".", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Optional topic sections instead of (or with) queries: TOP, WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH.", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Interface language (hl), e.g. en, en-GB, de, es, fr, pt-BR.", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "Edition country as ISO-2 (gl), e.g. US, GB, DE, BR, IN.", "default": "US" }, "timeRange": { "title": "Time range", "enum": [ "1h", "12h", "1d", "7d", "30d", "1y", "any" ], "type": "string", "description": "Relative window Google News understands. Ignored when dateFrom/dateTo are set.", "default": "7d" }, "dateFrom": { "title": "From date (YYYY-MM-DD)", "type": "string", "description": "Optional absolute start day (UTC). Uses Google's after: operator. Prefer this over timeRange for calendar windows." }, "dateTo": { "title": "To date (YYYY-MM-DD)", "type": "string", "description": "Optional absolute end day (UTC). Uses Google's before: operator." }, "maxArticlesPerQuery": { "title": "Max articles per query / topic", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Cap per search or topic. Google News RSS returns about 100 headlines per feed page; for longer ranges turn on Split by day.", "default": 100 }, "splitByDay": { "title": "Split date range by day", "type": "boolean", "description": "When dateFrom/dateTo are set (or the cap is over 100), fetch one RSS page per day so you can go deeper than a single feed page. More Google requests.", "default": false }, "decodeUrls": { "title": "Decode publisher URLs", "type": "boolean", "description": "Resolve each Google News link to the real publisher URL. Turn off only if you just need titles.", "default": true }, "includeFullText": { "title": "Include full article text", "type": "boolean", "description": "Fetch each publisher page and extract readable text (Mozilla Readability). Frame the text as for your own analysis; many sites block bots.", "default": false }, "includeRelated": { "title": "Include related stories", "type": "boolean", "description": "Keep the related headlines Google News lists under each story.", "default": true }, "requestDelayMs": { "title": "Delay between Google requests (ms)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Polite spacing for Google News RSS and URL decoding. Raise this if you hit HTTP 429.", "default": 300 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel page fetches for URL decoding and full-text extraction.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Left empty, the Actor uses the Apify datacenter IP and switches to Apify Proxy automatically on Google HTTP 429/403.", "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 } } } } } } } } } }