{ "openapi": "3.0.1", "info": { "title": "Google News Scraper — Real URLs, Full Text & Monitoring", "description": "Scrape Google News by keyword or topic. Real publisher URLs, past the 100-result limit, only-new mode for scheduled monitoring, optional full article text. Plain HTTP, pay only for saved articles.", "version": "0.1", "x-build-id": "8hVz9YRW2vpmvqF1Z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/studioploski~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-studioploski-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/studioploski~google-news-scraper/runs": { "post": { "operationId": "runs-sync-studioploski-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/studioploski~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-studioploski-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or Google News operators (when:1d, after:YYYY-MM-DD, site:example.com, …).", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Optional Google News topic feeds (in addition to queries).", "items": { "type": "string", "enum": [ "TOP_STORIES", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "Top stories", "World", "Nation", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "language": { "title": "Language (hl)", "type": "string", "description": "Google News language, e.g. en-US, fr, de, ja.", "default": "en-US" }, "country": { "title": "Country (gl)", "type": "string", "description": "Two-letter country/region code, e.g. US, CA, GB.", "default": "US" }, "timeRange": { "title": "Time range", "enum": [ "any", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Appended as when: for queries that do not already set when:/after:/before:. Ignored when dateFrom/dateTo are set.", "default": "7d" }, "dateFrom": { "title": "From date", "type": "string", "description": "YYYY-MM-DD. Overrides timeRange when set (with dateTo)." }, "dateTo": { "title": "To date", "type": "string", "description": "YYYY-MM-DD. Overrides timeRange when set (with dateFrom)." }, "maxArticlesPerQuery": { "title": "Max articles per query/topic", "minimum": 1, "maximum": 5000, "type": "integer", "description": "When over 100 (or a date range is given and a feed is full), the window is sliced by day to go past Google's ~100-item RSS cap.", "default": 100 }, "decodeUrls": { "title": "Decode real publisher URLs", "type": "boolean", "description": "Resolve news.google.com article links to the real publisher URL.", "default": true }, "fetchFullText": { "title": "Fetch full article text", "type": "boolean", "description": "GET the publisher page and extract article body (JSON-LD or
/

), author and image.", "default": false }, "onlyNew": { "title": "Only new articles", "type": "boolean", "description": "Skip article IDs already seen under monitorKey (for scheduled monitoring runs).", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Named seen-ID set in the google-news-monitor key-value store (sanitized).", "default": "default" }, "requestTimeoutSecs": { "title": "Per-request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for each HTTP response before retrying.", "default": 30 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Each retry uses a fresh session/IP when a proxy is set.", "default": {} } } }, "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 } } } } } } } } } }