{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Search, Topics, Date Range & Real Links", "description": "Scrape Google News by keyword, topic or city. Get headline, publisher, date and the real article link. Search past dates beyond the 100 result limit. Any language and country. No API key needed.", "version": "1.0", "x-build-id": "6uQq8gvqaAV3eq0aS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pipiagent~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pipiagent-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pipiagent~google-news-scraper/runs": { "post": { "operationId": "runs-sync-pipiagent-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pipiagent~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-pipiagent-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to scrape", "enum": [ "search", "topStories", "topic", "location" ], "type": "string", "description": "Search: articles that match your keywords. Top stories: the front page of Google News. Topic: one news section such as Business. Location: local news for a city.", "default": "search" }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "Search mode only. One search per line. Google search operators work: \"exact phrase\", OR, -exclude, intitle:word.", "items": { "type": "string" } }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Maximum number of articles to save. One search without a date range returns at most about 100 articles. Add a date range to get more.", "default": 100 }, "timeRange": { "title": "Time range", "enum": [ "any", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Search mode only. Keep only articles from the last hour, day, week, month or year. Ignored when a date range is set below.", "default": "any" }, "dateFrom": { "title": "Date from", "type": "string", "description": "Search mode only. First day of the date range, for example 2026-01-01. With a date range the Actor searches week by week and day by day, so it can return many more than 100 articles." }, "dateTo": { "title": "Date to", "type": "string", "description": "Search mode only. Last day of the date range. Leave empty for today." }, "sites": { "title": "Only these publishers", "type": "array", "description": "Search mode only. Keep only articles from these websites, for example reuters.com or bbc.com. Leave empty for all publishers.", "items": { "type": "string" } }, "topic": { "title": "Topic", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SCIENCE", "SPORTS", "HEALTH" ], "type": "string", "description": "Topic mode only. The news section to scrape.", "default": "WORLD" }, "location": { "title": "Location", "type": "array", "description": "Location mode only. Cities, for example London, New York or Berlin. One place per line. Works best for large cities. Use the language and country that match the city.", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code of the Google News edition, for example en, de, fr, es, pt, ja or zh. Use a code that matches the country.", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code of the Google News edition, for example US, GB, DE, FR, BR, JP or IN.", "default": "US" }, "resolveUrls": { "title": "Get the real article links", "type": "boolean", "description": "Google News links point to Google, not to the publisher. Turn this on to add the real publisher link as \"articleUrl\". It is slower, because it needs one extra request per article. If Google limits the requests, the article is still saved, with an empty \"articleUrl\".", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. The Actor works without a proxy. Turn one on only if runs start failing with blocked requests.", "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 } } } } } } } } } }