{ "openapi": "3.0.1", "info": { "title": "Google News Scraper ยท Real URLs, Full Text, Any Edition", "description": "Google News scraper with the real publisher URL on every article, optional full article text (charged only when extracted), keyword searches with Google operators, topic sections, several country editions per run, since-last-run checkpoint. $1 per 1,000 articles; first 25 each month free.", "version": "1.0", "x-build-id": "QUTc0UdIise7L7pUS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/agentsgearbox~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-agentsgearbox-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/agentsgearbox~google-news-scraper/runs": { "post": { "operationId": "runs-sync-agentsgearbox-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/agentsgearbox~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-agentsgearbox-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 on Google News. Supports Google operators such as `\"exact phrase\"`, `site:reuters.com`, `-word`, `intitle:`. One feed per query (max 100 articles each).", "items": { "type": "string" } }, "topics": { "title": "Topic headlines", "type": "array", "description": "Optional Google News topic sections to scrape in addition to the 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" ] }, "default": [] }, "feedUrls": { "title": "Custom Google News RSS URLs", "type": "array", "description": "Optional. Any `news.google.com/rss/...` URL, for example a publication feed or a geo feed.", "default": [], "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Google News language code, e.g. `en`, `en-GB`, `de`, `it`, `es`, `fr`, `pt-BR`.", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "Google News edition country code, e.g. `US`, `GB`, `DE`, `IT`, `IN`.", "default": "US" }, "editions": { "title": "Additional editions", "type": "array", "description": "Optional list of extra country editions as `COUNTRY:language`, for example `GB:en`, `DE:de`, `IT:it`, `BR:pt-BR`. Every query and topic is fetched once per edition (the main `country`/`language` pair plus these).", "default": [], "items": { "type": "string" } }, "publishedWithin": { "title": "Published within", "type": "string", "description": "Only articles newer than this (applied by Google). Examples: `1h`, `12h`, `1d`, `7d`, `30d`. Leave empty for no limit." }, "onlyNewSinceLastRun": { "title": "Only new articles since the last run (checkpoint)", "type": "boolean", "description": "For hourly monitoring. Remembers the newest publication time per query or topic in a named key-value store and skips everything older on the next run, so you pay only for new articles.", "default": false }, "checkpointStoreName": { "title": "Checkpoint store name", "type": "string", "description": "Key-value store that keeps the per-feed checkpoints (created automatically in your account). Use different names to run independent monitors.", "default": "google-news-state" }, "maxItemsPerFeed": { "title": "Max articles per query / topic", "minimum": 1, "maximum": 100, "type": "integer", "description": "Google News returns at most 100 articles per feed.", "default": 50 }, "decodeUrls": { "title": "Decode publisher URLs", "type": "boolean", "description": "Resolve Google's redirect links to the real article URL (`url`). Recommended. Costs one extra request per article.", "default": true }, "fetchArticleText": { "title": "Fetch full article text", "type": "boolean", "description": "Download each article and extract its readable text (`articleText`, `articleHtml`, `author`, `image`). Requires decoded URLs. Paywalled sites return a partial text.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy is recommended for large runs with article text, because publisher sites often block datacenter IPs." } } }, "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 } } } } } } } } } }