{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Headlines + Original Article URLs", "description": "Search Google News by keyword and get the public results back: headline, publishing outlet, publish time, and the publisher's own article URL resolved out of Google's redirect link at no extra charge.", "version": "0.0", "x-build-id": "ltt8RU2vHDETeNJxy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lanternlab318~google-news/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lanternlab318-google-news", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lanternlab318~google-news/runs": { "post": { "operationId": "runs-sync-lanternlab318-google-news", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lanternlab318~google-news/run-sync": { "post": { "operationId": "run-sync-lanternlab318-google-news", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "queries" ], "properties": { "queries": { "title": "Search terms", "type": "array", "description": "One Google News search term per line. Google's own search syntax works, for example quotes for an exact phrase, OR, a leading minus to exclude a word, or site:bbc.co.uk. Every term is searched separately and its results are labelled with it. An article that matches several of your terms is returned once and charged once.", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Google News interface language, as a BCP-47 tag: \"en-US\", \"zh-CN\", \"ja-JP\", \"de-DE\", \"pt-BR\", \"zh-TW\". This picks which edition of Google News is searched, so it changes which outlets appear, not just the wording.", "default": "en-US" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code of the Google News edition to search, for example \"US\", \"CN\", \"JP\", \"GB\". Pair it with a language of the same edition (\"zh-CN\" with \"CN\", \"ja-JP\" with \"JP\").", "default": "US" }, "timeRange": { "title": "Published within", "enum": [ "any", "1h", "1d", "7d", "30d" ], "type": "string", "description": "Only return articles Google published within this window. \"any\" applies no window. Shorter windows return fewer articles: a one-hour window on a quiet term can legitimately return nothing.", "default": "any" }, "maxArticlesPerQuery": { "title": "Max articles per search term", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Upper bound on the rows one search term may produce. Google News itself returns at most about 100 articles for a search term and offers no way to page past that, so a value above 100 does not reach more articles - the row count is then Google's ceiling, not this setting, and the run says so per term.", "default": 100 }, "resolvePublisherUrl": { "title": "Resolve the publisher's own article URL", "type": "boolean", "description": "Google News links point at a news.google.com redirect, not at the outlet. With this on, every article also gets publisherUrl: the outlet's own URL, resolved through two extra requests per article. It is included in the price - there is no separate charge for it. Turn it off for a much faster, lighter run that returns only the Google News link, with publisherUrl null.", "default": true }, "maxUpstreamRequests": { "title": "Max Google News requests", "minimum": 1, "type": "integer", "description": "Hard ceiling on the HTTP requests this run sends to Google News: search feeds, publisher-URL resolution and retries together. At the ceiling collection stops - the search terms not reached are written with partialReason \"upstream_request_cap\" and the run then ends normally. Leave empty and the Actor works a ceiling out from your search terms and limits, so a run is never unbounded." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "The proxy the requests to Google News go through. The default (Apify Proxy, datacenter) is the cheapest and is what this Actor is measured on; Google News serves its public search feeds over it without blocking.", "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 } } } } } } } } } }