{ "openapi": "3.0.1", "info": { "title": "Google News Scraper & API: Real Publisher URLs", "description": "Google News past the 100-result cap, with the publisher's real link instead of Google's redirect, and coverage grouped into stories. Any keyword, topic or country. No login. $1.50 per 1,000 articles, less on paid plans. For brand monitoring, PR and AI agents.", "version": "0.1", "x-build-id": "RWT1MKnkcEJX2QeKA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brainfoods_studio~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brainfoods_studio-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/brainfoods_studio~google-news-scraper/runs": { "post": { "operationId": "runs-sync-brainfoods_studio-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/brainfoods_studio~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-brainfoods_studio-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", "maxItems": 50, "type": "array", "description": "News searches, up to 50. Google search operators work, for example \"exact phrase\", site:bbc.com or OR. Each query is one source in the results.", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Google News topic feeds to fetch: WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH.", "items": { "type": "string", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "World", "Nation", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "includeTopStories": { "title": "Include top stories", "type": "boolean", "description": "Also fetch the Google News top stories feed for the chosen country and language.", "default": false }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code that sets the Google News edition, for example US, GB or IN.", "default": "US" }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code, for example en, de or fr.", "default": "en" }, "timeRange": { "title": "Time range", "enum": [ "any", "1h", "1d", "7d", "1y" ], "type": "string", "description": "How far back to search. Applies to search queries only; topics and top stories are always current. Ignored when Date from and Date to are set.", "default": "7d" }, "dateFrom": { "title": "Date from", "type": "string", "description": "First day to include, as YYYY-MM-DD. Give both Date from and Date to, or neither. Replaces the time range." }, "dateTo": { "title": "Date to", "type": "string", "description": "Last day to include, as YYYY-MM-DD. It cannot be in the future." }, "splitByDay": { "title": "Split by day", "type": "boolean", "description": "Run one search per day between Date from and Date to (at most 366 days). Google returns at most 100 articles per search, so this gets past that limit.", "default": false }, "maxArticlesPerQuery": { "title": "Max articles per query", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop collecting articles for a query, topic or top stories once this many are found. Charged per article.", "default": 100 }, "resolvePublisherUrls": { "title": "Resolve publisher URLs", "type": "boolean", "description": "Look up the real publisher link of each article instead of only the Google News link. Charged as a separate, higher-priced event for each article that is resolved.", "default": false }, "clusterStories": { "title": "Stories: group articles into stories (premium)", "type": "boolean", "description": "Groups articles about the same story across outlets. Adds one story row per story of 2 or more articles, with who published first, how many outlets covered it and how fast it spread. Charged per story row.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "Parallel requests, 1 to 8. The default of 2 is the safest; higher is faster but more likely to be rate-limited by Google.", "default": 2 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy is strongly recommended. Datacenter is tried first; residential is used automatically after repeated 429s if your plan has it.", "default": { "useApifyProxy": true } }, "monitorKey": { "title": "Monitor: remember results as", "type": "string", "description": "Turns on monitor mode. Results are remembered under this name, and later runs with the same name return only what is new. Use one name per schedule." }, "deliveryWebhookUrl": { "title": "Monitor: send new results to", "type": "string", "description": "Optional. A Slack incoming-webhook URL or any HTTPS endpoint. When a monitored run finds something new, it posts a short alert with a link to the results. Charged as one alert per run that sends one. Stored encrypted and hidden from logs, because a webhook URL works like a password." } } }, "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 } } } } } } } } } }