{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Keywords, Topics, 20+ Countries", "description": "Google News scraper for keywords, topics and top stories in 20+ countries. Export headlines, publishers and dates as JSON/CSV, with optional real article URLs, full text, Bing News and only-new mode for alerts. For media monitoring, PR tracking and news datasets.", "version": "0.1", "x-build-id": "cIiBfjNsodVNorQ1X" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bachiembmt~google-news-rss-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bachiembmt-google-news-rss-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bachiembmt~google-news-rss-scraper/runs": { "post": { "operationId": "runs-sync-bachiembmt-google-news-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bachiembmt~google-news-rss-scraper/run-sync": { "post": { "operationId": "run-sync-bachiembmt-google-news-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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. Google operators work: site:reuters.com, \"exact phrase\", intitle:, OR. Leave empty if you only want topics / top stories.", "default": [ "artificial intelligence" ], "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Optional topic feeds: TOP_STORIES, WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH.", "items": { "type": "string" } }, "countries": { "title": "Countries", "type": "array", "description": "Two-letter codes: us, gb, ca, au, in, ie, nz, sg, za, de, fr, es, it, br, mx, ar, jp, kr, vn, id, th, ph, tr. Each query is fetched once per country.", "default": [ "us" ], "items": { "type": "string" } }, "timeRange": { "title": "Time range", "enum": [ "any", "1h", "1d", "7d", "30d" ], "type": "string", "description": "Only articles published within this window (applied via Google's when: operator for keyword queries).", "default": "7d" }, "maxArticlesPerQuery": { "title": "Max articles per query and country", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Google RSS returns at most ~100 items per request. Use splitByDay for more.", "default": 30 }, "splitByDay": { "title": "Split by day", "type": "boolean", "description": "One request per day (after:/before:) over the time range (30 days when 'any') to get well over 100 articles per query. Keyword queries only.", "default": false }, "decodeUrls": { "title": "Decode original article URLs", "type": "boolean", "description": "Resolve news.google.com links to the publisher URL (2 extra throttled requests per article, ~1.5 s each).", "default": false }, "dedupe": { "title": "Remove duplicates", "type": "boolean", "description": "Skip articles already returned earlier in this run: same URL, or near-identical title (also across queries, countries and engines).", "default": true }, "sources": { "title": "Sources", "type": "array", "description": "News engines to query: google (default) and/or bing. Bing returns ~10-15 items per query and has no topic feeds.", "default": [ "google" ], "items": { "type": "string" } }, "extractContent": { "title": "Extract article content", "type": "boolean", "description": "Fetch each article page and extract main text, author, image and language into 'content' etc. Implies URL decoding for Google results. Slow (~2-4 s per article); paywalled pages are skipped. Extra charge per extracted article.", "default": false }, "onlyNew": { "title": "Only new articles", "type": "boolean", "description": "Skip articles already returned by earlier runs for the same query and country (state kept in the named key-value store 'google-news-seen').", "default": 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 } } } } } } } } } }