{ "openapi": "3.0.1", "info": { "title": "Google News Scraper (Keyword, Topic, Site, Date Range)", "description": "Google News Scraper returns articles for any keyword, site: search or topic, with time-range presets, excluded words, 100+ results per query by date splitting and real publisher URLs. $0.50 per 1,000 articles.", "version": "0.1", "x-build-id": "DtXHmRKcb2yigxTld" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webdatatools~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webdatatools-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/webdatatools~google-news-scraper/runs": { "post": { "operationId": "runs-sync-webdatatools-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/webdatatools~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-webdatatools-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": "Enter Google News search terms, one row is returned per matching article. Supports Google's search operators, e.g. web scraping, \"exact phrase\", site:reuters.com AI, or -unwanted. Leave empty and use Topics below instead if you only want section feeds.", "default": [ "web scraping" ], "items": { "type": "string" } }, "topics": { "title": "Section topics", "type": "array", "description": "Enter Google News section topics to fetch instead of (or in addition to) a search, e.g. TECHNOLOGY or BUSINESS. Accepted values: WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SCIENCE, SPORTS, HEALTH. Unknown values are ignored.", "default": [], "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Enter the 2-letter interface language code Google News should use, e.g. en for English or fr for French. Combined with Country to build the hl/gl/ceid feed parameters.", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "Enter the 2-letter country/edition code, e.g. US for the United States or GB for the United Kingdom. Combined with Language to build the hl/gl/ceid feed parameters.", "default": "US" }, "sinceDays": { "title": "Only articles from the last N days", "minimum": 0, "maximum": 365, "type": "integer", "description": "Enter how many days back to search, e.g. 7 for the last week. Appends Google's when:Nd search operator to every query (topic feeds ignore this — they are always \"latest\"). Enter 0 to disable and return whatever Google's default ranking gives.", "default": 0 }, "timeRange": { "title": "Time range preset", "enum": [ "1h", "1d", "7d", "1m", "1y" ], "type": "string", "description": "Optional. Only articles from the past hour, day, week, month or year (Google's when: operator). Overrides \"last N days\" above. Topic feeds ignore it." }, "excludeWords": { "title": "Exclude words", "type": "array", "description": "Optional. Drop articles that mention these words or phrases, e.g. crypto or \"press release\" — each becomes a -word operator on every search query.", "items": { "type": "string" } }, "splitByDate": { "title": "Get more than ~100 articles per query (split by date)", "type": "boolean", "description": "A single Google News search returns at most about 100 articles. Turn this on to split each search query into date windows (after:/before:) over the time range (or last N days, else the last 30 days), dedupe across windows, and keep up to Max items per query. Needs a span of 2+ days; topic feeds are not split.", "default": false }, "maxItems": { "title": "Max articles in total", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Optional. Cap on articles for the whole run across all queries and topics (the newest are kept). Leave empty for no cap besides Max items per query and your max total charge." }, "maxItemsPerQuery": { "title": "Max items per query/topic", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Enter the maximum number of articles to keep per query or topic, e.g. 50. One Google News request returns at most about 100 articles; to get more for a search query, turn on Split by date.", "default": 100 }, "resolvePublisherUrls": { "title": "Resolve publisher URLs", "type": "boolean", "description": "Keep this on to follow each article's news.google.com redirect link and fetch the publisher's real URL (2 extra requests per article, using an undocumented Google endpoint — best-effort, see README). This is the slow part of a run (roughly 5–10 articles per second at concurrency 5): with a short run timeout the Actor stops resolving in time and still saves every article, the unresolved ones with publisherUrl null. Turn it off for a much faster run that only returns the Google News link.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Enter how many queries/topics — and, separately, how many publisher-URL resolutions — to run in parallel, e.g. 5. Raise it for large query lists or short run timeouts, lower it if Google starts responding slower or with errors.", "default": 5 } } }, "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 } } } } } } } } } }