{ "openapi": "3.0.1", "info": { "title": "Google News Scraper: Articles by Keyword, Topic & Country", "description": "Scrape Google News articles by keyword or topic in any of 84 regions and languages: title, publisher name and site, date, Google News link, the publisher's article URL on request, and related coverage. Time filters (1 hour to 1 year), several keywords per run, past 100 per keyword. Misses free.", "version": "0.1", "x-build-id": "B5F4cOiv9qqVg9gUY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hyperbach~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hyperbach-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hyperbach~google-news-scraper/runs": { "post": { "operationId": "runs-sync-hyperbach-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hyperbach~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-hyperbach-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Keywords", "type": "array", "description": "Search words, one search per line (`bitcoin`, `artificial intelligence`, `\"electric vehicles\" OR EV`). Google's own operators work: `site:reuters.com`, `OR`, `-word`, quotes, and `when:`, `after:YYYY-MM-DD`, `before:YYYY-MM-DD` for your own dates (then `timeframe` is not added to that line). Up to 1,000 keywords and topics a run. A line given twice gets a free `duplicate` row.", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Google News sections: `WORLD`, `NATION`, `BUSINESS`, `TECHNOLOGY`, `ENTERTAINMENT`, `SPORTS`, `SCIENCE`, `HEALTH`, `TOP_STORIES` (the front page), or a topic or section URL copied from news.google.com (`https://news.google.com/topics/…`, read in the URL's own region and language). A topic's feed is its own list (about 40-70 articles); `timeframe` does not apply to it.", "items": { "type": "string" } }, "regionLanguage": { "title": "Region and language", "enum": [ "US:en", "SK:sk", "AU:en", "BW:en", "CA:en", "ET:en", "GH:en", "IN:en", "ID:en", "IE:en", "IL:en", "KE:en", "LV:en", "MY:en", "NA:en", "NZ:en", "NG:en", "PK:en", "PH:en", "SG:en", "ZA:en", "TZ:en", "UG:en", "GB:en", "ZW:en", "ID:id", "CZ:cs", "DE:de", "AT:de", "CH:de", "AR:es-419", "CL:es-419", "CO:es-419", "CU:es-419", "ES:es", "US:es-419", "MX:es-419", "PE:es-419", "VE:es-419", "BE:fr", "CA:fr", "FR:fr", "MA:fr", "SN:fr", "CH:fr", "IT:it", "LV:lv", "LT:lt", "HU:hu", "BE:nl", "NL:nl", "NO:no", "PL:pl", "BR:pt-419", "PT:pt-150", "RO:ro", "SI:sl", "SE:sv", "VN:vi", "TR:tr", "GR:el", "BG:bg", "RU:ru", "UA:ru", "RS:sr", "UA:uk", "IL:he", "AE:ar", "SA:ar", "LB:ar", "EG:ar", "IN:mr", "IN:hi", "BD:bn", "IN:bn", "IN:ta", "IN:te", "IN:ml", "TH:th", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "JP:ja", "KR:ko" ], "type": "string", "description": "The Google News edition to read: country and language, as Google names it (`US:en` is the United States in English, `DE:de` Germany in German, `BR:pt-419` Brazil in Portuguese).", "default": "US:en" }, "timeframe": { "title": "Time frame (keywords)", "enum": [ "all", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "How recent the keywords' articles are: `all` (any time; Google's own mix, newest first), `1h`, `1d`, `7d`, `30d` or `1y` (the last hour, day, week, month, year). For hourly monitoring take `1h` on a schedule.", "default": "all" }, "maxArticles": { "title": "Max articles per keyword or topic", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop each keyword or topic at this many articles (0 = every article the feeds serve). Google's feed serves about 100 a keyword; past that the run reads one day at a time, newest day first, back to the time frame's start (`all`: until 60 empty days in a row).", "default": 100 }, "decodeUrls": { "title": "Decode the publisher's article URL", "type": "boolean", "description": "Resolve each article's Google News link to the publisher's own article URL (`url`; two more requests an article, so a run takes longer). Off: `url` stays empty and `google_news_url` leads to the article through Google. The price is the same.", "default": false }, "onlyNew": { "title": "Only new articles (memory between runs)", "type": "boolean", "description": "Remember every article delivered under this memory (stateStoreName, or a name derived from the inputs) and skip it free in the next run: a scheduled task delivers only what is new. The input row counts the skipped (skipped_seen).", "default": false }, "stateStoreName": { "title": "Memory name", "pattern": "^([a-zA-Z0-9][a-zA-Z0-9._-]{0,63})?$", "type": "string", "description": "The name of the onlyNew memory, so several tasks can share one or keep theirs apart. Empty: a name derived from the inputs.", "default": "" }, "maxItems": { "title": "Max article rows (the whole run)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop the run after this many article rows across every keyword and topic (0 = no limit). Input rows are free and not counted; a keyword or topic left unread at the cap gets a free `not_read` row.", "default": 0 } } }, "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 } } } } } } } } } }