{ "openapi": "3.0.1", "info": { "title": "Google News Scraper — Headlines by Keyword, Topic, Country", "description": "Google News for AI agents and monitoring: keyword search with site:/when: operators, topic feeds (World, Business, Technology, Science, Health...), local news by city, top stories in 85 verified country/language editions. Title, source, time, Google link, optional real publisher URL.", "version": "0.1", "x-build-id": "6KnMSPoGxP4ilzVJY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~google-news-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-google-news-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~google-news-search/runs": { "post": { "operationId": "runs-sync-yadroo-google-news-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~google-news-search/run-sync": { "post": { "operationId": "run-sync-yadroo-google-news-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "auto", "search", "topic", "geo", "topStories" ], "type": "string", "description": "Which Google News feed to read. `auto` picks `topic` when a topic is set, else `geo` when locations are set, else `search` when queries are set, else `topStories`.", "default": "auto" }, "queries": { "title": "Search queries", "type": "array", "description": "One feed per query (mode `search`). Google operators work inside a query: quotes for exact phrase, `OR`, `-word`, `site:domain.com`, `when:7d`, `intitle:`. Each query returns up to 100 articles.", "items": { "type": "string" } }, "topic": { "title": "Topic feed", "enum": [ "", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SCIENCE", "SPORTS", "HEALTH" ], "type": "string", "description": "Google News section feed for the chosen edition (mode `topic`). Ignores queries.", "default": "" }, "locations": { "title": "Locations (local news)", "type": "array", "description": "City / region names for Google's local-news feed (mode `geo`), e.g. `Almaty`, `Berlin`, `Texas`. One feed per location; use the edition language for best results.", "items": { "type": "string" } }, "edition": { "title": "Edition (country:language)", "enum": [ "", "US:en", "US:es-419", "GB:en", "IE:en", "CA:en", "CA:fr", "AU:en", "NZ:en", "IN:en", "IN:hi", "IN:bn", "IN:ta", "IN:te", "IN:ml", "IN:mr", "IN:gu", "IN:pa", "PK:en", "BD:bn", "SG:en", "MY:en", "PH:en", "ID:id", "TH:th", "VN:vi", "JP:ja", "KR:ko", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "IL:en", "IL:he", "TR:tr", "GR:el", "SA:ar", "AE:ar", "EG:ar", "LB:ar", "ZA:en", "NG:en", "KE:en", "GH:en", "TZ:en", "UG:en", "ZW:en", "BW:en", "NA:en", "ET:en", "MA:fr", "SN:fr", "DE:de", "AT:de", "CH:de", "CH:fr", "FR:fr", "BE:fr", "BE:nl", "NL:nl", "IT:it", "ES:es", "PT:pt-150", "BR:pt-419", "MX:es-419", "AR:es-419", "CL:es-419", "CO:es-419", "PE:es-419", "VE:es-419", "CU:es-419", "RU:ru", "UA:uk", "UA:ru", "PL:pl", "CZ:cs", "SK:sk", "HU:hu", "RO:ro", "BG:bg", "RS:sr", "SI:sl", "LT:lt", "LV:lv", "EE:et", "FI:fi", "SE:sv", "NO:no" ], "type": "string", "description": "Verified Google News edition. Overrides `country` and `lang` when set.", "default": "" }, "country": { "title": "Country code (gl)", "type": "string", "description": "ISO-3166 alpha-2 country, e.g. `US`, `DE`, `KZ`. Used when `edition` is empty.", "default": "US" }, "lang": { "title": "Language (hl)", "type": "string", "description": "Language code, e.g. `en`, `de`, `ru`, `es-419`, `zh-Hans`. Used when `edition` is empty.", "default": "en" }, "sinceHours": { "title": "Only articles from the last N hours", "minimum": 0, "maximum": 8760, "type": "integer", "description": "Client-side filter on publish time; in `search` mode it is also sent to Google as a `when:` operator so the 100-item window is spent on fresh news. 0 = no time filter.", "default": 168 }, "useWhenOperator": { "title": "Send sinceHours to Google as when: operator", "type": "boolean", "description": "Search mode only. Turn off to filter purely on the client (Google then returns its default relevance window).", "default": true }, "sites": { "title": "Only these sites", "type": "array", "description": "Search mode: restrict to publisher domains, e.g. `reuters.com`, `bloomberg.com` (joined with OR). Works without queries too — then you get the site's latest indexed articles.", "items": { "type": "string" } }, "excludeSites": { "title": "Exclude sites", "type": "array", "description": "Search mode: publisher domains to drop via `-site:`.", "items": { "type": "string" } }, "includeKeywords": { "title": "Title/snippet must contain any of", "type": "array", "description": "Case-insensitive client-side filter applied to title + snippet (useful with topic/geo feeds that have no query).", "items": { "type": "string" } }, "excludeKeywords": { "title": "Drop items containing any of", "type": "array", "description": "Case-insensitive client-side exclusion on title + snippet.", "items": { "type": "string" } }, "limit": { "title": "Max items per feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "Google RSS returns at most 100 items per feed.", "default": 50 }, "maxItems": { "title": "Max items per run (all feeds)", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on dataset rows for the run — protects cost when many queries are given.", "default": 500 }, "sort": { "title": "Sort within a feed", "enum": [ "newest", "oldest", "feed" ], "type": "string", "description": "Order used before the per-feed limit is applied.", "default": "newest" }, "dedupe": { "title": "Deduplicate by title", "type": "boolean", "description": "Skip repeated stories across all feeds of the run (normalized title or identical Google id).", "default": true }, "decodeUrls": { "title": "Resolve real publisher URLs", "type": "boolean", "description": "Google links point to news.google.com redirects. Turn on to resolve the publisher URL into `articleUrl` (2 extra requests per article, about 1 s each). The actor first checks news.google.com/robots.txt and does not call Google's resolver where it is disallowed — as of 2026-10-02 it disallows both paths the resolver needs (/rss/articles/ and /_/), so `articleUrl` stays null except for the rare links that embed the publisher URL. Resolving also stops for the rest of the run at the first refusal from Google (HTTP 403/429) or after 3 failures in a row; articles are always saved, and the status says why `articleUrl` is null.", "default": false }, "maxDecode": { "title": "Max URLs to try resolving per run", "minimum": 0, "maximum": 200, "type": "integer", "description": "Most articles to resolve over the network per run (each try counts, resolved or not). Articles beyond it keep `articleUrl: null`. Links that already contain the publisher URL are resolved without a request and do not count.", "default": 20 }, "includeSnippet": { "title": "Include snippet", "type": "boolean", "description": "Google feeds carry little beyond the headline; the snippet is what remains after stripping title and source (often empty).", "default": true }, "fields": { "title": "Output fields", "type": "array", "description": "Keep only these fields, in this order, e.g. [\"publishedAt\", \"source\", \"title\", \"url\"]. `id` is always kept (first unless you place it). Field names: id, feed, feedType, title, source, sourceUrl, url, articleUrl, publishedAt, snippet, edition, effectiveEdition, country, lang, feedUrl, fetchedAt. Letter case, spaces, snake_case and the RSS names link / pubDate / guid / description / publisher are understood; an unknown name is left out and named in the status. Empty = every field.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }