{ "openapi": "3.0.1", "info": { "title": "Google News Scraper — Decoded Article URLs, Any Edition", "description": "Scrape Google News search, topic and top-stories feeds into rows: headline, publisher, publish date, related coverage — and the REAL article URL, decoded out of Google's redirector instead of the useless news.google.com link. 100+ editions. No API key.", "version": "0.1", "x-build-id": "ysDAxWwE8WTqccMcX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapersdelight~google-news-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapersdelight~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Keywords to search Google News for — one feed per query, up to ~100 articles each. Google News search operators work here: `\"exact phrase\"`, `tesla OR rivian`, `intitle:layoffs`, `site:reuters.com`. Leave every input empty and the actor returns Google News top stories instead.", "default": [], "items": { "type": "string" } }, "sections": { "title": "Sections", "type": "array", "description": "Google News' own front-page sections. `TOP` is the main top-stories feed; the rest are the standard topic sections. These are broad, always-populated feeds — good for a daily news sweep with no keyword.", "items": { "type": "string", "enum": [ "TOP", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ] }, "default": [] }, "newsUrls": { "title": "Google News URLs", "type": "array", "description": "Paste any news.google.com URL straight from your browser — a search page, a `/topics/` page, a `/headlines/section/...` page, the home page, or an existing `/rss/...` feed. Each is converted to its RSS feed automatically.", "default": [], "items": { "type": "string" } }, "language": { "title": "Language (hl)", "type": "string", "description": "Google News interface/content language, e.g. `en-US`, `en-GB`, `fr`, `de`, `es`, `pt-BR`, `ja`. Combined with each country below to select the edition.", "default": "en-US" }, "countries": { "title": "Countries (gl)", "type": "array", "description": "Two-letter country codes for the Google News editions to read, e.g. `US`, `GB`, `IN`, `CA`, `AU`, `DE`, `FR`, `BR`, `JP`. Every query and section is run once per country, which is how you get past the ~100-article cap on a single feed.", "default": [ "US" ], "items": { "type": "string" } }, "when": { "title": "Time window", "enum": [ "any", "1h", "12h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Restrict search queries to articles published inside this window (Google's own `when:` operator). Applies to `queries` only — sections and pasted URLs are always Google's current feed. Note `1h` can legitimately return only a handful of articles.", "default": "any" }, "includeSites": { "title": "Only these publishers", "type": "array", "description": "Restrict search queries to these publisher domains, e.g. `reuters.com`, `bbc.co.uk`. Multiple domains are OR-ed together. Applies to `queries` only.", "default": [], "items": { "type": "string" } }, "excludeSites": { "title": "Exclude these publishers", "type": "array", "description": "Drop these publisher domains from search queries, e.g. `yahoo.com`. Useful for stripping syndication mirrors out of a media-monitoring feed. Applies to `queries` only.", "default": [], "items": { "type": "string" } }, "decodeArticleUrls": { "title": "Decode real article URLs", "type": "boolean", "description": "Resolve each `news.google.com/rss/articles/CBMi...` redirector into the publisher's own URL (e.g. `https://www.reuters.com/...`). This is what makes the rows usable for anything downstream — link checking, full-text fetching, dedupe by domain. Included in the per-article price; switch it off only if you want the fastest possible run and do not need the links.", "default": true }, "includeRelatedArticles": { "title": "Include related coverage", "type": "boolean", "description": "On Google's cluster feeds (top stories, sections, topics) each story carries a list of other outlets covering the same event. Ship that list with the row as `relatedArticles`. Search feeds rarely carry one.", "default": true }, "maxItems": { "title": "Max articles", "minimum": 0, "type": "integer", "description": "Stop after this many articles across all feeds. The default is deliberately small so a first run is cheap — raise it once you know the scope you want. 0 = no limit.", "default": 200 }, "maxItemsPerFeed": { "title": "Max articles per feed", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap each individual feed. Google News RSS itself returns at most ~100 articles per feed and has no page parameter, so values above 100 have no effect.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Google News RSS served Apify's egress without a proxy in testing, so the default is no proxy. Turn on Apify Proxy (RESIDENTIAL) if you run at high volume, need a specific country's edition served from that country, or start seeing blocked-request warnings in the log.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }