{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Real Publisher URLs, Not Redirects", "description": "Google News links are useless redirects, so this resolves the real publisher URL on every result. Get title, publisher, source URL, date and snippet, plus full text and AI summary on demand. $3.00 per 1,000 articles with no run-start fee - only articles returned are charged.", "version": "0.1", "x-build-id": "zmfy6MXnzf7DFw6kN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dami_studio~google-news-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-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/dami_studio~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-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": { "query": { "title": "Search query", "type": "string", "description": "Keywords to search Google News for (e.g. \"electric vehicles\", or advanced: \"tesla OR rivian site:reuters.com\"). Leave empty if using a Topic instead." }, "topic": { "title": "Topic (instead of a query)", "enum": [ "", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "type": "string", "description": "Use a Google News topic feed instead of a search query.", "default": "" }, "freshness": { "title": "Freshness", "enum": [ "", "1h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Only return articles newer than this (applied to query searches).", "default": "" }, "language": { "title": "Language (hl)", "type": "string", "description": "Interface/article language code, e.g. en-US, en-GB, fr, de, es-419.", "default": "en-US" }, "country": { "title": "Country (gl)", "type": "string", "description": "Edition country code, e.g. US, GB, CA, DE, FR, IN.", "default": "US" }, "maxItems": { "title": "Max articles", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of articles to return (Google News feeds cap around 100 per query).", "default": 50 }, "resolveUrls": { "title": "Resolve real publisher URLs", "type": "boolean", "description": "Decode Google's redirect links into the actual article URL (e.g. reuters.com/...). Best-effort; falls back to the Google link with urlResolved=false if a link can't be decoded. Check urlResolved per row to know whether url is the real publisher link or the Google redirect.", "default": true }, "fetchArticleText": { "title": "Fetch full article text", "type": "boolean", "description": "Download each resolved article and extract its main body text. Slower; requires Resolve URLs. Some sites block scraping or have no extractable body — those rows come back with articleText=null and are flagged ok:false and NOT charged, so you only pay for articles whose text was actually fetched.", "default": false }, "aiSummary": { "title": "AI summary + sentiment", "type": "boolean", "description": "Generate a 1-2 sentence summary and a sentiment label per article using OpenAI. Needs an OpenAI API key. Best-effort: if the OpenAI call fails for an article, the aiSummary and sentiment fields are simply omitted/null for that row (the article itself is still returned).", "default": false }, "openaiApiKey": { "title": "OpenAI API key (for AI summary)", "type": "string", "description": "Only needed when AI summary is on. Kept private." }, "notionConnector": { "title": "Notion connector (optional)", "type": "string", "description": "Optional. Write each article as a page into your Notion when the run finishes. Authorize a Notion connector once in Settings → API & Integrations → MCP connectors, then pick it here. Leave empty to skip (default) — results are always saved to the dataset regardless." }, "notionParentId": { "title": "Notion target data source ID", "type": "string", "description": "Optional. The Notion data source ID of the database to write into (only used if a Notion connector is set). Leave empty to create the pages privately in your workspace instead." }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "OPTIONAL. Google News RSS is a public, no-auth API with no anti-bot, so no proxy is needed and the default routes traffic directly (saving proxy credits). Only enable Apify Proxy if you hit IP rate limits when running very high volumes.", "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 } } } } } } } } } }