{ "openapi": "3.0.1", "info": { "title": "Google News Scraper: Full-Text Articles to Markdown", "description": "Find Google News articles by keyword or topic and return each full article as clean Markdown plus RAG-ready chunks.", "version": "1.0", "x-build-id": "m9sc57W89zKc5YAPa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sunburst077~google-news-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sunburst077-google-news-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sunburst077~google-news-to-markdown/runs": { "post": { "operationId": "runs-sync-sunburst077-google-news-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sunburst077~google-news-to-markdown/run-sync": { "post": { "operationId": "run-sync-sunburst077-google-news-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Keywords / queries", "type": "array", "description": "Search Google News the same way you would in the search box. Operators such as OR, quotes, minus, site:, and intitle: work. Each query is fetched as its own RSS search.", "default": [ "NASA" ], "items": { "type": "string" } }, "topics": { "title": "Topic feeds", "type": "array", "description": "Built-in Google News sections. These are standalone feeds, not combined with your keywords. Date filters are applied after download because topic RSS cannot take when:.", "items": { "type": "string", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "World", "Nation", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] }, "default": [] }, "topicUrls": { "title": "Custom topic / section URLs", "type": "array", "description": "Paste a Google News topic or section URL from your browser (news.google.com/topics/... or .../sections/...). Converted to the public RSS feed automatically.", "default": [], "items": { "type": "string" } }, "topicsHashed": { "title": "Hashed topic IDs", "type": "array", "description": "Topic hashes from a Google News URL, e.g. CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB or TOPIC/sections/SECTION.", "default": [], "items": { "type": "string" } }, "locale": { "title": "Language and region", "enum": [ "US:en", "GB:en", "CA:en", "AU:en", "IN:en", "IE:en", "NZ:en", "ZA:en", "SG:en", "PH:en", "US:es", "MX:es", "ES:es", "AR:es", "CO:es", "CL:es", "DE:de", "AT:de", "CH:de", "FR:fr", "CA:fr", "BE:fr", "CH:fr", "IT:it", "PT:pt", "BR:pt", "NL:nl", "BE:nl", "JP:ja", "KR:ko", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "RU:ru", "PL:pl", "CZ:cs", "SK:sk", "HU:hu", "SE:sv", "NO:no", "DK:da", "FI:fi", "TR:tr", "GR:el", "RO:ro", "BG:bg", "HR:hr", "UA:uk", "ID:id", "TH:th", "VN:vi", "MY:ms", "IL:he", "AE:ar", "SA:ar", "EG:ar" ], "type": "string", "description": "Google News edition as country:language (ceid). Sets hl, gl, and ceid together.", "default": "US:en" }, "language": { "title": "hl override", "type": "string", "description": "Optional Google News hl (e.g. en-US). Leave empty to derive it from the locale." }, "country": { "title": "gl override", "type": "string", "description": "Optional Google News gl / country code (e.g. US). Leave empty to derive it from the locale." }, "timeWindow": { "title": "Time window", "enum": [ "1h", "1d", "7d", "30d", "1y", "all" ], "type": "string", "description": "Added to keyword searches as when:1d / when:7d / …. Ignored when After / Before dates are set. Topic feeds are filtered client-side.", "default": "7d" }, "dateAfter": { "title": "Published after", "type": "string", "description": "YYYY-MM-DD. Added as after: on keyword searches. Also filters topic results." }, "dateBefore": { "title": "Published before", "type": "string", "description": "YYYY-MM-DD. Added as before: on keyword searches. Also filters topic results." }, "maxArticlesPerQuery": { "title": "Max articles per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Cap per keyword or topic feed. Google News search RSS returns at most ~100 items.", "default": 8 }, "maxArticles": { "title": "Max articles (all queries)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Optional global cap after de-duplication. Leave empty to keep every per-query result." }, "deduplicate": { "title": "De-duplicate across queries", "type": "boolean", "description": "Drop the same Google News item (and the same resolved publisher URL) when it appears in more than one query.", "default": true }, "extractFullText": { "title": "Extract full article text", "type": "boolean", "description": "Fetch the publisher page and convert the main article to Markdown. Turn off for metadata-only runs (cheaper, faster).", "default": true }, "createChunks": { "title": "Create RAG chunks", "type": "boolean", "description": "Split Markdown into heading-aware chunks: text, source, section, chunkIndex, startChar, endChar.", "default": true }, "headingAware": { "title": "Heading-aware chunks", "type": "boolean", "description": "Split on Markdown headings and keep the heading path in section. Disable for a plain sliding window.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target maximum characters per chunk. About 4 characters per token.", "default": 1600 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "Characters repeated from the previous chunk when a section is split.", "default": 160 }, "minFullTextChars": { "title": "Minimum full-text characters", "minimum": 40, "maximum": 20000, "type": "integer", "description": "Shorter extractions are treated as paywalled or empty (status metadata_only, no full-text charge).", "default": 240 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 16, "type": "integer", "description": "Parallel HTTP requests. Keep this modest to stay polite to publishers.", "default": 4 }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Global polite pause. Hosts get a slightly longer gap.", "default": 250 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for each HTTP request before giving up.", "default": 25 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 8, "type": "integer", "description": "Retries for timeouts and 429 / 5xx responses.", "default": 3 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Off by default — most publisher pages and Google News RSS work without a proxy. Turn on Apify Proxy only if you see blocks.", "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 }, "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 } } } } } } } } } }