{ "openapi": "3.0.1", "info": { "title": "Google News Scraper", "description": "Scrape Google News articles by search, topic, place or URL in 82 editions (70 countries): title, publisher, date, related coverage, original URL and full text. More than 100 articles per search. Export to JSON, CSV or Excel.", "version": "0.0", "x-build-id": "y7byxvlqKelu13X4w" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nice_dev~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nice_dev-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nice_dev~google-news-scraper/runs": { "post": { "operationId": "runs-sync-nice_dev-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nice_dev~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-nice_dev-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Google News URLs", "maxItems": 1000, "type": "array", "description": "news.google.com pages or RSS feeds, as copied from the browser: a search (`https://news.google.com/search?q=tesla`), a topic or section, a local news page, a **Full coverage** story, a publisher page or any news.google.com RSS feed. The country / language of the URL (`hl`, `gl`, `ceid`) is kept. Added to the searches, topics and places below. Max 1 000 URLs.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "query": { "title": "Search query", "maxLength": 500, "type": "string", "description": "What to search, exactly as on Google News. Search operators work: `\"exact phrase\"`, `OR`, `-word`, `site:reuters.com`, `intitle:word` (e.g. `artificial intelligence -crypto`)." }, "searchQueries": { "title": "More search queries", "maxItems": 100, "uniqueItems": true, "type": "array", "description": "Several searches in one run (one search per query and per edition below). Added to **Search query**; an article found by several searches is saved once.", "default": [], "items": { "type": "string" } }, "topics": { "title": "Topics", "uniqueItems": true, "type": "array", "description": "Google News sections to read for each edition: top stories, world, business, technology… (about 40 articles for the front page, 60-75 for the other sections, per edition; most with their related coverage).", "items": { "type": "string", "enum": [ "TOP", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "Top stories (front page)", "World", "Nation (the edition's country)", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] }, "default": [] }, "location": { "title": "Local news for a place", "maxLength": 200, "type": "string", "description": "City whose local news to read (Google News **Local** section, e.g. `Paris`, `New York`, `Munich`), or a country in its own edition (`Germany` with `DE:de`). Google News has no local news for a region or a state (`Bavaria`, `Texas`: 0 articles). Read once per edition; not combined with the search queries." }, "locations": { "title": "More places", "maxItems": 100, "uniqueItems": true, "type": "array", "description": "Several places in one run: local news of each place. Added to **Local news for a place**.", "default": [], "items": { "type": "string" } }, "regionLanguage": { "title": "Country and language (edition)", "enum": [ "US:en", "GB:en", "CA:en", "CA:fr", "AU:en", "NZ:en", "IE:en", "IN:en", "IN:hi", "IN:bn", "IN:mr", "IN:ta", "IN:te", "IN:ml", "SG:en", "MY:en", "PH:en", "PK:en", "NG:en", "ZA:en", "KE:en", "GH:en", "UG:en", "TZ:en", "ZW:en", "ET:en", "NA:en", "BW:en", "IL:en", "IL:he", "LB:ar", "EG:ar", "SA:ar", "AE:ar", "MA:fr", "SN:fr", "FR:fr", "BE:fr", "BE:nl", "CH:fr", "CH:de", "DE:de", "AT:de", "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", "US:es-419", "PL:pl", "CZ:cs", "SK:sk", "HU:hu", "RO:ro", "BG:bg", "GR:el", "RS:sr", "SI:sl", "LT:lt", "LV:lv", "UA:uk", "UA:ru", "RU:ru", "SE:sv", "NO:no", "FI:fi", "TR:tr", "JP:ja", "KR:ko", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "TH:th", "VN:vi", "ID:id" ], "type": "string", "description": "Google News edition used for the searches, topics and places: it decides the country and the language of the articles.", "default": "US:en" }, "regionLanguages": { "title": "More editions", "uniqueItems": true, "type": "array", "description": "Run every search, topic and place in several editions at once (e.g. the same query in France, Germany and Japan). Added to **Country and language**. A run reads at most 1 000 searches: each search, topic or place counts once per edition, each start URL once.", "items": { "type": "string", "enum": [ "US:en", "GB:en", "CA:en", "CA:fr", "AU:en", "NZ:en", "IE:en", "IN:en", "IN:hi", "IN:bn", "IN:mr", "IN:ta", "IN:te", "IN:ml", "SG:en", "MY:en", "PH:en", "PK:en", "NG:en", "ZA:en", "KE:en", "GH:en", "UG:en", "TZ:en", "ZW:en", "ET:en", "NA:en", "BW:en", "IL:en", "IL:he", "LB:ar", "EG:ar", "SA:ar", "AE:ar", "MA:fr", "SN:fr", "FR:fr", "BE:fr", "BE:nl", "CH:fr", "CH:de", "DE:de", "AT:de", "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", "US:es-419", "PL:pl", "CZ:cs", "SK:sk", "HU:hu", "RO:ro", "BG:bg", "GR:el", "RS:sr", "SI:sl", "LT:lt", "LV:lv", "UA:uk", "UA:ru", "RU:ru", "SE:sv", "NO:no", "FI:fi", "TR:tr", "JP:ja", "KR:ko", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "TH:th", "VN:vi", "ID:id" ], "enumTitles": [ "United States (English) — US:en", "United Kingdom (English) — GB:en", "Canada (English) — CA:en", "Canada (French) — CA:fr", "Australia (English) — AU:en", "New Zealand (English) — NZ:en", "Ireland (English) — IE:en", "India (English) — IN:en", "India (Hindi) — IN:hi", "India (Bengali) — IN:bn", "India (Marathi) — IN:mr", "India (Tamil) — IN:ta", "India (Telugu) — IN:te", "India (Malayalam) — IN:ml", "Singapore (English) — SG:en", "Malaysia (English) — MY:en", "Philippines (English) — PH:en", "Pakistan (English) — PK:en", "Nigeria (English) — NG:en", "South Africa (English) — ZA:en", "Kenya (English) — KE:en", "Ghana (English) — GH:en", "Uganda (English) — UG:en", "Tanzania (English) — TZ:en", "Zimbabwe (English) — ZW:en", "Ethiopia (English) — ET:en", "Namibia (English) — NA:en", "Botswana (English) — BW:en", "Israel (English) — IL:en", "Israel (Hebrew) — IL:he", "Lebanon (Arabic) — LB:ar", "Egypt (Arabic) — EG:ar", "Saudi Arabia (Arabic) — SA:ar", "United Arab Emirates (Arabic) — AE:ar", "Morocco (French) — MA:fr", "Senegal (French) — SN:fr", "France (French) — FR:fr", "Belgium (French) — BE:fr", "Belgium (Dutch) — BE:nl", "Switzerland (French) — CH:fr", "Switzerland (German) — CH:de", "Germany (German) — DE:de", "Austria (German) — AT:de", "Netherlands (Dutch) — NL:nl", "Italy (Italian) — IT:it", "Spain (Spanish) — ES:es", "Portugal (Portuguese) — PT:pt-150", "Brazil (Portuguese) — BR:pt-419", "Mexico (Spanish) — MX:es-419", "Argentina (Spanish) — AR:es-419", "Chile (Spanish) — CL:es-419", "Colombia (Spanish) — CO:es-419", "Peru (Spanish) — PE:es-419", "Venezuela (Spanish) — VE:es-419", "Cuba (Spanish) — CU:es-419", "United States (Spanish) — US:es-419", "Poland (Polish) — PL:pl", "Czechia (Czech) — CZ:cs", "Slovakia (Slovak) — SK:sk", "Hungary (Hungarian) — HU:hu", "Romania (Romanian) — RO:ro", "Bulgaria (Bulgarian) — BG:bg", "Greece (Greek) — GR:el", "Serbia (Serbian) — RS:sr", "Slovenia (Slovenian) — SI:sl", "Lithuania (Lithuanian) — LT:lt", "Latvia (Latvian) — LV:lv", "Ukraine (Ukrainian) — UA:uk", "Ukraine (Russian) — UA:ru", "Russia (Russian) — RU:ru", "Sweden (Swedish) — SE:sv", "Norway (Norwegian) — NO:no", "Finland (Finnish) — FI:fi", "Turkey (Turkish) — TR:tr", "Japan (Japanese) — JP:ja", "South Korea (Korean) — KR:ko", "China (Simplified Chinese) — CN:zh-Hans", "Taiwan (Traditional Chinese) — TW:zh-Hant", "Hong Kong (Traditional Chinese) — HK:zh-Hant", "Thailand (Thai) — TH:th", "Vietnam (Vietnamese) — VN:vi", "Indonesia (Indonesian) — ID:id" ] }, "default": [] }, "maxItems": { "title": "Max articles", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum number of articles to save for the whole run (after deduplication and filters). 0 = no limit.", "default": 100 }, "maxItemsPerQuery": { "title": "Max articles per search", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Cap for EACH search, topic, place or URL (per edition), so that the first one cannot use up the whole **Max articles** budget. 0 = no per-search cap.", "default": 0 }, "fetchBeyond100": { "title": "Get more than 100 articles per search", "type": "boolean", "description": "Google News returns at most 100 articles per search. When a search reaches 100, the Actor splits its date range into smaller periods (down to one day) and reads each one, so a search can return thousands of articles. The range is **Posted after** → **Posted before**, or the last **Look-back days** when they are empty. No effect on topics and places.", "default": true }, "lookbackDays": { "title": "Look-back days (more than 100)", "minimum": 1, "maximum": 3650, "type": "integer", "description": "How far back to split a search that reaches 100 articles, when **Posted after** is empty: that many days before **Posted before**, or before the run's start. Up to 3 650 days (10 years).", "default": 30 }, "sortBy": { "title": "Order of the articles", "enum": [ "relevance", "date" ], "type": "string", "description": "Order of the articles of each search, topic or place: as ranked by Google News (relevance), or newest first.", "default": "relevance" }, "resolveUrls": { "title": "Original article URL (publisher link)", "type": "boolean", "description": "Replace the Google News redirect link by the real article URL on the publisher's site (`articleUrl`), resolved through Google News itself. Charged per article resolved (see Pricing).", "default": false }, "extractDetails": { "title": "Full article text, image and author", "type": "boolean", "description": "Open each article on the publisher's site and add its full text, word count, reading time, main image, author(s), summary, keywords, section and last-update date. Includes the original article URL. Some publishers refuse robots or show a paywall: the article is then saved without these fields and this option is not charged for it.", "default": false }, "includeRelatedArticles": { "title": "Related coverage", "type": "boolean", "description": "Add the other articles that Google News groups with each article (same story, other publishers: title, publisher, link), free of charge.", "default": true }, "timeframe": { "title": "Time period", "enum": [ "any", "1h", "12h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Only articles from this recent period (Google News `when:`). For an exact range, use **Posted after** / **Posted before** instead.", "default": "any" }, "postedAfter": { "title": "Posted after", "type": "string", "description": "Only articles published on or after this date: `2026-09-01`, or a period before now such as `7 days`, `2 weeks`, `1 month` (API: `24 hours` and full ISO date-times work too). Reads the publication date given by Google News." }, "postedBefore": { "title": "Posted before", "type": "string", "description": "Only articles published on or before this date (the whole day is included), or older than a period such as `30 days`." }, "sites": { "title": "Only these publishers", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Keep only articles from these sites (domain, e.g. `reuters.com`, `bbc.co.uk`). Added to every search as `site:`, and checked on topics and places.", "default": [], "items": { "type": "string" } }, "excludeSites": { "title": "Exclude publishers", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Drop articles from these sites (domain, e.g. `yahoo.com`).", "default": [], "items": { "type": "string" } }, "titleOnly": { "title": "Search words in the title only", "type": "boolean", "description": "Match the search query in the article title only (Google News `intitle:`).", "default": false }, "excludeKeywords": { "title": "Exclude keywords", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Drop the articles whose title contains one of these words or phrases, as whole words: `war` drops \"War in…\" but keeps \"Warner\" (case and accents ignored; in Chinese, Japanese, Korean, Thai… any part of the title counts).", "default": [], "items": { "type": "string" } }, "onlyNew": { "title": "Only new articles", "type": "boolean", "description": "Skip the articles that a previous run (same **Memory key**) already delivered: they are not saved and not charged, and their page is not even opened. First run = everything is new.", "default": false }, "stateKey": { "title": "Memory key", "pattern": "^[a-zA-Z0-9_-]{1,64}$", "maxLength": 64, "type": "string", "description": "Name of the memory used by **Only new articles**. Give each schedule / task its own key (e.g. `tesla-alerts`) so that they do not share their memory. Letters, digits, `-` and `_`.", "default": "default" }, "resetState": { "title": "Reset the memory", "type": "boolean", "description": "Forget everything remembered under this **Memory key** before the run: this run returns (and charges) every article again. Untick it afterwards.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy or your own proxies. Keep the default: it is included in the price. The residential Apify proxy is not available in this Actor.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of requests processed in parallel.", "default": 8 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 10, "maximum": 2000, "type": "integer", "description": "Most requests to Google News and to publisher sites in any 60 seconds, all of them counted. A budget, not an even pace: up to this many can leave at once when the minute starts (spread them with the minimum delay below). Lower it if the log shows HTTP 429.", "default": 120 }, "minRequestIntervalMs": { "title": "Min delay between requests", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Smallest gap between two requests, in milliseconds. Unlike the per-minute rate, this spreads the requests evenly instead of letting them go out in a burst. 0 = no gap.", "default": 0 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 20, "type": "integer", "description": "Retries per request before it is marked as failed. Behind a proxy, a request the site turns away is also retried on a new proxy session up to 10 times without using up these retries.", "default": 5 }, "debugLog": { "title": "Debug log", "type": "boolean", "description": "Include debug messages in the run log.", "default": 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 } } } } } } } } } }