{ "openapi": "3.0.1", "info": { "title": "Google News Keyword & Full-Text Article Scraper", "description": "Search Google News by keyword with real resolved article links, headlines, sources, and dates, plus optional full article text and image extraction, filterable by date, language, and publisher.", "version": "2.0", "x-build-id": "bIH7aBp5p44Lvpppe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nimbryxo-studio~google-news-keyword-and-full-text-article-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nimbryxo-studio-google-news-keyword-and-full-text-article-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nimbryxo-studio~google-news-keyword-and-full-text-article-scraper/runs": { "post": { "operationId": "runs-sync-nimbryxo-studio-google-news-keyword-and-full-text-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nimbryxo-studio~google-news-keyword-and-full-text-article-scraper/run-sync": { "post": { "operationId": "run-sync-nimbryxo-studio-google-news-keyword-and-full-text-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "keyword", "topic", "newsUrl", "rss", "articleUrls" ], "type": "string", "description": "What to scrape. Each mode reads its own list field below.", "default": "keyword" }, "queries": { "title": "Search queries (mode=keyword)", "type": "array", "description": "One or more keyword queries. Google operators such as site:, intitle: and OR are supported. Results are deduplicated across queries.", "items": { "type": "string" }, "default": [] }, "topics": { "title": "Topics (mode=topic)", "type": "array", "description": "Topic names (WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH), TOP for top stories, Google News topic hashes/section URLs, or topic URLs. Topic feeds ignore server-side date filters; results are filtered after download.", "items": { "type": "string" }, "default": [] }, "newsUrls": { "title": "Google News URLs (mode=newsUrl)", "type": "array", "description": "Google News search URLs, topic URLs, RSS search/topic URLs, or RSS/Atom feed URLs to convert into a feed.", "items": { "type": "string" }, "default": [] }, "rssUrls": { "title": "RSS / Atom feeds (mode=rss)", "type": "array", "description": "Any public RSS or Atom feed. Google News links inside the feed are resolved to publisher URLs automatically.", "items": { "type": "string" }, "default": [] }, "articleUrls": { "title": "Article URLs (mode=articleUrls)", "type": "array", "description": "Publisher article URLs or Google News article URLs. Every page is fetched and full text is extracted, with a per-record status when a publisher blocks or paywalls it.", "items": { "type": "string" }, "default": [] }, "language": { "title": "Language", "enum": [ "en", "de", "fr", "es", "it", "pt", "nl", "pl", "ru", "uk", "tr", "ar", "he", "fa", "hi", "bn", "ur", "ta", "te", "ml", "mr", "gu", "kn", "pa", "ja", "ko", "zh", "th", "vi", "id", "ms", "fil", "sv", "no", "da", "fi", "cs", "sk", "hu", "ro", "bg", "el", "hr", "sr", "sl", "lt", "lv", "et", "ca", "eu", "gl", "af", "sw", "am", "az", "kk", "uz", "ne", "si", "my", "km", "lo", "mn", "ka", "hy", "is", "ga", "mt", "mk", "sq", "bs", "be", "ky", "tg" ], "type": "string", "description": "Language of the Google News edition. Combined with country in the edition token (for example US:en, DE:de, JP:ja).", "default": "en" }, "country": { "title": "Country / edition", "enum": [ "US", "GB", "CA", "AU", "NZ", "IE", "IN", "PK", "BD", "LK", "NP", "DE", "FR", "ES", "IT", "PT", "NL", "BE", "AT", "CH", "SE", "NO", "DK", "FI", "IS", "PL", "CZ", "SK", "HU", "RO", "BG", "GR", "HR", "RS", "SI", "UA", "RU", "TR", "IL", "SA", "AE", "EG", "QA", "KW", "BH", "OM", "JO", "LB", "IQ", "IR", "MA", "DZ", "TN", "NG", "KE", "ZA", "GH", "ET", "TZ", "UG", "MX", "BR", "AR", "CL", "CO", "PE", "VE", "EC", "UY", "PY", "BO", "CR", "PA", "DO", "GT", "HN", "SV", "NI", "PR", "JP", "KR", "CN", "HK", "TW", "SG", "MY", "ID", "TH", "VN", "PH", "KH", "MM", "LA", "MN", "KZ", "UZ", "AZ", "GE", "AM" ], "type": "string", "description": "Country edition for Google News. The actor always pins the edition so results do not change with the machine's IP.", "default": "US" }, "dateRange": { "title": "Date range", "enum": [ "any", "1h", "6h", "12h", "1d", "7d", "30d", "1y", "custom" ], "type": "string", "description": "Recency window. Every item is post-filtered by its real publication time, so items newer than the window never leak. 'custom' uses startDate/endDate. Multi-day ranges can be walked day by day to collect more than one feed page.", "default": "any" }, "startDate": { "title": "Start date", "type": "string", "description": "Custom range start (YYYY-MM-DD, inclusive). Also used when dateRange=custom." }, "endDate": { "title": "End date", "type": "string", "description": "Custom range end (YYYY-MM-DD, inclusive). Items published after the end are dropped client-side." }, "maxResultsPerQuery": { "title": "Max results per query window", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum records taken from each Google News feed request (1-100, Google's own cap is about 100). When a date range spans several days, the actor walks day windows and can collect more than 100 for one query, up to maxItems.", "default": 20 }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on unique records emitted by the run (1-5000).", "default": 500 }, "extractFullText": { "title": "Extract full text", "type": "boolean", "description": "Fetch each publisher page and extract its article body, description, author, and image. Default off for fast metadata-only runs. The articleUrls mode always extracts.", "default": false }, "maxFullText": { "title": "Max full-text extractions", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum pages fetched for full text per run (1-500). Records beyond this cap are still returned with fullTextStatus=skipped_cap.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. No proxy is needed by default; Google News RSS and publisher pages work without one. Residential proxies can make Google rate-limit more, so leave this off unless you need it.", "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 } } } } } } } } } }