{ "openapi": "3.0.1", "info": { "title": "Google News Scraper", "description": "Extract Google News headlines, publishers, publish times, snippets, and links via public RSS queries. Pay per article. Demo mode included.", "version": "1.0", "x-build-id": "V8t3r72eECAB4ubiR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/intelscrape~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-intelscrape-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/intelscrape~google-news-scraper/runs": { "post": { "operationId": "runs-sync-intelscrape-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/intelscrape~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-intelscrape-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Google News search queries (e.g. electric vehicles). Supports operators: OR, quotes, site:, -exclude.", "items": { "type": "string" } }, "topics": { "title": "News topics", "uniqueItems": true, "type": "array", "description": "Predefined Google News topic feeds (in addition to keyword queries).", "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": "Custom Google News topic or section URLs (data_xplorer parity). Examples: https://news.google.com/topics/CAAq… or /rss/topics/…. Scraped via RSS. Cap 20.", "default": [], "items": { "type": "string" } }, "timeframe": { "title": "Time period", "enum": [ "6h", "1h", "1d", "7d", "30d", "1y", "all" ], "type": "string", "description": "Recency filter for keyword searches (appended as when: to the RSS query + client filter). Topics ignore RSS when:; client filter still applies unless dateFrom/dateTo override. Use dateFrom/dateTo for exact calendar bounds.", "default": "all" }, "dateFrom": { "title": "Date from (YYYY-MM-DD)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only keep articles published on/after this date (YYYY-MM-DD). Overrides/narrows timeframe for client filtering when set. Rival parity with crawlerbros/powerai/easyapi." }, "dateTo": { "title": "Date to (YYYY-MM-DD)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only keep articles published on/before this date (YYYY-MM-DD). Use with dateFrom for a calendar window." }, "maxResultsPerQuery": { "title": "Max results per query", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Optional per-query/topic cap applied before the global maxArticles limit (crawlerbros parity). Leave unset for no per-query cap." }, "regionLanguage": { "title": "Region and language", "enum": [ "US:en", "GB:en", "CA:en", "AU:en", "IN:en", "IE:en", "NZ:en", "SG:en", "ZA:en", "DE:de", "AT:de", "CH:de", "FR:fr", "CA:fr", "ES:es", "MX:es-419", "BR:pt-419", "IT:it", "NL:nl", "PL:pl", "SE:sv", "NO:no", "JP:ja", "KR:ko", "TW:zh-Hant", "CN:zh-Hans" ], "type": "string", "description": "Google News region:language (gl/hl/ceid). Default US English.", "default": "US:en" }, "siteFilter": { "title": "Site filter", "type": "array", "description": "Limit keyword searches to these domains (appended as site:domain). Rival parity with crawlerbros/memo23.", "default": [], "items": { "type": "string" } }, "excludeWords": { "title": "Exclude words", "type": "array", "description": "Words to exclude from keyword searches (appended as -word).", "default": [], "items": { "type": "string" } }, "decodeUrls": { "title": "Normalize URLs", "type": "boolean", "description": "Normalize article URLs via URL parser (best-effort; full CBM decode not billed separately).", "default": true }, "maxArticles": { "title": "Max articles", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum articles to push across all queries/topics.", "default": 50 }, "extractDescriptions": { "title": "Extract article descriptions", "type": "boolean", "description": "Fetch each article page and pull meta description / og:description when snippet is thin (data_xplorer parity). Slower.", "default": false }, "extractImages": { "title": "Extract article images", "type": "boolean", "description": "Fetch og:image from article pages when RSS has no image (data_xplorer/crawlerbros parity). Slower.", "default": false }, "maxEnrich": { "title": "Max pages to enrich", "minimum": 0, "maximum": 200, "type": "integer", "description": "Cap how many article pages get extractDescriptions/extractImages fetches (protects run time). Default 20.", "default": 20 }, "demoMode": { "title": "Demo mode", "type": "boolean", "description": "Push synthetic fixtures (no live scrape).", "default": false }, "includeNewsSummary": { "title": "Include news summary", "type": "boolean", "description": "Push one extractive query-summary row per search query/topic (top publishers, keywords, date range) and charge news-summary. Default on.", "default": true } } }, "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 } } } } } } } } } }