{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Real URLs & Article Text", "description": "Scrape Google News by keyword, topic, or headlines. Decodes Google's redirect links to real publisher URLs, with optional full article text and deduplicated monitoring.", "version": "1.0", "x-build-id": "jhtjFZfytWqdaIQ2N" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sauliusautomatesit~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sauliusautomatesit-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sauliusautomatesit~google-news-scraper/runs": { "post": { "operationId": "runs-sync-sauliusautomatesit-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sauliusautomatesit~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-sauliusautomatesit-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Keywords or phrases to search Google News for. Supports Google News operators (e.g. `\"exact phrase\"`, `intitle:`, `site:reuters.com`).", "items": { "type": "string" } }, "topics": { "title": "Topic feeds", "type": "array", "description": "Google News topic sections to pull. Valid: world, nation, business, technology, entertainment, sports, science, health.", "items": { "type": "string" } }, "includeTopHeadlines": { "title": "Include top headlines", "type": "boolean", "description": "Also fetch the main Top Headlines feed for the chosen country/language.", "default": false }, "language": { "title": "Language", "type": "string", "description": "Interface/content language, e.g. `en-US`, `en-GB`, `de`, `fr`, `es-419`.", "default": "en-US" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country/edition code, e.g. `US`, `GB`, `DE`, `IN`.", "default": "US" }, "timeRange": { "title": "Time range (search queries)", "enum": [ "any", "hour", "day", "week", "month", "year" ], "type": "string", "description": "Restrict search-query results to a recent window. Topics/headlines are always current.", "default": "any" }, "maxArticlesPerQuery": { "title": "Max articles per feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on articles taken from each query/topic/headlines feed (Google News returns up to ~100 per feed).", "default": 100 }, "resolveUrls": { "title": "Resolve real article URLs", "type": "boolean", "description": "Decode Google's redirect links into the real publisher URL (recommended). Disable for faster/cheaper runs that only need the Google News link.", "default": true }, "extractArticleText": { "title": "Extract full article text", "type": "boolean", "description": "Also fetch each article and extract readable body text, author, and image. Best-effort — some publishers block or paywall content (those rows keep metadata and note the reason, and are not charged the content fee).", "default": false }, "dedupByUrl": { "title": "Deduplicate across runs", "type": "boolean", "description": "Skip articles already seen in previous runs (great for scheduled monitoring). Dedup key is the resolved URL when available.", "default": true }, "dedupStoreName": { "title": "Dedup store name", "type": "string", "description": "Named storage used to remember seen articles across runs. Use one distinct name per monitoring watchlist so their histories don't mix.", "default": "google-news-dedup" }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Articles processed in parallel.", "default": 8 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Apify Proxy (automatic) is recommended, especially with article-text extraction.", "default": { "useApifyProxy": 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 } } } } } } } } } }