{ "openapi": "3.0.1", "info": { "title": "Google News AI Scraper", "description": "Search Google News by keyword, optionally extract full article text and AI-generated summaries via OpenRouter, and never re-scrape the same article twice across runs via built-in cross-run deduplication.", "version": "1.0", "x-build-id": "Ti8FQdgds2kjMBLsm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/confidential_gnat~google-news-ai-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-confidential_gnat-google-news-ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/confidential_gnat~google-news-ai-scraper/runs": { "post": { "operationId": "runs-sync-confidential_gnat-google-news-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/confidential_gnat~google-news-ai-scraper/run-sync": { "post": { "operationId": "run-sync-confidential_gnat-google-news-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "queries" ], "properties": { "projectName": { "title": "Project name", "type": "string", "description": "Articles already scraped under this project name in a previous run are skipped. Leave empty to disable cross-run caching." }, "queries": { "title": "Search queries", "type": "array", "description": "Keywords or phrases to search on Google News. Each query is scraped separately.", "items": { "type": "string" } }, "maxResultsPerQuery": { "title": "Max results per query", "minimum": 1, "type": "integer", "description": "Maximum number of articles to return for each search query, after deduplication.", "default": 1 }, "language": { "title": "Language", "type": "string", "description": "2-letter BCP-47 language code for Google News results (e.g. 'en', 'de', 'fr', 'es').", "default": "en" }, "country": { "title": "Country", "type": "string", "description": "ISO 3166-1 alpha-2 country code for regional news (e.g. 'US', 'GB', 'DE', 'IN').", "default": "US" }, "dateRange": { "title": "Date range", "enum": [ "1h", "1d", "7d", "1m", "1y", "any" ], "type": "string", "description": "Filter articles by recency. Ignored if Date from / Date to is set.", "default": "any" }, "dateFrom": { "title": "Date from", "type": "string", "description": "Only return articles published on or after this date (YYYY-MM-DD). Overrides Date range." }, "dateTo": { "title": "Date to", "type": "string", "description": "Only return articles published on or before this date (YYYY-MM-DD). Overrides Date range." }, "siteFilter": { "title": "Site filter", "type": "string", "description": "Restrict results to a specific domain (e.g. 'reuters.com', 'bbc.com')." }, "excludeWords": { "title": "Exclude words", "type": "array", "description": "Words that must not appear in results.", "items": { "type": "string" } }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Extract the article's main image (og:image). Note: this makes the Actor visit each article page with a browser, even if Extract full text is off.", "default": false }, "extractFullText": { "title": "Extract full text", "type": "boolean", "description": "Visit each article with a browser and extract the full, cleaned article text (not just the search-result snippet). Automatically turned on when AI enrichment is enabled, since enrichment quality depends on having the full text.", "default": false }, "aiEnabled": { "title": "Enable AI enrichment", "type": "boolean", "description": "Run each article through an OpenRouter model to generate the AI outputs selected below.", "default": false }, "aiApiKey": { "title": "OpenRouter API key", "type": "string", "description": "Your OpenRouter API key (https://openrouter.ai/keys). Optional: if left empty while AI enrichment is enabled, this Actor's own key is used instead and a small per-article platform fee is charged. Never logged or stored in output." }, "aiModel": { "title": "AI model", "enum": [ "openai/gpt-4o-mini", "anthropic/claude-3.5-haiku", "google/gemini-2.0-flash-001", "meta-llama/llama-3.1-8b-instruct", "mistralai/mistral-small" ], "type": "string", "description": "OpenRouter model used for AI enrichment.", "default": "openai/gpt-4o-mini" }, "aiFeatures": { "title": "AI features", "type": "array", "description": "What the AI should generate for each article.", "items": { "type": "string", "enum": [ "summarize", "paraphrase", "keywords", "sentiment", "custom" ], "enumTitles": [ "Summary", "Paraphrase", "Keywords", "Sentiment", "Custom instruction" ] }, "default": [ "summarize" ] }, "aiCustomInstructions": { "title": "Custom AI instructions", "type": "string", "description": "Extra instructions for the AI, used when 'Custom instruction' is selected above (e.g. 'Extract any stock tickers mentioned')." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Google News and most publisher sites don't require a proxy. Enable one only if you see blocked requests.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }