{ "openapi": "3.0.1", "info": { "title": "Google News Scraper (Real Publisher URLs, Date Ranges)", "description": "Scrape Google News by keyword, topic or Google News URL in any country/language. Every article includes its real decoded publisher URL, source, publish date and related coverage. Date ranges get past Google's 100-result cap. Pay only for articles with a decoded URL.", "version": "0.1", "x-build-id": "zPE4GGsoqoQk9BFmt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~google-news-scraper-decoded-urls/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-google-news-scraper-decoded-urls", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~google-news-scraper-decoded-urls/runs": { "post": { "operationId": "runs-sync-blond_terrarium-google-news-scraper-decoded-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~google-news-scraper-decoded-urls/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-google-news-scraper-decoded-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One per line. Google News operators work: \"exact phrase\", OR, -exclude, site:reuters.com, intitle:. Each query returns up to ~100 articles per feed; use a date range to get more.", "items": { "type": "string" } }, "topics": { "title": "Topics / headlines", "type": "array", "description": "Google News sections for each edition. Top stories include related coverage clusters.", "items": { "type": "string", "enum": [ "TOP", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "Top stories", "World", "Nation (edition country)", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "startUrls": { "title": "Google News URLs", "type": "array", "description": "news.google.com search, topic, publication, local (geo) or story URLs, web or RSS form. The URL's own ceid/edition is respected.", "items": { "type": "string" } }, "editions": { "title": "Editions (country:language)", "type": "array", "description": "One per line, Google's ceid format: US:en, GB:en, IN:en, CA:fr, DE:de, FR:fr, ES:es, MX:es-419, BR:pt-419, JP:ja, IT:it… Every query/topic runs in every edition.", "default": [ "US:en" ], "items": { "type": "string" } }, "timeRange": { "title": "Time range", "enum": [ "any", "1h", "12h", "1d", "7d", "30d", "1y" ], "type": "string", "description": "Applied to search queries (Google's when: operator). Ignored when a date range is set.", "default": "any" }, "dateFrom": { "title": "Date from", "type": "string", "description": "YYYY-MM-DD or relative like \"30 days\". With a date range, each query is searched day by day (newest first), so you can get far more than 100 articles per query. Only dateTo set = the 7 days up to it." }, "dateTo": { "title": "Date to", "type": "string", "description": "YYYY-MM-DD (inclusive). Default: today." }, "maxArticlesPerQuery": { "title": "Max articles per query / topic / URL", "minimum": 0, "type": "integer", "description": "Per query and edition, across all day windows. 0 = no limit.", "default": 100 }, "decodeUrls": { "title": "Decode real publisher URLs", "type": "boolean", "description": "Resolve each news.google.com link to the publisher's article URL. Articles that can't be decoded are written free (status URL_NOT_DECODED).", "default": true }, "fetchArticleDetails": { "title": "Fetch article details (image, description, author)", "type": "boolean", "description": "Visit each publisher page (head only, ≤512 KB) for og:image, description, author, publish time, canonical URL. Best effort: paywalls/bot walls leave these empty. Slower; same price.", "default": false }, "includeRelated": { "title": "Include related coverage", "type": "boolean", "description": "Other outlets' coverage of the same story (mostly on Top stories / topic feeds).", "default": true }, "deduplicate": { "title": "Deduplicate across queries and days", "type": "boolean", "description": "Each article is returned and charged once per run.", "default": true }, "includeFailedRows": { "title": "Include free rows for failures", "type": "boolean", "description": "One free row per input that returned nothing, and per undecoded article, with the reason.", "default": true }, "maxChargedArticles": { "title": "Max charged articles", "minimum": 0, "type": "integer", "description": "Hard stop on charged articles (0 = no limit). The run also stops at your Max total charge.", "default": 0 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel requests (Google News requests are also paced).", "default": 4 }, "requestDelayMs": { "title": "Delay between Google News requests (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Polite pacing; raised automatically on 429/503.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout in seconds for each HTTP request to Google News or a publisher page.", "default": 30 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Not needed normally. Apify datacenter proxy can be used if Google rate-limits; residential proxy is not supported.", "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 } } } } } } } } } }