{ "openapi": "3.0.1", "info": { "title": "Google News Scraper — Articles, Sources & Full Text", "description": "Scrape Google News by keyword or topic in any language and country, with real publisher URLs (decoded), dates, sources, and optional full article text, author and image. Goes past the 100-result limit by splitting dates.", "version": "1.0", "x-build-id": "wb0R7TSNS8u6Oswf7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datakiln~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datakiln-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datakiln~google-news-scraper/runs": { "post": { "operationId": "runs-sync-datakiln-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datakiln~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-datakiln-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 to search on Google News, one per line. Google News operators work: \"exact phrase\", OR, -exclude, site:reuters.com, intitle:word, when:2d, after:2026-01-01, before:2026-02-01 (if you add your own date operators, the date settings below are not applied to that query).", "items": { "type": "string" } }, "topics": { "title": "Topics (headlines)", "type": "array", "description": "Google News topic sections to scrape the current headlines from. Topic feeds return Google's current selection (usually 30–70 stories) and can't be split by date.", "items": { "type": "string", "enum": [ "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "World", "Nation (country news)", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "language": { "title": "Language", "type": "string", "description": "Google News edition language (hl), e.g. en-US, en-GB, de, fr, es, ar, pt-BR, ja, zh-TW.", "default": "en-US" }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code of the edition (gl), e.g. US, GB, DE, FR, SA, IN, BR.", "default": "US" }, "additionalLocales": { "title": "More editions (language:COUNTRY)", "type": "array", "description": "Scrape the same queries/topics in more Google News editions, one per line as language:COUNTRY, e.g. ar:SA, de:DE, en-GB:GB, es:MX. Results are de-duplicated across editions.", "items": { "type": "string" } }, "timeRange": { "title": "Time range", "enum": [ "1h", "1d", "7d", "30d", "1y", "any" ], "type": "string", "description": "Only articles published in this period. With 1 day or longer, when Google's feed is full (~100 items) the scraper splits the period into single days to collect more. Ignored when Date from / Date to are set.", "default": "7d" }, "dateFrom": { "title": "Date from", "type": "string", "description": "Only articles published on or after this day (YYYY-MM-DD). Overrides Time range. The period is split into single days so you can get far more than 100 articles per query." }, "dateTo": { "title": "Date to", "type": "string", "description": "Only articles published on or before this day (YYYY-MM-DD). Leave empty for today." }, "maxArticlesPerQuery": { "title": "Max articles per query / topic", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum unique articles for each query or topic in each edition.", "default": 100 }, "decodeUrls": { "title": "Resolve real article URLs", "type": "boolean", "description": "Google News RSS links point to news.google.com redirects. When on, each one is resolved to the publisher's real URL (url field). Turn off for a faster run that returns only Google links.", "default": true }, "extractFullText": { "title": "Extract full article text", "type": "boolean", "description": "Open each article on the publisher's site and extract the main text, author, publish date, top image and language. Costs extra only for articles where the text was actually extracted.", "default": false }, "maxConcurrency": { "title": "Publisher pages in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many publisher pages to download at the same time when extracting full text.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not required. Use a proxy only if Google starts rate-limiting large runs or many publisher pages come back blocked." } } }, "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 } } } } } } } } } }