{ "openapi": "3.0.1", "info": { "title": "Google News Scraper: Article Text and New-Only Monitor", "description": "Scrape Google News by keyword, topic or publisher. Get headlines, dates, resolved publisher URLs, best-effort article text and new-only results for news monitoring.", "version": "0.1", "x-build-id": "w569Q2UXVR4Yg9P5O" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/danthedataman~google-news-article-ledger/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-danthedataman-google-news-article-ledger", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/danthedataman~google-news-article-ledger/runs": { "post": { "operationId": "runs-sync-danthedataman-google-news-article-ledger", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/danthedataman~google-news-article-ledger/run-sync": { "post": { "operationId": "run-sync-danthedataman-google-news-article-ledger", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startInputs": { "title": "Queries, topics and publishers", "type": "array", "description": "Mixed queries, predefined topic names, Google News search/topic URLs or publisher domains. Omitted/null/[] makes no requests.", "items": { "type": "string" } }, "country": { "title": "Country", "type": "string", "description": "Two-letter country code. Omitted/null means US." }, "language": { "title": "Language", "type": "string", "description": "Google News language code, including locale variants. Omitted/null means en." }, "timeframe": { "title": "Timeframe", "enum": [ "all", "1h", "6h", "1d", "7d", "30d", "1m", "1y" ], "type": "string", "description": "Recency operator for query/publisher feeds. Omitted/null means all. Explicit dates override it; topic feeds keep Google's window." }, "since": { "title": "Published since", "type": "string", "description": "Inclusive ISO date or zoned datetime. A since date enables backward day slicing for query/publisher feeds. No filter when omitted/null." }, "until": { "title": "Published until", "type": "string", "description": "Inclusive ISO date or zoned datetime. A date includes its whole UTC day. No upper publication filter when omitted/null." }, "maxItems": { "title": "Maximum delivered articles", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Maximum delivered rows, not a guaranteed yield. Omitted/null means 100; zero makes no requests." }, "maxArticlesPerInput": { "title": "Maximum selected articles per input", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Maximum distinct current canonical URLs selected per input before seen-URL suppression. Omitted/null means 100; zero removes this cap within the run budget." }, "resolveUrls": { "title": "Resolve publisher URLs", "type": "boolean", "description": "Omitted/null means true. False returns Google News links and feed metadata only, with no signatures, decoding or publisher reads; requires extractArticleText=false." }, "extractArticleText": { "title": "Read publisher article text", "type": "boolean", "description": "Omitted/null means true. True requires resolveUrls=true. Fetch publisher body and metadata; false keeps feed metadata only. Inaccessible or unconfirmed bodies remain null with a reason." }, "siteFilter": { "title": "Restrict query to publishers", "type": "array", "description": "Domains OR-ed with site: operators for query inputs; ignored for publisher-domain inputs. No restriction for omitted/null/[].", "items": { "type": "string" } }, "excludeWords": { "title": "Excluded words or phrases", "type": "array", "description": "Quoted negative search operators for query/publisher inputs. Omitted/null/[] adds no exclusions; topic feeds retain Google's selection.", "items": { "type": "string" } }, "alreadySeenUrls": { "title": "Already seen canonical URLs", "type": "array", "description": "Suppress previously delivered canonical URLs in the same resolution mode. Keep an accumulated list for successive monitor runs; no article-row charges for matches.", "items": { "type": "string" } }, "baselineDatasetId": { "title": "Prior full snapshot", "type": "string", "description": "Read-only dataset from a successful full snapshot run. Emits only unseen canonical URLs. Unreadable or malformed baselines fail before source requests; never supply a monitor delta." } } }, "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 } } } } } } } } } }