{ "openapi": "3.0.1", "info": { "title": "News & Brand Monitoring Scraper", "description": "Monitor any brand, competitor or topic across Google News in any country. Headline, outlet, timestamp and coverage-breadth stats per query - plus optional resolution of Google's redirect links into the publisher's own URL, which most scrapers cannot do. No API key.", "version": "0.0", "x-build-id": "Iny2tj7q2W72LpPg6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/eiv~news-monitoring-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-eiv-news-monitoring-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/eiv~news-monitoring-scraper/runs": { "post": { "operationId": "runs-sync-eiv-news-monitoring-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/eiv~news-monitoring-scraper/run-sync": { "post": { "operationId": "run-sync-eiv-news-monitoring-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Queries", "type": "array", "description": "One per line. Google News search syntax works: quote a phrase (\"acme corp\"), combine with OR, exclude with a minus, restrict to an outlet with site:reuters.com. If you combine site: with a keyword, quote the keyword — site:reuters.com \"tesla\" — because unquoted it is barely weighted and you get the outlet's recent output instead. Measured: 15 of 100 headlines matched unquoted, 71 of 100 quoted.", "items": { "type": "string" } }, "sourceDatasetId": { "title": "Source dataset ID", "type": "string", "description": "Read queries from an existing dataset instead of typing them — for example the keywords found by a keyword research run." }, "sourceDatasetField": { "title": "Source dataset field", "type": "string", "description": "Which field on the source dataset holds the query.", "default": "query" }, "country": { "title": "Country edition", "type": "string", "description": "ISO code such as US, GB, DE, JP. Google News runs a separate edition per country, and each carries different outlets — the German edition is not the American one translated.", "default": "US" }, "language": { "title": "Language", "type": "string", "description": "Two-letter code. Left empty it follows the country: DE gives German, JP Japanese, BR Portuguese." }, "timeWindow": { "title": "Time window", "enum": [ "1h", "24h", "7d", "30d", "1y", "any" ], "type": "string", "description": "How far back to look. Only Google's own windows work; anything else would be searched for as words rather than read as a filter.", "default": "7d" }, "resolveArticleUrls": { "title": "Resolve publisher URLs", "type": "boolean", "description": "Turn Google's redirect links into the publisher's own address. Costs two extra requests and about 600 KB per article, because the tokens Google needs sit at the very end of a full article page. Leave off when the headline and outlet are enough.", "default": false }, "maxResolvedPerQuery": { "title": "Max URLs to resolve per query", "minimum": 0, "maximum": 100, "type": "integer", "description": "Caps the expensive part. Articles beyond the cap keep their Google News link and are marked NOT_REQUESTED. Ignored unless resolution is on.", "default": 25 }, "maxArticlesPerQuery": { "title": "Max articles per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Google News caps a feed at roughly 100 articles regardless. Queries that come back full are flagged truncated.", "default": 100 }, "deduplicateAcrossQueries": { "title": "Deduplicate across queries", "type": "boolean", "description": "Monitoring a brand and its product usually returns the same story twice. On, each story is emitted once and charged once; off, repeats are kept and marked isDuplicate.", "default": true }, "includeQuerySummary": { "title": "Include a summary per query", "type": "boolean", "description": "Add one rollup record per query: distinct outlets, top outlets, date range and articles per day. Not billed as an article.", "default": true }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Queries processed in parallel.", "default": 4 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout.", "default": 45 }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for connection resets and 5xx responses.", "default": 2 }, "flattenOutput": { "title": "Flatten output for CSV", "type": "boolean", "description": "Emit flat dot-notation columns. Mainly affects the top-outlets list on summary rows.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. The feed itself is a public RSS endpoint and does not block; a proxy mainly matters when resolving many publisher URLs in one run.", "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 } } } } } } } } } }