{ "openapi": "3.0.1", "info": { "title": "Google News Scraper: By Date", "description": "Google News read day by day past the usual 100 per search: 4,440 articles from two keywords over 30 days. $1 per 1,000 articles. Topics and links too.", "version": "0.1", "x-build-id": "Zw16coGXKgbk5DFUy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/luzivanlt~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-luzivanlt-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/luzivanlt~google-news-scraper/runs": { "post": { "operationId": "runs-sync-luzivanlt-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/luzivanlt~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-luzivanlt-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": { "keywords": { "title": "Keywords", "type": "array", "description": "Words to search Google News for, one search per line, as you would type them in Google News' search box, e.g. artificial intelligence. Google's search operators work too: \"exact phrase\", OR, -word, site:example.com. Up to 300 characters each. With a date window set, leave out after:, before: and when: (use one or the other). A link here is refused: paste it under Google News links.", "items": { "type": "string" } }, "topics": { "title": "Topics", "type": "array", "description": "Google News sections to read: TOP (top stories), WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH, e.g. TECHNOLOGY. Each section is one feed of about 40 to 100 articles, read in the edition under Country and language. A date window only filters it.", "items": { "type": "string", "enum": [ "TOP", "WORLD", "NATION", "BUSINESS", "TECHNOLOGY", "ENTERTAINMENT", "SPORTS", "SCIENCE", "HEALTH" ], "enumTitles": [ "Top stories", "World", "Nation", "Business", "Technology", "Entertainment", "Sports", "Science", "Health" ] } }, "startUrls": { "title": "Google News links", "type": "array", "description": "Links to Google News pages: a search (news.google.com/search?q=…), a section or topic (news.google.com/topics/…, /headlines/section/topic/BUSINESS), or the front page; RSS links work too. A link keeps its own country and language (its ceid, or hl and gl); one without them uses Country and language. e.g. https://news.google.com/search?q=solar", "items": { "type": "string" } }, "edition": { "title": "Country and language", "type": "string", "description": "The Google News edition to read, as COUNTRY:language, e.g. US:en, GB:en, IN:en, DE:de, FR:fr, JP:ja, BR:pt-419, MX:es-419, TW:zh-Hant or VN:vi. Default US:en. Links keep their own edition. Each row's feed_language shows the edition Google served; an unknown edition reads as US English.", "default": "US:en" }, "onlyArticlesNewerThan": { "title": "Only articles newer than", "type": "string", "description": "A date, e.g. 2026-10-01, or a span back from now (12 hours, 3 days, 2 weeks, 1 month, 1 year). With a date window, each keyword is read one day at a time, up to about 100 articles a day, so a long window returns far more articles, each charged. Sections and links are only filtered. Leave empty for Google's latest articles (about 100 per keyword)." }, "onlyArticlesOlderThan": { "title": "Only articles older than", "type": "string", "description": "Optional end of the window: a date, e.g. 2026-10-15 (articles before that day), or a span back from now, e.g. 1 week. Needs \"Only articles newer than\" and must be later than it. The window is at most 366 days. Leave empty to read up to now." }, "maxArticlesPerFeed": { "title": "Max articles per keyword, topic or link", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop each keyword, topic or link after this many articles, from 1 to 10,000; default 100. With a date window, the newest days are read first. Each article is charged once per run ($1 per 1,000 articles), so this caps each one's cost. Example: 3,000 articles cost at most $3. An article found by two keywords is charged once but counts toward both limits.", "default": 100 }, "onlyNewItems": { "title": "Only new articles", "type": "boolean", "description": "Turn this on for a scheduled run, or a re-run of the same task: each run then reads the latest articles of each keyword, topic or link and returns only those it has not returned before. Skipped articles are neither saved nor charged; each new article is charged as usual. On a keyword search it needs Only articles newer than left empty (the form fills in 3 days: clear it), since a dated search reads one feed a day. Runs with other settings, or from another task, keep their own list. Off by default." } } }, "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 } } } } } } } } } }