{ "openapi": "3.0.1", "info": { "title": "News & RSS Scraper: Google News to JSON", "description": "Scrape news and blog articles from Google News searches, Google News topics, and any RSS 2.0, RSS 1.0, Atom or JSON Feed URL. One identical row per article: title, link, publisher, publish date, author, summary, categories, images and optional full article text for RAG pipelines.", "version": "0.1", "x-build-id": "wVZcEbCQxs0TPyeRR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/axiorasolutions~news-feed-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-axiorasolutions-news-feed-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/axiorasolutions~news-feed-scraper/runs": { "post": { "operationId": "runs-sync-axiorasolutions-news-feed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/axiorasolutions~news-feed-scraper/run-sync": { "post": { "operationId": "run-sync-axiorasolutions-news-feed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "sources" ], "properties": { "sources": { "title": "Sources", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Mix any of these in one run. gnews:artificial intelligence runs a Google News search. gnews-topic:TECHNOLOGY pulls a Google News topic. gnews:top pulls top stories. A feed URL is read directly. A plain website URL is auto-resolved to its RSS, Atom or JSON feed.", "items": { "type": "string" } }, "googleNewsLanguage": { "title": "Google News language", "type": "string", "description": "Language and region code for Google News sources, for example en-US, en-GB, de-DE, fr-FR, es-ES, pt-BR, ja-JP. Ignored by plain feed URLs.", "default": "en-US" }, "googleNewsCountry": { "title": "Google News country", "type": "string", "description": "Two-letter edition country for Google News sources, for example US, GB, DE, FR, IN, AU. Ignored by plain feed URLs.", "default": "US" }, "maxItemsPerSource": { "title": "Max articles per source", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after this many articles from each source. Google News returns at most 100 per search.", "default": 50 }, "maxItemsTotal": { "title": "Max articles for the whole run", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Hard ceiling across every source. The run stops cleanly when it is reached.", "default": 500 }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Keep only articles published on or after this date. Accepts 2026-01-31 or a relative value such as 24 hours or 7 days. Articles with no date are kept." }, "keywords": { "title": "Keywords", "type": "array", "description": "Keep only articles whose title or summary contains one of these words, case-insensitive. Leave empty to keep everything the sources return.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Excluded keywords", "type": "array", "description": "Drop articles whose title or summary contains any of these words, case-insensitive.", "items": { "type": "string" } }, "deduplicateBy": { "title": "Deduplicate by", "enum": [ "url", "title", "guid", "none" ], "type": "string", "description": "Google News returns the same story from many outlets. url keeps one row per link, title collapses re-publications of the same headline, guid trusts the feed's own ID, none keeps everything.", "default": "url" }, "includeArticleText": { "title": "Fetch full article text", "type": "boolean", "description": "Fetch each article page and extract the main body as clean plain text, for embedding or summarisation. Adds one request per article. Google News links are redirect pages that cannot be read without a browser, so they are skipped and reported.", "default": false }, "articleTextMaxChars": { "title": "Article text limit", "minimum": 500, "maximum": 120000, "type": "integer", "description": "Truncate extracted article text at this many characters.", "default": 12000 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Give up on a single feed or article request after this many seconds.", "default": 25 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Most feeds answer direct requests. Turn on datacenter proxy rotation if a publisher blocks you, especially when fetching full article text at volume.", "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 } } } } } } } } } }