{ "openapi": "3.0.1", "info": { "title": "News Article Extractor: RSS, URLs & Clean Text", "description": "Extract clean article text, author, publish date, tags and image from news links, or get the newest articles from up to 50 news sites through their RSS feeds and sitemaps. Text or Markdown, only-new mode for schedules.", "version": "0.1", "x-build-id": "d02Ghxcgppl0u818P" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cliqtomedia~news-article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cliqtomedia-news-article-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cliqtomedia~news-article-extractor/runs": { "post": { "operationId": "runs-sync-cliqtomedia-news-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cliqtomedia~news-article-extractor/run-sync": { "post": { "operationId": "run-sync-cliqtomedia-news-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "articleUrls": { "title": "Article URLs", "type": "array", "description": "Direct links to news articles. Each page is fetched and returned as clean text with title, author, publish date, image, tags and language. Every URL in this list is processed (up to 500); maxArticles does not apply here.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "siteUrls": { "title": "News sites, RSS feeds or sitemaps", "type": "array", "description": "Homepages (e.g. https://www.theverge.com), RSS/Atom feed URLs or sitemap URLs. For a homepage the Actor finds the site's RSS/Atom feed or news sitemap itself, then extracts the newest articles. Up to 50 sites.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxArticles": { "title": "Max articles from sites", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of articles to extract from all siteUrls together (newest first, sites are interleaved). Does not limit articleUrls.", "default": 20 }, "dateFrom": { "title": "Only articles published after", "pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{1,4}\\s*(day|days|d))?$", "type": "string", "description": "Skip site articles published before this date. Use an absolute date like 2026-10-01 or a relative one like \"7 days\". Articles without a publish date are skipped when this is set. Does not filter articleUrls." }, "onlyNew": { "title": "Only new articles (skip ones returned before)", "type": "boolean", "description": "Remember delivered article URLs between runs and skip them next time. Ideal for scheduled runs: you pay only for articles you have not received yet.", "default": false }, "stateKey": { "title": "Memory name for 'Only new'", "pattern": "^[A-Za-z0-9_-]{1,40}$", "type": "string", "description": "Separate memory for different schedules or projects that use 'Only new'. Letters, digits, - and _ only.", "default": "default" }, "outputFormat": { "title": "Article body format", "enum": [ "text", "markdown", "both" ], "type": "string", "description": "Plain text (paragraphs separated by blank lines), Markdown (keeps headings, links and lists) or both.", "default": "text" }, "minWords": { "title": "Minimum words", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Pages with fewer words in the article body (section pages, video pages, short teasers) are skipped and not charged.", "default": 50 } } }, "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 } } } } } } } } } }