{ "openapi": "3.0.1", "info": { "title": "News and Blog Article Extractor: Clean Text, Author, Date", "description": "Paste news or blog URLs, or a section page, RSS feed or sitemap to discover them. Get one row per article: clean text, Markdown or HTML, author, publish and update dates, title, site name, language, tags, lead image and word count. Reads JSON-LD and OpenGraph. No browser, no login.", "version": "1.0", "x-build-id": "rUnOUvSAUB9dAUc9e" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fernandosord~article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fernandosord-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fernandosord~article-extractor/runs": { "post": { "operationId": "runs-sync-fernandosord-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fernandosord~article-extractor/run-sync": { "post": { "operationId": "run-sync-fernandosord-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "Article URLs", "type": "array", "description": "Links to news articles or blog posts. Each one becomes one row. A link to an RSS feed or sitemap is also accepted here and its articles are followed.", "items": { "type": "string" } }, "discoveryUrls": { "title": "Find articles on these pages (optional)", "type": "array", "description": "A section page, blog home, RSS or Atom feed, or sitemap. The Actor collects article links on the same site, newest first, and extracts them. Pages that turn out not to be articles are skipped and not charged.", "items": { "type": "string" } }, "maxArticlesPerSection": { "title": "Max articles per section", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many articles to extract from each page in the field above.", "default": 10 }, "maxArticles": { "title": "Max articles in total", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard limit on rows for the whole run, direct URLs and discovered articles together. The run stops when it is reached.", "default": 50 }, "outputFormats": { "title": "Article body formats", "type": "array", "description": "Which versions of the article body to include in each row. Plain text has paragraphs separated by blank lines. HTML is the cleaned article markup with absolute links.", "items": { "type": "string", "enum": [ "text", "markdown", "html" ], "enumTitles": [ "Plain text", "Markdown", "Clean HTML" ] }, "default": [ "text", "markdown" ] }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Adds an images list (URL, alt text, caption) with the pictures inside the article body, and keeps image links in the Markdown and HTML. The lead image is always included.", "default": true }, "minWords": { "title": "Minimum words for pages without article markup", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages that declare themselves as articles (JSON-LD Article, NewsArticle or BlogPosting) are accepted from 25 words. Pages with no such markup need at least this many words of readable text, otherwise they are treated as non-articles.", "default": 120 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Most news and blog sites load without a proxy. If a site answers HTTP 403, turn on Apify Proxy (residential works best for hard sites).", "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 } } } } } } } } } }