{ "openapi": "3.0.1", "info": { "title": "Article Extractor: Text, Markdown, Author, Date from Any URL", "description": "Extract clean article text and Markdown from news and blog URLs, with title, author, publish date, language, tags and word count. Works on lists or a dataset column, respects robots.txt, no API key. Non-articles, errors and blocked pages are free rows.", "version": "0.0", "x-build-id": "tq04pf33q8c09fB4B" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/charlesmarkette~article-extractor-text-markdown-author-date/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-charlesmarkette-article-extractor-text-markdown-author-date", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/charlesmarkette~article-extractor-text-markdown-author-date/runs": { "post": { "operationId": "runs-sync-charlesmarkette-article-extractor-text-markdown-author-date", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/charlesmarkette~article-extractor-text-markdown-author-date/run-sync": { "post": { "operationId": "run-sync-charlesmarkette-article-extractor-text-markdown-author-date", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Article URLs", "type": "array", "description": "One per line. Links to news articles, blog posts, documentation pages or any other web page with a main text. Each URL becomes one output row.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset to enrich", "type": "string", "description": "Optional. A dataset from another run that has article links (a sitemap or RSS run, a scraper's results…). Each item's URL is extracted and the article columns are added next to the item's fields. Use {{resource.defaultDatasetId}} in an integration." }, "urlField": { "title": "URL field", "type": "string", "description": "The item field that holds the article URL. Dotted paths work (link.href). Default: url." }, "keepItemFields": { "title": "Keep the item's original fields", "type": "boolean", "description": "On: each output row is the original item plus the article columns (article columns win if a name clashes). Off: only the article columns.", "default": true }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which versions of the main text to return. Text: plain text, one paragraph per line. Markdown: headings, lists, bold and italics, code blocks and tables (plus links and images when those options are on); the best input for LLMs and RAG. HTML: the cleaned main content as simple HTML.", "items": { "type": "string", "enum": [ "text", "markdown", "html" ], "enumTitles": [ "Plain text", "Markdown", "Clean HTML" ] }, "default": [ "text", "markdown" ] }, "includeComments": { "title": "Include reader comments", "type": "boolean", "description": "Adds a comments field with the text of reader comments when the page shows them in its HTML. Comments loaded later by JavaScript (Disqus and similar) aren't seen.", "default": false }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Adds a links list (url and text) of the links inside the article text, and keeps them as [text](url) in the Markdown.", "default": false }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Adds an images list (url and alt text) of the images inside the article, and keeps them as ![alt](url) in the Markdown. The lead image is always in the image field.", "default": false }, "language": { "title": "Only these languages", "type": "string", "description": "Optional. Comma-separated language codes, e.g. en, de. Pages that declare another language (in their HTML lang attribute, og:locale, JSON-LD or Content-Language header) get a free 'language-skipped' row without text. Pages that declare no language are kept." }, "minWords": { "title": "Minimum words for an article", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Pages whose main text has fewer words are reported as 'not-article' without text and aren't charged (home pages, category pages, product grids, login walls). Chinese and Japanese characters count as one word each.", "default": 50 }, "maxTextLength": { "title": "Max text length (characters)", "minimum": 100, "type": "integer", "description": "Optional. Cuts each text field (text, markdown, html, comments) to this many characters and sets truncated to true. wordCount is always for the full text. Without a value, fields are capped at 1,000,000 characters." }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "On (recommended): each site's robots.txt is read first, and pages it disallows for bots get a free 'robots-blocked' row instead of being fetched. If robots.txt can't be read because the site is down or overloaded (HTTP 429 or 5xx), the site is treated as off-limits, as the robots.txt standard (RFC 9309) says. Turn off only for sites you are allowed to fetch.", "default": true }, "concurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages to fetch at the same time (1–20).", "default": 5 }, "perHostConcurrency": { "title": "Parallel pages per site", "minimum": 1, "maximum": 10, "type": "integer", "description": "At most this many requests to the same host at a time (1–10), to stay polite to each site.", "default": 2 }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "How long one request may take (5–300). A page, with its redirects, retries and robots.txt check, gets at most twice this long.", "default": 45 }, "dedupe": { "title": "Process each URL once", "type": "boolean", "description": "Skip repeats of a URL already processed in this run (URLs that differ only by #fragment count as the same). Skipped repeats get no row and are free.", "default": true }, "maxResults": { "title": "Max output rows", "minimum": 1, "type": "integer", "description": "Optional cap on output rows (each row is one URL, extracted or not)." } } }, "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 } } } } } } } } } }