{ "openapi": "3.0.1", "info": { "title": "News Article Extractor: Clean Text, Author, Date & Images", "description": "Extract any news or blog article from its URL: title, authors, publish and modified dates, clean text and Markdown, lead image and all images, language, tags, word count and summary. Feeds and sitemaps too. $0.90 per 1,000 articles.", "version": "0.1", "x-build-id": "q0ljIzZ1oV7nDZmAv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plotpointtech~news-article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plotpointtech-news-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plotpointtech~news-article-extractor/runs": { "post": { "operationId": "runs-sync-plotpointtech-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/plotpointtech~news-article-extractor/run-sync": { "post": { "operationId": "run-sync-plotpointtech-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": "Links to individual news or blog articles. Each URL becomes one result with title, authors, dates, clean text, Markdown, images and more. Only pages that the site's robots.txt allows are fetched; paywalls and logins are never bypassed.", "items": { "type": "string" } }, "discoveryUrls": { "title": "Discover articles from feeds, sitemaps or sites", "type": "array", "description": "Optional. RSS/Atom feed URLs, XML sitemap or news-sitemap URLs, or a site's homepage (its feed or sitemap is found automatically). The newest articles are extracted, up to the limit below per source.", "default": [], "items": { "type": "string" } }, "maxArticlesPerSource": { "title": "Maximum articles per feed / sitemap", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many of the newest article links to take from each discovery URL.", "default": 10 }, "sameSiteOnly": { "title": "Only articles on the same site", "type": "boolean", "description": "Skip feed or sitemap links that point to a different website than the feed itself.", "default": true }, "maxArticles": { "title": "Maximum articles in total", "minimum": 0, "type": "integer", "description": "Stop after this many articles across all inputs. 0 = no limit.", "default": 0 }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Return the clean main article text (no menus, ads, comments or related links).", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Return the article body as Markdown with headings, lists, links, tables and images.", "default": true }, "includeImages": { "title": "Include all images", "type": "boolean", "description": "Return every image in the article body (URL and alt text) and keep images in the Markdown. The lead image is always returned.", "default": true }, "summarySentences": { "title": "Summary sentences", "minimum": 0, "maximum": 20, "type": "integer", "description": "Length of an extractive summary built from the article's own most representative sentences (no AI, no extra cost). 0 = no summary.", "default": 3 }, "maxTextChars": { "title": "Maximum characters of text / Markdown", "minimum": 0, "type": "integer", "description": "Trim text and Markdown to this length. 0 = full article.", "default": 0 }, "minWordCount": { "title": "Minimum words", "minimum": 0, "type": "integer", "description": "Pages with less article text than this are skipped and not charged (index pages, consent walls, paywalled stubs).", "default": 50 }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Pages fetched at the same time (each website is still paced politely and robots.txt crawl-delay is honoured).", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Give up on a page that does not answer within this time.", "default": 30 } } }, "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 } } } } } } } } } }