{ "openapi": "3.0.1", "info": { "title": "Inkpluck — Article Extractor: URL to Text, Markdown & Metadata", "description": "Article extractor API for news, blogs and docs: URLs or HTML in, clean text + Markdown, title, authors, publish date, language, top image, videos and paywall flag out. newspaper3k-compatible fields. $0.001 per article; failures free.", "version": "0.1", "x-build-id": "QSKk2XgFMc6ZWEYQ2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cybermax~article-extract/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cybermax-article-extract", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cybermax~article-extract/runs": { "post": { "operationId": "runs-sync-cybermax-article-extract", "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/cybermax~article-extract/run-sync": { "post": { "operationId": "run-sync-cybermax-article-extract", "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": { "urls": { "title": "Article URLs", "type": "array", "description": "News articles, blog posts or docs pages to extract. One URL per line; the scheme is optional (\"example.com/post\" works). Duplicates are skipped.", "items": { "type": "string" } }, "feedUrls": { "title": "RSS/Atom feeds to watch", "type": "array", "description": "Feed URLs (e.g. https://techcrunch.com/feed/). Inkpluck reads each feed and extracts its newest articles. Combine with \"Only new articles\" and an Apify Schedule to get each new article once, as Markdown, every day.", "items": { "type": "string" } }, "maxArticlesPerFeed": { "title": "Articles per feed", "minimum": 1, "maximum": 200, "type": "integer", "description": "Newest items taken from each feed.", "default": 20 }, "onlyNew": { "title": "Only new articles (monitor mode)", "type": "boolean", "description": "Skip URLs this monitor already extracted in earlier runs (skips are free and produce no record). Memory is kept in a named key-value store per monitor name in your account.", "default": false }, "monitorName": { "title": "Monitor name", "type": "string", "description": "Separate memories for separate watch lists, e.g. \"ai-news\" or \"competitor-blogs\". Letters, digits and dashes.", "default": "default" }, "htmlDocuments": { "title": "Raw HTML documents (optional)", "type": "array", "description": "Already have the HTML? Pass [{\"url\": \"https://site.com/post\", \"html\": \"...\"}] and Inkpluck extracts it without fetching. The URL is used to resolve relative links and dates." }, "onlyArticles": { "title": "Only charge for real articles", "type": "boolean", "description": "Home pages, section pages (/news, /tech) and link lists are returned as free failures instead of extracted pages. Turn on when feeding crawled link lists; leave off to extract any page's main text.", "default": false }, "outputMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Add a `markdown` field (headings, lists, links, images and tables kept) next to the plain `text`. Ideal for LLM/RAG pipelines.", "default": true }, "includeHtml": { "title": "Include cleaned article HTML", "type": "boolean", "description": "Add an `html` field with the article body only (no navigation, ads or footer).", "default": false }, "newspaper3kFields": { "title": "Add newspaper3k field names", "type": "boolean", "description": "Also output newspaper3k's attribute names (publish_date, top_image, movies, meta_lang, meta_description, meta_keywords, canonical_link, source_url) so existing newspaper3k code keeps working.", "default": false }, "minWords": { "title": "Minimum words for a successful extraction", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages with fewer words of article text are reported as failures (free).", "default": 50 }, "maxConcurrency": { "title": "Pages in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many pages are fetched and extracted at the same time.", "default": 10 }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Give up on a page after this many seconds (one automatic retry on network errors and 5xx).", "default": 20 }, "retryBlockedWithProxy": { "title": "Retry blocked pages through Apify Proxy", "type": "boolean", "description": "When a site answers 403/429/503 to a direct request, try once more through Apify Proxy (uses your account's proxy).", "default": true }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Send every request through this proxy (e.g. residential for sites that block datacenters). Leave empty for direct requests with the automatic retry above.", "default": { "useApifyProxy": false } }, "startUrls": { "title": "Start URLs (compatibility)", "type": "array", "description": "Same as Article URLs, in the [{\"url\": ...}] format other Actors use.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } } } }, "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 } } } } } } } } } }