{ "openapi": "3.0.1", "info": { "title": "Article to Clean Markdown & JSONL for AI", "description": "Extract Japanese and English articles into clean Markdown, JSONL, structured metadata, and RAG-ready chunks. Static-first with optional browser fallback.", "version": "0.1", "x-build-id": "FJaOWmKcVKhWNB0w2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fxosie-create~article-to-clean-markdown-jsonl/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fxosie-create-article-to-clean-markdown-jsonl", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fxosie-create~article-to-clean-markdown-jsonl/runs": { "post": { "operationId": "runs-sync-fxosie-create-article-to-clean-markdown-jsonl", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fxosie-create~article-to-clean-markdown-jsonl/run-sync": { "post": { "operationId": "run-sync-fxosie-create-article-to-clean-markdown-jsonl", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public HTTP(S) article or listing URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of pages processed in one run.", "default": 20 }, "renderMode": { "title": "Render mode", "enum": [ "auto", "static", "browser" ], "type": "string", "description": "auto: Static extraction first. Browser rendering is used only when necessary and can incur the browser surcharge. static: Lowest-cost option. JavaScript-only content may not be extracted. browser: Uses browser rendering and incurs the browser surcharge for each successful article.", "default": "auto" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "JSON is always stored in the dataset.", "items": { "type": "string", "enum": [ "json", "jsonl", "markdown", "cleanText", "html" ] }, "default": [ "json", "jsonl", "markdown" ] }, "generateChunks": { "title": "Generate RAG chunks", "type": "boolean", "description": "Generate Japanese-aware text and Markdown chunks for downstream RAG use.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Approximate maximum number of characters in each generated chunk.", "default": 1400 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only enqueue links on the start URL's registered domain.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Enabled by default. Disabling this does not waive site terms, copyright, or legal obligations.", "default": true }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "Maximum link depth from each start URL.", "default": 1 }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Allow subdomains when same-domain crawling is enabled.", "default": false }, "minArticleWords": { "title": "Minimum article words", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Minimum extracted word or Japanese character-unit count for a usable article.", "default": 80 }, "removeNavigation": { "title": "Remove navigation", "type": "boolean", "description": "Remove common navigation and breadcrumb elements before extraction.", "default": true }, "removeAdvertisements": { "title": "Remove advertisements", "type": "boolean", "description": "Remove common advertisement elements before extraction.", "default": true }, "removeRelatedArticles": { "title": "Remove related/recommended articles", "type": "boolean", "description": "Remove common related and recommended article blocks before extraction.", "default": true }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Include article image metadata in each result.", "default": true }, "includeLinks": { "title": "Include outbound links", "type": "boolean", "description": "Include normalized outbound links found in the extracted article.", "default": true }, "includeJsonLd": { "title": "Include JSON-LD", "type": "boolean", "description": "Include parsed JSON-LD objects found in the page.", "default": true }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Approximate number of characters repeated between adjacent chunks.", "default": 150 }, "languageHint": { "title": "Language hint", "type": "string", "description": "Optional BCP-47-style hint such as ja or en.", "default": "" }, "requestTimeoutSeconds": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout for static and browser retrieval.", "default": 30 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum simultaneous page tasks. URL count alone does not increase memory. Keep this low and use the request interval to avoid target-site load.", "default": 3 }, "maxBrowserConcurrency": { "title": "Maximum browser concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "Maximum simultaneous browser renderers for auto/browser mode. Effective browser concurrency is the lowest of this value, maxConcurrency, and expected browser work. One or two uses 2048 MB; three or four selects 4096 MB. Ignored by static extraction at runtime.", "default": 2 }, "expectedBrowserFallbacks": { "title": "Expected browser fallbacks", "minimum": 0, "maximum": 500, "type": "integer", "description": "Planning estimate used only for memory selection. Use 0 for static, estimate auto fallbacks, and use the planned page count for browser mode. A large URL list stays at 2048 MB when browser concurrency is 1-2.", "default": 1 }, "maxHtmlBytes": { "title": "Maximum HTML bytes per page", "minimum": 250000, "maximum": 12000000, "type": "integer", "description": "Maximum accepted HTML response size. Up to 6,000,000 bytes uses 2048 MB; a higher limit selects 4096 MB.", "default": 6000000 }, "minRequestIntervalMillis": { "title": "Minimum interval per website (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Minimum delay between page requests to the same origin. Use a larger value when a site's policy requires it.", "default": 500 } } }, "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 } } }, "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 } } } } } } } } } }