{ "openapi": "3.0.1", "info": { "title": "Pandoc Document Converter - HTML to Markdown, DOCX, EPUB, PPTX", "description": "Convert documents between formats with Pandoc in the cloud: HTML to Markdown for LLMs and RAG, Markdown to Word DOCX, EPUB e-books, PowerPoint PPTX, LaTeX, reStructuredText and more. Feed it URLs or raw text, get one converted document per input.", "version": "0.1", "x-build-id": "0akg9blNPvCAqSLyV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeworks~pandoc-document-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeworks-pandoc-document-converter", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapeworks~pandoc-document-converter/runs": { "post": { "operationId": "runs-sync-scrapeworks-pandoc-document-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapeworks~pandoc-document-converter/run-sync": { "post": { "operationId": "run-sync-scrapeworks-pandoc-document-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs to fetch and convert", "type": "array", "description": "Web pages or raw files to download and convert. Each URL becomes one converted document in the dataset. The input format is auto-detected from the response (HTML pages, .md files, etc.) unless you override it with 'Input format'.", "items": { "type": "string" } }, "texts": { "title": "Raw texts to convert", "type": "array", "description": "Raw document contents to convert (e.g. Markdown or HTML strings). Each entry becomes one converted document in the dataset. Use this when you already have the content and don't need fetching." }, "inputFormat": { "title": "Input format", "enum": [ "auto", "html", "markdown", "gfm", "commonmark", "latex", "rst", "org", "mediawiki", "textile", "docbook", "opml", "csv" ], "type": "string", "description": "Format of the source documents. 'auto' detects HTML vs Markdown per item (from the HTTP Content-Type, file extension, or content). Set explicitly when converting LaTeX, reStructuredText, Org, MediaWiki, Textile, DocBook, OPML or CSV.", "default": "auto" }, "outputFormat": { "title": "Output format", "enum": [ "gfm", "markdown", "commonmark", "html", "plain", "docx", "pptx", "epub", "odt", "rtf", "rst", "latex", "asciidoc", "org", "mediawiki", "textile", "opml" ], "type": "string", "description": "Format to convert every document into. Text formats (Markdown, HTML, plain text, LaTeX, ...) are returned inline in the dataset; binary formats (DOCX, PPTX, EPUB, ODT) are stored in the run's key-value store and the dataset row contains a direct download URL.", "default": "gfm" }, "standalone": { "title": "Standalone document", "type": "boolean", "description": "Produce a complete document with header and metadata (e.g. a full HTML page with , or an RTF/LaTeX document that compiles on its own) instead of a fragment. Binary formats (DOCX, PPTX, EPUB, ODT) are always standalone.", "default": false }, "documentTitle": { "title": "Document title", "type": "string", "description": "Title metadata embedded in standalone and binary outputs (shown e.g. as the EPUB book title or DOCX document title). If empty, the source URL or 'Converted document' is used.", "default": "" } } }, "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 } } } } } } } } } }