{ "openapi": "3.0.1", "info": { "title": "Document to Markdown API: DOCX, XLSX, PPTX, No Login", "description": "Convert public DOCX, XLSX, PPTX, CSV and HTML files to clean Markdown from a URL. One row per document with title, headings, word count and warnings. No login, no API key, no OCR. A URL that fails is returned as an error row and is not charged.", "version": "0.0", "x-build-id": "dMM9ZNriEubV6vxNJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/conserving_celerytop~document-to-markdown-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-conserving_celerytop-document-to-markdown-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/conserving_celerytop~document-to-markdown-api/runs": { "post": { "operationId": "runs-sync-conserving_celerytop-document-to-markdown-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/conserving_celerytop~document-to-markdown-api/run-sync": { "post": { "operationId": "run-sync-conserving_celerytop-document-to-markdown-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Document URLs", "maxItems": 1000, "type": "array", "description": "Enter one public file URL per line. The file must open without a login. Supported: DOCX, XLSX, PPTX, CSV and HTML. Old .doc, .xls and .ppt files, PDF files and images are not supported.", "items": { "type": "string" } }, "listDatasetId": { "title": "Dataset with the list", "type": "string", "description": "Pick an Apify Dataset that holds your file addresses, one entry per item. They are added to the entries typed above." }, "listDatasetField": { "title": "Field in the dataset", "type": "string", "description": "Name of the dataset field that holds the entry. Leave empty to use the first text field it finds." }, "listFileUrl": { "title": "List file URL", "type": "string", "description": "Web address of a .txt, .csv or .json file with your file addresses, one entry per line. A header row is skipped. Up to 10 MB." }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many converted rows. Each converted row is one charged result. Rows with status error do not count and are not charged.", "default": 100 }, "sheetsAs": { "title": "Spreadsheet output", "enum": [ "one-row-per-document", "one-row-per-sheet" ], "type": "string", "description": "Choose how an XLSX workbook is returned. One row per workbook puts every sheet into one row. One row per sheet returns each sheet as its own row, and each row is charged.", "default": "one-row-per-document" }, "maxRowsPerSheet": { "title": "Max rows per sheet", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Keep at most this many rows of each XLSX sheet and of each CSV file. A warning says when rows were left out.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 50, "type": "integer", "description": "Reject a file that is larger than this many megabytes. The size is checked while the file downloads. The hard limit is 50 MB.", "default": 25 }, "timeoutSeconds": { "title": "Timeout per URL (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Total time allowed to download one URL, including redirects and retries.", "default": 60 }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Off by default: an image is shown as [Image: alt text] and only counted. On: images inside DOCX and PPTX files are embedded as base64 data (up to 300 KB each and 4 MB in total), and HTML images keep their address.", "default": false } } }, "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 } } } } } } } } } }