{ "openapi": "3.0.1", "info": { "title": "Office Text Extractor - DOCX, XLSX, PPTX, ODT, ODP & RTF", "description": "Extract text and structured JSON from DOCX, XLSX, PPTX, ODT, ODP and RTF files. Includes Word tables, Excel rows, PowerPoint slide text, tables and speaker notes. Batch up to 50 files from direct URLs, Google Drive or Dropbox.", "version": "0.6", "x-build-id": "30gzVyYThjpnXMcyA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gochujang~docx-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gochujang-docx-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gochujang~docx-text-extractor/runs": { "post": { "operationId": "runs-sync-gochujang-docx-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gochujang~docx-text-extractor/run-sync": { "post": { "operationId": "run-sync-gochujang-docx-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "File URLs", "type": "array", "description": "List of .docx, .xlsx, .pptx, .odt, .odp or .rtf URLs to download and extract. Supports Google Drive and Dropbox share links.", "default": [], "items": { "type": "string" } }, "urlsText": { "title": "File URLs (paste, one per line)", "type": "string", "description": "Alternative to the URLs list — paste multiple .docx/.xlsx/.pptx/.odt/.odp/.rtf URLs, one per line. Merged with 'urls' if both provided.", "default": "" }, "url": { "title": "Single File URL", "type": "string", "description": "Single .docx, .xlsx, .pptx, .odt, .odp or .rtf URL. Used when 'urls' is empty.", "default": "" }, "outputFormat": { "title": "Output format", "enum": [ "full", "summary" ], "type": "string", "description": "full: include all text, paragraphs, tables, and rows. summary: metadata + truncated text only (faster, smaller output).", "default": "full" }, "includeMetadata": { "title": "Include Metadata", "type": "boolean", "description": "Include document metadata: author, created date, last modified date, last modified by. Always included for DOCX files.", "default": true }, "changeDetection": { "title": "Enable Change Detection", "type": "boolean", "description": "Compare document content hash against the previous run stored in KVS. Sets content_changed=true and is_new_document=true on each output record. Use with a named Key-Value Store to persist state across runs.", "default": false }, "telegramBotToken": { "title": "Telegram Bot Token", "type": "string", "description": "Optional. Telegram bot token (from @BotFather). When changeDetection=true and a document changes, sends a Telegram alert." }, "telegramChatId": { "title": "Telegram Chat ID", "type": "string", "description": "Optional. Telegram chat/channel ID to send alerts to. Required when telegramBotToken is set." }, "maxRowsPerSheet": { "title": "Max rows per sheet (Excel)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "For Excel files: maximum rows to extract per sheet.", "default": 1000 }, "limit": { "title": "Max files", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum files to process (max 50).", "default": 50 } } }, "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 } } } } } } } } } }