{ "openapi": "3.0.1", "info": { "title": "Document Text Extractor: PDF, Word, Excel to Markdown", "description": "Turn PDF, DOCX, PPTX, XLSX, HTML, CSV and EPUB files into clean Markdown or plain text, with page counts, metadata and optional RAG-ready chunks. Failed documents are free.", "version": "1.0", "x-build-id": "qY1mAE8PSUXq0cF5H" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pipwort~document-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pipwort-document-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pipwort~document-text-extractor/runs": { "post": { "operationId": "runs-sync-pipwort-document-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pipwort~document-text-extractor/run-sync": { "post": { "operationId": "run-sync-pipwort-document-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "documentUrls" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to the files (PDF, DOCX, PPTX, XLSX, XLS, HTML, CSV, JSON, XML, TXT, MD, EPUB). You can also upload a text file with one URL per line.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps headings, lists and tables. Plain text strips formatting.", "default": "markdown" }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Set above 0 to also return the text split into chunks on paragraph boundaries, ready for embeddings. 0 turns chunking off.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Characters repeated from the end of the previous chunk.", "default": 0 }, "includePages": { "title": "Include per-page text (PDF)", "type": "boolean", "description": "Add an array with the text of each PDF page.", "default": false }, "cleanLayoutNoise": { "title": "Clean PDF layout noise", "type": "boolean", "description": "Remove runs of one-letter lines (rotated margin text) and stray dots that PDF extraction often produces.", "default": true }, "maxPagesPerDocument": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "0 means all pages. Useful to cap cost on very long PDFs.", "default": 0 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped with a clear error (not charged).", "default": 50 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many files to process at once.", "default": 4 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Per download.", "default": 60 }, "conversionTimeoutSecs": { "title": "Conversion timeout (seconds)", "minimum": 10, "maximum": 1800, "type": "integer", "description": "Per document.", "default": 180 }, "maxRetries": { "title": "Download retries", "minimum": 0, "maximum": 6, "type": "integer", "description": "Retries on timeouts, 429 and 5xx responses.", "default": 3 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Optional custom User-Agent header for downloads." } } }, "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 } } } } } } } } } }