{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor & Document to Markdown (Word, Excel, PPT)", "description": "Extract text from PDF, Word, PowerPoint, Excel, HTML and EPUB files as clean, LLM-ready Markdown. Batch file URLs, tables kept, pay only for documents that convert. Built for RAG and AI agents.", "version": "1.1", "x-build-id": "BPfjaW4iitP0uoqfH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pavel.tashev~doc-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pavel.tashev-doc-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pavel.tashev~doc-to-markdown/runs": { "post": { "operationId": "runs-sync-pavel.tashev-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pavel.tashev~doc-to-markdown/run-sync": { "post": { "operationId": "run-sync-pavel.tashev-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "fileUrls" ], "properties": { "fileUrls": { "title": "File URLs", "type": "array", "description": "Direct links to the documents you want to convert. Supports PDF (including scanned PDFs), Word (.docx), PowerPoint (.pptx), Excel (.xlsx), HTML, EPUB, CSV, JSON, XML, plain text and images (PNG, JPG, TIFF, WebP, BMP). You can paste many URLs or 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" } } } }, "includeMarkdown": { "title": "Include Markdown in output", "type": "boolean", "description": "Turn off to return only metadata (file type, title, word count) without the converted text.", "default": true }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "off", "force" ], "type": "string", "description": "OCR reads text from images and from PDF pages that have no text layer (scans). \"Auto\" runs OCR only where it is needed, \"Off\" never runs it (scanned pages come back empty and images fail), \"Force\" OCRs every PDF page even if it already has text. OCR pages are charged separately.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the text in your scans and images. Pick the ones that appear in the documents (up to 5); each extra language makes OCR slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "bul", "ron", "ces", "rus", "ukr", "tur" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Bulgarian", "Romanian", "Czech", "Russian", "Ukrainian", "Turkish" ] }, "default": [ "eng" ] }, "maxOcrPagesPerFile": { "title": "Maximum OCR pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop OCR after this many pages in one file. Pages beyond the limit are left out and the result is marked as truncated.", "default": 200 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this are skipped and not charged.", "default": 50 }, "maxConcurrency": { "title": "Files processed in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many documents to download and convert at the same time. Higher is faster but uses more memory.", "default": 5 } } }, "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 } } } } } } } } } }