{ "openapi": "3.0.1", "info": { "title": "PDF to Text & OCR – PDF & Image Text Extraction (Erdnal)", "description": "PDF to text and OCR: extract text from PDFs, scanned PDFs and JPEG/PNG images (image to text) by URL, page by page, as JSON, text or Markdown. Optional invoice to JSON. EU-hosted, documents not kept. Pay per page.", "version": "0.1", "x-build-id": "kbAuYtz5OGDLdfjZZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/erdnal_api~erdnal-documents-text-extraction/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-erdnal_api-erdnal-documents-text-extraction", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/erdnal_api~erdnal-documents-text-extraction/runs": { "post": { "operationId": "runs-sync-erdnal_api-erdnal-documents-text-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/erdnal_api~erdnal-documents-text-extraction/run-sync": { "post": { "operationId": "run-sync-erdnal_api-erdnal-documents-text-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "minItems": 1, "maxItems": 500, "type": "array", "description": "Public https:// URLs of the PDF, JPEG or PNG files to read, one per line (1 to 500 per run, 20 MB per file, up to 3 redirects, e.g. download links). Each file becomes one row of the output.", "items": { "type": "string" } }, "extract": { "title": "What to extract", "enum": [ "text", "invoice" ], "type": "string", "description": "Text (default): the text of every page, read from the PDF text layer or by OCR for scans. Invoice data: invoice or receipt fields as JSON (number, dates, supplier and VAT number, customer, currency, subtotal, tax lines, total, line items); costs 5 extra credits per page and sends the extracted text to an AI model (Anthropic).", "default": "text" }, "mode": { "title": "Extraction mode", "enum": [ "auto", "text", "ocr" ], "type": "string", "description": "Auto (default, cheapest and most accurate): pages with a text layer are read directly, only scanned pages go through OCR. Text: never use OCR (scanned pages come back empty). OCR: run OCR on every page, even when a text layer exists (useful if the text layer is broken).", "default": "auto" }, "languages": { "title": "OCR languages", "minItems": 1, "maxItems": 3, "type": "array", "description": "Languages of your documents, used by OCR only (1 to 3). Choose only the languages actually present: each extra language makes OCR slower. Default English and French.", "items": { "type": "string", "enum": [ "eng", "fra", "deu", "spa", "ita", "por", "nld" ], "enumTitles": [ "English", "French", "German", "Spanish", "Italian", "Portuguese", "Dutch" ] }, "default": [ "eng", "fra" ] }, "pages": { "title": "Pages", "type": "string", "description": "Pages to extract, e.g. 1-3,7 (numbers start at 1). Leave empty for all pages (200 at most). A document can have at most 5 pages read by OCR per run: split long scanned documents with page ranges." }, "includePages": { "title": "Include page details", "type": "boolean", "description": "On (default): add the text, method (text layer or OCR) and OCR confidence of each page, besides the full text. Off: only the full text, for smaller output.", "default": true } } }, "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 } } } } } } } } } }