{ "openapi": "3.0.1", "info": { "title": "PDF OCR Tool — Extract Text from Scanned Documents", "description": "Extract text from scanned PDFs and images using Tesseract OCR. 100+ languages, multi-page support. Configurable DPI, page segmentation, language selection. Output as plain text or structured JSON per page.", "version": "1.0", "x-build-id": "iciTHoZhGMrXnRMvj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~pdf-ocr-tool/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-pdf-ocr-tool", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~pdf-ocr-tool/runs": { "post": { "operationId": "runs-sync-junipr-pdf-ocr-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~pdf-ocr-tool/run-sync": { "post": { "operationId": "run-sync-junipr-pdf-ocr-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "List of PDF URLs to process. Each entry is an object with a 'url' field and an optional 'label' for identification.", "default": [ { "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf", "label": "sample" } ] }, "language": { "title": "OCR Language", "enum": [ "eng", "fra", "deu", "spa", "ita", "por", "chi_sim", "jpn", "kor", "ara", "rus" ], "type": "string", "description": "Language used by Tesseract OCR for text recognition. Choose the primary language in your PDFs for best accuracy.", "default": "eng" }, "outputFormat": { "title": "Output Format", "enum": [ "text", "markdown", "json" ], "type": "string", "description": "Format for the extracted text. 'text' returns plain text, 'markdown' adds basic structure hints, 'json' returns structured data.", "default": "text" }, "extractMetadata": { "title": "Extract Metadata", "type": "boolean", "description": "Extract PDF metadata such as title, author, subject, creator, producer, creation date, and modification date.", "default": true }, "pageByPage": { "title": "Page-by-Page Output", "type": "boolean", "description": "When enabled, output includes a 'pages' array with text, character count, and OCR confidence score for each individual page.", "default": true }, "maxPages": { "title": "Max Pages", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to process per PDF. Set to 0 to process all pages. Useful for previewing large documents or managing costs.", "default": 0 }, "dpi": { "title": "OCR Resolution (DPI)", "minimum": 72, "maximum": 600, "type": "integer", "description": "Resolution in DPI used when rendering PDF pages to images for OCR. Higher values improve accuracy on small text but increase processing time.", "default": 300 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of PDFs to process simultaneously. OCR is CPU-intensive, so keep this low to avoid timeouts.", "default": 2 }, "requestTimeout": { "title": "Request Timeout (ms)", "minimum": 10000, "maximum": 600000, "type": "integer", "description": "Timeout in milliseconds for downloading each PDF from a URL. Increase for very large files or slow servers.", "default": 120000 } } }, "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 } } } } } } } } } }