{ "openapi": "3.0.1", "info": { "title": "OCR: Images & Scanned PDFs to Text", "description": "OCR for images and scanned PDFs: per-page text, a confidence score and optional word boxes, in 27 languages (Tesseract). Give file URLs or a key-value store. Pages with no text and failed files are not charged.", "version": "0.1", "x-build-id": "o9a6pES7dSmjMYbc9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datagleaner~ocr-images-pdfs/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datagleaner-ocr-images-pdfs", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datagleaner~ocr-images-pdfs/runs": { "post": { "operationId": "runs-sync-datagleaner-ocr-images-pdfs", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datagleaner~ocr-images-pdfs/run-sync": { "post": { "operationId": "run-sync-datagleaner-ocr-images-pdfs", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Direct links to image or PDF files, one per line. Each must download without a login. The host's robots.txt is respected. Links on social networks and other sites whose terms forbid automated downloads are refused. Leave empty (with no key-value store) to read a built-in 3-page sample scan.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyValueStoreId": { "title": "Key-value store ID (your uploaded files)", "type": "string", "description": "Optional. A key-value store whose records are images or PDFs, for example files you uploaded in Apify Console (Storage > Key-value stores) or another run's store (`{{resource.defaultKeyValueStoreId}}` in an integration). Without keys below, every image or PDF record in the store is read and other records are skipped." }, "keyValueStoreKeys": { "title": "Record keys", "type": "array", "description": "Optional. Only these record keys of the key-value store above.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "The languages printed in the files, up to 5 (more makes OCR slower and less accurate). Pick every language a page mixes, e.g. English and German. Default: English.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "swe", "dan", "nor", "fin", "tur", "rus", "ukr", "ell", "ara", "heb", "hin", "tha", "vie", "ind", "chi_sim", "chi_tra", "jpn", "kor" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Swedish", "Danish", "Norwegian", "Finnish", "Turkish", "Russian", "Ukrainian", "Greek", "Arabic", "Hebrew", "Hindi", "Thai", "Vietnamese", "Indonesian", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean" ] }, "default": [ "eng" ] }, "includeWordBoxes": { "title": "Include word boxes", "type": "boolean", "description": "Add a `words` array per page: each word with its confidence and pixel box (left, top, width, height) and its block, paragraph and line number, for highlighting, redaction or layout work.", "default": false }, "pageSegmentationMode": { "title": "Page layout", "enum": [ "auto", "single_column", "single_block", "single_line", "sparse" ], "type": "string", "description": "How the page is split into text before reading. Automatic suits most scans; try Sparse for screenshots and photos, One uniform block for receipts.", "default": "auto" }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "PDF pages are rendered at this resolution before OCR. 300 is the standard; use 400 for small print, 200 for speed on large text.", "default": 300 }, "pageRange": { "title": "Page range", "type": "string", "description": "Optional, 1-based, applied to every file: for example 1-5, 8, 10-12 or 3- (page 3 to the end). Empty means all pages." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Only the first N selected pages of each file are read; pageCount still shows the full length.", "default": 100 }, "maxPages": { "title": "Max pages in total", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Upper bound on pages read in this run, across all files: your cost cap.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Larger files are skipped with an error and not billed.", "default": 50 }, "maxConcurrency": { "title": "Files in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many files are downloaded and read at once. OCR is CPU-bound: more memory gives the run more CPU, so raise both together.", "default": 2 } } }, "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 } } } } } } } } } }