{ "openapi": "3.0.1", "info": { "title": "Scanned PDF OCR: Searchable PDF + Text", "description": "Turn scanned PDFs and images into searchable PDFs: OCR adds an invisible text layer and keeps every page looking the same, so files can be searched, copied and indexed where they are. Also returns the text of each page. 16 languages, PDF/A option.", "version": "0.1", "x-build-id": "Ok1dwprCSjmhSEIMi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/iiclabs~scanned-pdf-ocr-searchable/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-iiclabs-scanned-pdf-ocr-searchable", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/iiclabs~scanned-pdf-ocr-searchable/runs": { "post": { "operationId": "runs-sync-iiclabs-scanned-pdf-ocr-searchable", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/iiclabs~scanned-pdf-ocr-searchable/run-sync": { "post": { "operationId": "run-sync-iiclabs-scanned-pdf-ocr-searchable", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "files" ], "properties": { "files": { "title": "Files", "type": "array", "description": "URLs of scanned PDFs or images (JPEG, PNG, TIFF), up to 200 MB each.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "The languages in the documents. Choose only the ones present: each extra language slows OCR down.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "swe", "dan", "nor", "fin", "tur", "ron", "hun" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Swedish", "Danish", "Norwegian", "Finnish", "Turkish", "Romanian", "Hungarian" ] }, "default": [ "eng" ] }, "mode": { "title": "Pages that already have text", "enum": [ "skip-text", "redo-ocr", "force-ocr" ], "type": "string", "description": "Skip keeps a page's existing text layer (born-digital pages are charged at the lower text-page price). Redo replaces old OCR text but keeps real text. Force OCRs every page again (the page is turned into an image).", "default": "skip-text" }, "rotatePages": { "title": "Fix page rotation", "type": "boolean", "description": "Turns sideways or upside-down pages upright (not with Redo).", "default": true }, "pdfA": { "title": "PDF/A for archiving", "type": "boolean", "description": "Save PDF/A-2b instead of a regular PDF.", "default": false }, "optimize": { "title": "File size", "enum": [ "0", "1", "2" ], "type": "string", "description": "Keep images as they are, optimise losslessly (safe), or compress images more.", "default": "1" }, "includeText": { "title": "Text per page in the dataset", "type": "boolean", "description": "Also return each page's text, for search indexes and AI pipelines.", "default": true }, "maxPagesPerFile": { "title": "Maximum pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Longer PDFs are refused (not charged).", "default": 500 } } }, "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 } } } } } } } } } }