{ "openapi": "3.0.1", "info": { "title": "Searchable PDF OCR — Add a Text Layer to Scanned PDFs", "description": "Turn scanned or image-only PDFs into fully searchable, selectable, copy-pasteable PDFs. Keeps the original page image untouched and adds an invisible OCR text layer underneath.", "version": "0.1", "x-build-id": "qfj3EhH26C8wHraRY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/northbound_works~searchable-pdf-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-northbound_works-searchable-pdf-ocr", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/northbound_works~searchable-pdf-ocr/runs": { "post": { "operationId": "runs-sync-northbound_works-searchable-pdf-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/northbound_works~searchable-pdf-ocr/run-sync": { "post": { "operationId": "run-sync-northbound_works-searchable-pdf-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "pdfUrls" ], "properties": { "pdfUrls": { "title": "PDF URLs", "minItems": 1, "type": "array", "description": "Direct links to the PDFs you want to make searchable. Each must be a publicly reachable URL ending in a PDF file — not a viewer page. The original page images are preserved exactly; an invisible text layer is added underneath.", "items": { "type": "string" } }, "language": { "title": "Document language", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "nld", "pol", "rus", "ukr", "tur", "ara", "hin", "jpn", "kor", "chi_sim", "chi_tra", "vie", "ind", "swe", "dan", "nor", "fin", "ces", "ell", "heb" ], "type": "string", "description": "Language of the text in the scans. Picking the right one materially improves accuracy — English OCR on a German document produces garbage.", "default": "eng" }, "mode": { "title": "How to handle pages that already have text", "enum": [ "skip-text", "force-ocr", "redo-ocr" ], "type": "string", "description": "Most PDFs are a mix. 'Skip' is the safe default and the cheapest — it only OCRs pages that genuinely have no text, and you are only charged for those. Use 'Force' when a PDF has a bad existing text layer you want replaced.", "default": "skip-text" }, "deskew": { "title": "Straighten crooked scans", "type": "boolean", "description": "Rotates slightly tilted pages back to level before reading them. Improves accuracy on photographed or hand-fed scans. Leave on unless your scans are already perfectly square.", "default": true }, "rotatePages": { "title": "Auto-correct page orientation", "type": "boolean", "description": "Detects sideways or upside-down pages and rotates them upright.", "default": true }, "cleanBeforeOcr": { "title": "Clean up speckle before reading", "type": "boolean", "description": "Removes scanner noise and speckle to help the reader. The cleaning is used only for recognition — the page you get back is still your original image, untouched.", "default": false }, "optimize": { "title": "Output file size optimisation", "enum": [ "0", "1", "2", "3" ], "type": "string", "description": "How hard to compress the resulting PDF. Levels above 1 can visibly soften images, so leave it at 1 unless file size matters more than fidelity.", "default": "1" }, "includeTextInDataset": { "title": "Also return the extracted text", "type": "boolean", "description": "Puts the full recognised text of each document into the dataset alongside the download link, so you can search or process it without opening the PDF.", "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 } } }, "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 } } } } } } } } } }