{ "openapi": "3.0.1", "info": { "title": "Bulk OCR: Images & Scanned PDFs to Text (Tesseract)", "description": "Turn scanned PDFs and images (PNG, JPEG, TIFF, WebP) into text with the open-source Tesseract OCR engine: one row per page with words and confidence. 9 languages. PDFs that already contain text are read directly. Pay per page with text; blank pages are free.", "version": "0.1", "x-build-id": "RLZ8Tf474M4dGwynq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/stellalytics~bulk-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-stellalytics-bulk-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/stellalytics~bulk-ocr/runs": { "post": { "operationId": "runs-sync-stellalytics-bulk-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/stellalytics~bulk-ocr/run-sync": { "post": { "operationId": "run-sync-stellalytics-bulk-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "fileUrls": { "title": "File links", "type": "array", "description": "Direct links to your images (PNG, JPEG, TIFF, GIF, BMP, WebP) or PDFs, one per line. Each file is downloaded once. Use only files you have the right to process.", "items": { "type": "string" } }, "keyValueStoreId": { "title": "Key-value store with your files", "type": "string", "description": "Optional: a key-value store whose image and PDF records should be read, for example one you uploaded scans to in Apify Console. The Actor only reads it." }, "languages": { "title": "Languages in the documents", "type": "array", "description": "Pick every language that appears. More languages make reading a little slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "tur" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Turkish" ] }, "default": [ "eng" ] }, "useTextLayer": { "title": "Use a PDF's own text when it has one", "type": "boolean", "description": "PDF pages that already contain text (not scans) are read directly, which is exact and fast. Turn off to OCR every page as an image.", "default": true }, "pdfDpi": { "title": "PDF scan resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution used to turn PDF pages into images before OCR. 300 suits most scans; use 400 for small print.", "default": 300 }, "maxPagesPerFile": { "title": "Maximum pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Later pages of longer files are skipped (and not charged).", "default": 100 }, "maxPages": { "title": "Maximum pages to read in this run", "minimum": 0, "type": "integer", "description": "Caps the cost: the run stops after this many charged pages. 0 means no limit (your maximum cost per run still applies).", "default": 0 } } }, "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 } } } } } } } } } }