{ "openapi": "3.0.1", "info": { "title": "PDF & Scanned Document to Text, Tables & Fields (OCR)", "description": "Extract text, Markdown, tables and key fields (dates, amounts, invoice numbers) from PDFs and scanned images by URL. Built-in OCR for scanned pages in 11 languages, no external AI or API key. Pay per document and per page.", "version": "1.0", "x-build-id": "3V6dXnOqAXYlidQHV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jakob_jerich~pdf-ocr-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jakob_jerich-pdf-ocr-table-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jakob_jerich~pdf-ocr-table-extractor/runs": { "post": { "operationId": "runs-sync-jakob_jerich-pdf-ocr-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jakob_jerich~pdf-ocr-table-extractor/run-sync": { "post": { "operationId": "run-sync-jakob_jerich-pdf-ocr-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documentUrls" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Direct, public links to the files to extract: PDF (text or scanned), PNG, JPEG, TIFF (multi-page), WEBP, GIF or BMP. Up to 1,000 URLs per run. The link must download the file itself, not an HTML page that shows it.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "When to run OCR (optical character recognition). 'auto' reads the PDF's own text layer and runs OCR only on pages that have no usable text (scanned pages). 'always' OCRs every page, which helps with PDFs whose text layer is garbled. 'never' only reads the text layer (fastest, cheapest; images return no text). Images are always OCR-ed unless set to 'never'.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned text, used by OCR. Pick the languages that appear in your documents (max 4); fewer languages are faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "slv", "hrv" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Slovenian", "Croatian" ] }, "default": [ "eng" ] }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables on text-based PDF pages and return them as rows and columns (plus a Markdown version). Works on tables with ruled lines/borders; not on scanned (OCR) pages.", "default": true }, "extractFields": { "title": "Extract key fields", "type": "boolean", "description": "Find dates (normalized to ISO 8601), money amounts with currency, percentages, URLs, reference numbers (invoice, order, PO, contract no.) and 'Label: value' pairs. Personal data such as e-mails, phone numbers and names is never extracted.", "default": true }, "includeFullText": { "title": "Include full text and Markdown", "type": "boolean", "description": "Add the whole document as plain text ('text') and as LLM/RAG-ready Markdown with tables ('markdown').", "default": true }, "includePages": { "title": "Include per-page results", "type": "boolean", "description": "Add a 'pages' array with the text, Markdown, extraction method (text layer or OCR) and OCR confidence of each page. Turn off to get smaller results.", "default": true }, "pageRange": { "title": "Page range", "type": "string", "description": "Optional. Only process these pages of each document, e.g. '1-3, 5, 10-' (10- means page 10 to the end). Leave empty for all pages." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety limit: at most this many pages are processed per document (after applying the page range). The output says when a document was cut off.", "default": 50 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this are skipped with a clear error instead of being downloaded.", "default": 50 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents to process at the same time. Higher is faster for many small files but needs more memory (use 2 GB+ memory for 4 or more).", "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 } } } } } } } } } }