{ "openapi": "3.0.1", "info": { "title": "PDF to Text, Tables & Markdown (OCR)", "description": "Pull text, tables and Markdown out of PDFs in bulk, with OCR for scanned pages and invoices. One row per page, tables come back as rows you can use straight away, and failed PDFs are never charged.", "version": "0.1", "x-build-id": "UtngSE8tcRYCINv88" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyrun~pdf-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyrun-pdf-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tidyrun~pdf-to-text/runs": { "post": { "operationId": "runs-sync-tidyrun-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tidyrun~pdf-to-text/run-sync": { "post": { "operationId": "run-sync-tidyrun-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "PDF URLs", "type": "array", "description": "Direct links to public PDF files (the link should download the .pdf itself, not a page that shows it).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "ocr": { "title": "OCR (scanned pages)", "enum": [ "auto", "always", "off" ], "type": "string", "description": "Auto reads the PDF's own text where it exists and runs OCR only on scanned pages or pages whose text is unreadable. OCR pages are priced separately.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages printed in your scanned pages. Pick only the ones you need: each extra language makes OCR slower.", "items": { "type": "string", "enum": [ "eng", "tha", "spa", "fra", "deu", "por", "ita", "nld", "ind", "vie" ], "enumTitles": [ "English", "Thai", "Spanish", "French", "German", "Portuguese", "Italian", "Dutch", "Indonesian", "Vietnamese" ] }, "default": [ "eng" ] }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Return tables with ruled grid lines as rows and cells (tables), and as Markdown tables in markdown.", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Markdown with headings, paragraphs in reading order (two-column layouts included) and tables. Handy for LLMs and RAG.", "default": true }, "includePageImages": { "title": "Page-1 preview image", "type": "boolean", "description": "Save a small PNG of the first processed page, shown in the Output tab.", "default": true }, "pageRange": { "title": "Pages", "type": "string", "description": "Optional, e.g. 1-5 or 1, 3, 10-. Leave empty for all pages." }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety cap. Pages after this are skipped (not charged) and the row is flagged truncatedAtMaxPages.", "default": 200 }, "datasetId": { "title": "PDF URLs from a dataset", "type": "string", "description": "Optional ID of a dataset (for example from a scraper run) that holds PDF links. Used together with the URLs above." }, "datasetField": { "title": "Dataset field with the URL", "type": "string", "description": "Field in each dataset item that holds the PDF link (a URL or a list of URLs).", "default": "url" } } }, "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 } } } } } } } } } }