{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: Text, Pages & Metadata from PDF (OCR)", "description": "Extract the text of any PDF (native or scanned with OCR), Word, PowerPoint, Excel or web page: full text, text per page, page count, title, author and dates as JSON, CSV or Excel. Bulk URLs or uploads, no API key. Pay per document.", "version": "1.0", "x-build-id": "vn8a9RNDp8Ozj7Y7e" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fguiraud~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fguiraud-pdf-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fguiraud~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-fguiraud-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fguiraud~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-fguiraud-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "sources": { "title": "Document URLs", "type": "array", "description": "Document URLs. Supported: PDF (native or scanned), DOCX, XLSX, XLS, PPTX, HTML pages, CSV, TXT and images. Share links from Google Drive, Google Docs/Sheets/Slides, Dropbox, OneDrive/SharePoint and GitHub are converted to downloads automatically (the file must be shared as 'Anyone with the link'). The real file type is detected from the content.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "base64Files": { "title": "Files as base64 (optional)", "type": "array", "description": "For files that are not reachable by URL, e.g. from an AI agent or a local script: a list of objects {\"fileName\": \"report.pdf\", \"content\": \"\"}. A data: URI is also accepted as content. Keep the total input under ~9 MB; use URLs for bigger files." }, "outputs": { "title": "What to return", "type": "array", "description": "Fields to include for each document. 'text': the whole document as plain text. 'pages': the text of each page (or slide/sheet). 'markdown': LLM-ready Markdown with headings and tables. 'tables': every table as header + rows + CSV. 'chunks': text split into RAG chunks with page numbers.", "items": { "type": "string", "enum": [ "markdown", "tables", "text", "pages", "chunks" ], "enumTitles": [ "Markdown", "Tables (JSON + CSV)", "Plain text", "Per-page content", "RAG chunks" ] }, "default": [ "text", "pages" ] }, "ocr": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "'auto': run OCR only on scanned pages that contain no text (recommended). 'always': OCR every page, even if it has a text layer. 'never': no OCR (images and scanned pages return no text). OCR pages are billed separately.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned text. Adding more languages is slightly slower.", "items": { "type": "string", "enum": [ "eng", "spa", "deu", "fra", "por", "ita", "nld" ], "enumTitles": [ "English", "Spanish", "German", "French", "Portuguese", "Italian", "Dutch" ] }, "default": [ "eng" ] }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to process, e.g. '1-5, 8'. Applies to PDF pages, PowerPoint slides and Excel sheets. Leave empty for all." }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit on pages processed per document.", "default": 500 }, "removeHeadersFooters": { "title": "Remove running headers and footers", "type": "boolean", "description": "Drop lines repeated at the top or bottom of most PDF pages (page numbers, document titles, confidentiality notices) so Markdown and RAG chunks stay clean.", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs (applies to all PDFs in the run)." }, "followDocumentLinks": { "title": "Also process documents linked from web pages", "type": "boolean", "description": "If a source URL is a web page, find links to PDF/DOCX/XLSX/XLS/PPTX/CSV files on it and convert those documents instead (e.g. a reports, filings or publications page). The page itself is not billed.", "default": false }, "maxLinkedDocuments": { "title": "Max linked documents per page", "minimum": 1, "maximum": 500, "type": "integer", "description": "Limit for 'Also process documents linked from web pages'.", "default": 20 }, "saveFiles": { "title": "Also save downloadable files", "type": "boolean", "description": "Save each document's Markdown as a .md file, each table as a .csv file and all tables together as an Excel workbook (.xlsx, one sheet per table) in the run's key-value store; the result includes their download links (handy without code: open the link, get the file).", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Documents larger than this are skipped (not billed).", "default": 50 }, "failOnError": { "title": "Fail the run if any document fails", "type": "boolean", "description": "Mark the run as FAILED when a document cannot be processed or yields no text. Useful for pipelines and monitoring. Successfully processed documents are still returned (and billed).", "default": false }, "maxConcurrency": { "title": "Max parallel documents", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents are processed at the same time.", "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 } } } } } } } } } }