{ "openapi": "3.0.1", "info": { "title": "PDF Text & Table Extractor — Markdown, OCR", "description": "Text, markdown, ruled tables and RAG chunks from PDF URLs, one item per page or per document, with optional Tesseract OCR for scanned pages. Built on PDFium: 140 pages in about a second. Charged per page delivered; document summaries, errors and skipped pages are free.", "version": "0.1", "x-build-id": "7egeqtqAC4W1I1cW7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/acotr_moonie~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-acotr_moonie-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/acotr_moonie~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-acotr_moonie-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/acotr_moonie~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-acotr_moonie-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "PDF URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Direct links to PDF files (http or https), one per line. Must be the PDF itself, not a viewer page such as Google Docs or a browser preview. Each URL is fetched once with a plain GET, no proxy, no login; requests to the same host are spaced at least one second apart. You are responsible for the hosting site's terms and robots rules.", "items": { "type": "string" } }, "outputMode": { "title": "Output mode", "enum": [ "page", "document", "chunk" ], "type": "string", "description": "page = one item per page (CSV and Google Sheets friendly). document = one item per PDF with full text, markdown and a pages array. chunk = RAG chunks of chunkSize characters with page and character offsets. A free document summary row is always written.", "default": "page" }, "includeMarkdown": { "title": "Markdown", "type": "boolean", "description": "Add a markdown field: headings inferred from font-size rank, paragraphs from line gaps, tables as GitHub tables when extractTables is on. Heuristic, not a layout model.", "default": true }, "extractTables": { "title": "Extract ruled tables", "type": "boolean", "description": "Detect tables drawn with ruling lines and return them as arrays of rows. Borderless tables stay in the text. Adds about 0.3-0.5 s per page. No extra charge.", "default": false }, "pageRange": { "title": "Page range", "pattern": "^[0-9,\\- ]*$", "type": "string", "description": "Pages to extract, 1-based, e.g. 1-5, 8, 12- (12 to end). Empty = all pages. Pages outside the range are never charged." }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages beyond this are not extracted or charged; the document row gets status partial with errorCode pages_capped. Raise it deliberately for long documents.", "default": 100 }, "maxPages": { "title": "Max pages (total, charged)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Hard stop for the whole run. Your main cost control: at $0.0003 per page, 5000 pages = $1.50. Documents not reached are reported with errorCode budget_exhausted and are free. 0 = no limit.", "default": 5000 }, "maxPdfMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Files larger than this are refused before download (Content-Length) and aborted during download. Free error row too_large. The effective cap is also bounded by the run's memory (memory MB / 4).", "default": 50 }, "ocr": { "title": "OCR scanned pages", "type": "boolean", "description": "Run Tesseract (English) on pages that have no text layer but contain an image. Such pages are charged as OCR page ($0.003) instead of page. Off = those pages are delivered empty with needsOcr true, free.", "default": false }, "ocrLanguage": { "title": "OCR language", "enum": [ "eng" ], "type": "string", "description": "Tesseract language pack. Only packs shipped in the image are listed.", "default": "eng" }, "maxOcrPagesPerPdf": { "title": "Max OCR pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "OCR cost control. Remaining image-only pages are delivered empty with needsOcr true and are not charged.", "default": 50 }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Used only in chunk mode. 1500 characters is roughly 375 tokens. Split at paragraph, then sentence, then hard cut.", "default": 1500 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Tail of the previous chunk repeated at the start of the next. Clamped to half of chunkSize.", "default": 200 }, "pdfPassword": { "title": "PDF password (optional)", "type": "string", "description": "Applied to every password-protected PDF in this run. Wrong or missing password = free error row password_required. PDFs whose owner disabled text copying are always skipped (free error row permissions_restricted); there is no override." } } }, "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 } } } } } } } } } }