{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor — Markdown, Per-Page Text, Tables, OCR & RAG", "description": "Turn any PDF (URL or upload) into clean data: full text, LLM-ready Markdown, per-page text, tables, RAG chunks, metadata and a READY_FOR_RAG / NEEDS_OCR verdict. OCR for scanned pages in 7 languages, page ranges, header/footer removal, passwords, change detection. $0.05 per PDF; failures free.", "version": "0.1", "x-build-id": "kkjSUsZLWYWc4t5Ap" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nexgenwatch~pdf-text-intake-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nexgenwatch-pdf-text-intake-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/nexgenwatch~pdf-text-intake-auditor/runs": { "post": { "operationId": "runs-sync-nexgenwatch-pdf-text-intake-auditor", "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/nexgenwatch~pdf-text-intake-auditor/run-sync": { "post": { "operationId": "run-sync-nexgenwatch-pdf-text-intake-auditor", "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 PDF files (redirects followed). Downloaded through a public-host and robots.txt check. Also accepted as `pdfUrls`, `startUrls` ({url}) or one `pdfUrl`.", "items": { "type": "string" } }, "files": { "title": "PDF files (base64 or key-value-store keys)", "type": "array", "description": "Locally-supplied PDFs — each item is a base64 data string (optionally a data: URL) or a key naming an entry in the run's key-value store. Per file: text-layer presence, page count, encryption, scan likelihood, per-page text density, document metadata, SHA-256, warnings, and a READY_FOR_RAG / NEEDS_OCR / REJECT verdict. A completed verdict bills; an unreadable/oversized/rejected file is delivered unbilled. Untrusted-file guards: size + page caps, decompression-bomb guard, no macro/JS execution.", "items": { "type": "string" }, "default": [] }, "password": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs; tried on every document that needs one. Leave empty for normal PDFs." }, "pageRange": { "title": "Page range", "type": "string", "description": "Extract only these pages, e.g. `1-5, 8, 12-` (`12-` = page 12 to the end). Empty = all pages (up to Max pages)." }, "includeFullText": { "title": "Include full text", "type": "boolean", "description": "The complete plain text of the document in `text`.", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "A Markdown rendition in `markdown`: headings (from font size), bullets and paragraphs rebuilt from the layout — LLM/RAG ready.", "default": true }, "includePerPageText": { "title": "Include per-page text", "type": "boolean", "description": "A `pages` array with the text of each page. Turn off to keep rows small for long PDFs.", "default": true }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables on each page and return them as rows of cells in `tables`. Slower on complex layouts.", "default": false }, "ocrScannedPages": { "title": "OCR scanned pages", "type": "boolean", "description": "When a page has no usable text layer (scanned / image-only), render it and run Tesseract OCR to recover the text. Slower; the row says how many pages were OCR'd.", "default": false }, "ocrLanguage": { "title": "OCR language", "enum": [ "eng", "deu", "fra", "spa", "por", "ita", "nld", "eng+deu", "eng+fra", "eng+spa" ], "type": "string", "description": "Language of the scanned pages for OCR.", "default": "eng" }, "ocrMaxPagesPerPdf": { "title": "Max OCR pages per PDF", "minimum": 1, "maximum": 300, "type": "integer", "description": "Upper bound on pages sent to OCR within one PDF; the row is flagged `ocr_capped` when reached.", "default": 20 }, "removeHeaderFooter": { "title": "Remove repeated headers/footers", "type": "boolean", "description": "Drop lines that repeat on 30% or more of the pages (running titles, company names).", "default": false }, "removePageNumbers": { "title": "Remove page-number lines", "type": "boolean", "description": "Drop lines that are only a page number (`42`, `Page 3 of 10`, `- 5 -`).", "default": false }, "ragChunks": { "title": "RAG chunks", "type": "boolean", "description": "Also split the text into overlapping chunks (`chunks`) at paragraph/sentence boundaries, ready for embedding.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target characters per chunk (about 500 tokens at 4 chars/token).", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters shared between consecutive chunks.", "default": 200 }, "changeDetection": { "title": "Change detection", "type": "boolean", "description": "Hash each PDF's text and compare with the previous run (stored in a named key-value store). Rows get `changed: true/false` (null on first sight).", "default": false }, "changedOnly": { "title": "Deliver changed PDFs only", "type": "boolean", "description": "With change detection on, skip (and do not bill) PDFs whose text did not change since the last run.", "default": false }, "maxBytes": { "title": "Max file bytes", "minimum": 1024, "maximum": 104857600, "type": "integer", "description": "Reject files larger than this (decompression-bomb guard).", "default": 26214400 }, "maxPages": { "title": "Max pages inspected", "minimum": 1, "maximum": 3000, "type": "integer", "description": "Cap pages walked for density.", "default": 300 }, "timeoutPerPdfSecs": { "title": "Download timeout per PDF (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Raise for very large files or slow hosts.", "default": 60 }, "userAgent": { "title": "User agent", "type": "string", "description": "Override the transparent crawler UA." } } }, "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 } } } } } } } } } }