{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor + OCR for Scanned PDFs", "description": "Extract text from PDFs by URL, with automatic OCR for scanned pages. One flat row per URL, never null, only successful PDFs billed. Fast, low-memory engine; Google Drive, Dropbox and arXiv links accepted. Built for pipelines and AI agents.", "version": "0.1", "x-build-id": "RXbK3KEcbxHgEe6VV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sumitr_mardy~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sumitr_mardy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sumitr_mardy~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-sumitr_mardy-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sumitr_mardy~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-sumitr_mardy-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Links to PDF files, one per line. Direct links, Google Drive, Dropbox and OneDrive share links, and arXiv /abs/ pages are all accepted. Every URL gets exactly one output row, including the ones that fail.", "items": { "type": "string" } }, "ocrMode": { "title": "OCR for scanned pages", "enum": [ "auto", "off" ], "type": "string", "description": "Auto runs OCR only on pages with no text layer that contain an image (scans, photos of documents). Pages that already have text are never OCRed. Only pages where OCR actually recovers text are charged.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "type": "string", "description": "Tesseract language code; join several with + (for example eng+fra). Available: eng, fra, deu, spa, por, ita, nld, pol, ces, ron, hun, swe, dan, nor, fin, tur, rus, ukr, ell, vie, ind, msa, tha, chi_sim, chi_tra, jpn, kor, ara, heb, hin.", "default": "eng" }, "maxOcrPagesPerPdf": { "title": "Max OCR pages per PDF", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Upper bound on pages OCRed in one PDF, to keep the cost of a huge scanned book predictable. Scanned pages beyond it are returned without text and reported in notes.", "default": 50 }, "pageRange": { "title": "Page range", "type": "string", "description": "Extract only these pages, for example 1-5, 8, 12- (12- means page 12 to the end). Empty extracts every page.", "default": "" }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Add a pages array with each page number, its text, and whether the text came from OCR. Useful for page-level citations.", "default": false }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Split the text into chunks of about this many characters, each carrying the pages it spans. 0 turns chunking off.", "default": 0 }, "chunkOverlap": { "title": "RAG chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters of the previous chunk repeated at the start of the next one, so a sentence cut at a boundary still appears whole once.", "default": 200 }, "password": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs. Applied to every PDF in the run that needs one." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and reported as failed (too_large), not charged.", "default": 100 }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "Time allowed per download. Raise it for very large files on slow hosts.", "default": 60 }, "maxConcurrency": { "title": "PDFs in parallel", "minimum": 1, "maximum": 32, "type": "integer", "description": "How many PDFs are downloaded and processed at once.", "default": 4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Downloads go direct by default. If a host answers 401/403/407/429, the download is retried once through Apify Proxy automatically. Turn this on to always download through a proxy.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }