{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: PDF to Text, Pages & OCR", "description": "Paste PDF links, get clean text, per-page text, RAG-ready chunks and metadata (title, author, dates, page count). Scanned pages are read with Tesseract OCR in 7 languages. Failed, encrypted and empty files are free. Free while in launch; planned price $2 per 1,000 PDFs.", "version": "1.0", "x-build-id": "uPnHefg6y9LQuMryd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/adamhaleworks~pdf-text-extractor-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-adamhaleworks-pdf-text-extractor-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/adamhaleworks~pdf-text-extractor-ocr/runs": { "post": { "operationId": "runs-sync-adamhaleworks-pdf-text-extractor-ocr", "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/adamhaleworks~pdf-text-extractor-ocr/run-sync": { "post": { "operationId": "run-sync-adamhaleworks-pdf-text-extractor-ocr", "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": "Direct links to PDF files, one per line. Up to 10,000 per run.", "items": { "type": "string" } }, "outputMode": { "title": "Rows", "enum": [ "document", "pages" ], "type": "string", "description": "One row per PDF (full text in 'text'), or one row per page (text in 'pageText', with the PDF's metadata repeated).", "default": "document" }, "includePageTexts": { "title": "Add per-page texts to each PDF row", "type": "boolean", "description": "Adds 'pages': [{page, text, ocr}] in 'One row per PDF' mode.", "default": false }, "chunkSize": { "title": "Chunk size for RAG (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "0 = off. Otherwise adds 'chunks' (or 'pageChunks' per page): pieces of at most this many characters, cut at paragraph, sentence or word boundaries.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters repeated between consecutive chunks (at most half the chunk size).", "default": 200 }, "ocr": { "title": "OCR scanned pages", "type": "boolean", "description": "Pages with fewer than 20 characters of embedded text are rendered at 300 dpi and read with Tesseract OCR.", "default": true }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages in the scanned documents. More languages are slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch" ] }, "default": [ "eng" ] }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Pages after this are skipped (the row says so).", "default": 500 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are reported as 'too_large' and not charged.", "default": 50 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "PDFs downloaded and read at the same time. At most 2 requests run against the same host.", "default": 4 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "How long to wait for each download.", "default": 60 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for network errors and HTTP 429/5xx answers, with backoff. Retry-After is honoured up to 30 s.", "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 } } } } } } } } } }