{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor & OCR - Bulk PDF and Image to Text", "description": "Extract text from PDFs and images in bulk: text layer read exactly, OCR (Tesseract, 8 languages) only on scanned pages. $1.50 per 1,000 PDFs + $0.002 per OCR page; failed downloads and blank pages are free.", "version": "0.1", "x-build-id": "rftz7ZOw8f9agDbBf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tinyrex~pdf-ocr-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tinyrex-pdf-ocr-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tinyrex~pdf-ocr-text-extractor/runs": { "post": { "operationId": "runs-sync-tinyrex-pdf-ocr-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/tinyrex~pdf-ocr-text-extractor/run-sync": { "post": { "operationId": "run-sync-tinyrex-pdf-ocr-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": { "fileUrls": { "title": "PDF or image URLs", "type": "array", "description": "Direct links to PDF files or images (PNG, JPEG, TIFF, WebP, GIF, BMP), one per line. Duplicates are removed. Links that fail to download or are not a PDF/image are listed with the reason and are free.", "items": { "type": "string" } }, "datasetId": { "title": "Read file URLs from a dataset (optional)", "type": "string", "description": "ID of an Apify dataset with file links, e.g. the output of another scraper. Without a URL field, every value that looks like a link to a .pdf or image file is collected." }, "urlField": { "title": "URL field in the dataset (optional)", "type": "string", "description": "Name of the dataset field that holds the file link (dot notation like documents.url works; arrays are expanded). Use it when your links don't end in .pdf." }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto = read the PDF's own text layer and OCR only pages without text (scanned pages) and images. always = OCR every page. never = text layer only, no OCR charges.", "default": "auto" }, "languages": { "title": "OCR languages", "type": "array", "description": "Languages printed in your scanned documents. Pick only the ones you need: each extra language makes OCR slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish" ] }, "default": [ "eng" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution used to render scanned PDF pages before OCR. 200 is fast and accurate for normal print; use 300 for small text.", "default": 200 }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Adds a pages array (page number, method text-layer/ocr/empty, text) to each row. Handy for RAG chunking and page citations.", "default": false }, "keepLayout": { "title": "Keep physical layout", "type": "boolean", "description": "Keeps columns and table alignment of text-layer pages with spaces (pdftotext -layout). Off = natural reading order.", "default": false }, "maxPagesPerFile": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Only the first N pages of each PDF are read. Remaining pages are reported in pagesNotProcessed.", "default": 100 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Bigger files are skipped (free).", "default": 50 }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on unique URLs processed in this run.", "default": 1000 } } }, "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 } } } } } } } } } }