{ "openapi": "3.0.1", "info": { "title": "Extract text from PDF", "description": "Efficiently extract text content from PDF files, ideal for data processing, content analysis, and automation workflows. Supports various PDF structures and outputs clean, readable text.", "version": "1.4", "x-build-id": "8VKUh60eCbJwVtrn7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/akash9078~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-akash9078-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/akash9078~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-akash9078-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/akash9078~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-akash9078-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "pdfUrl" ], "properties": { "pdfUrl": { "title": "PDF URL", "minLength": 1, "type": "string", "description": "URL of the PDF file to extract. Can be: (1) Direct download URL, (2) Google Drive share link, (3) Dropbox share link, (4) OneDrive share link", "default": "https://drive.google.com/file/d/1mt0Tt0YQumH5AOX3bapn4XjxCrtKY4Ns/view?usp=drive_link" }, "maxPages": { "title": "Maximum Pages to Extract", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to extract. Set to 0 or leave empty to extract all pages. Useful for large PDFs to limit processing time and memory usage.", "default": 0 }, "ocrFallback": { "title": "Enable OCR Fallback", "type": "boolean", "description": "When enabled, any page that contains fewer than 50 characters of embedded text is rendered to an image and processed with Tesseract OCR. Use this for scanned PDFs or image-based PDFs that have no text layer. Increases processing time and memory usage.", "default": true }, "ocrLanguage": { "title": "OCR Language", "type": "string", "description": "Tesseract language code used for OCR. Only applies when ocrFallback is true. Common codes: eng (English), fra (French), deu (German), spa (Spanish), chi_sim (Chinese Simplified), jpn (Japanese), ara (Arabic). See https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html for the full list.", "default": "eng" }, "mistralApiKey": { "title": "Mistral AI API Key", "type": "string", "description": "Optional Mistral AI API key for premium OCR fallback. When provided, if both pdf.js-extract and Tesseract OCR fail to produce meaningful text, the PDF URL is sent to Mistral OCR for state-of-the-art document understanding (tables, equations, complex layouts). Get your key at https://console.mistral.ai/api-keys/" } } }, "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 } } } } } } } } } }