{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor - Page by Page, With OCR for Scans", "description": "Extract text from any list of PDF URLs, one row per page, with title, author and page count. Scanned pages with no text layer are read by OCR in the same run, and each row says how it was read. 20 languages. Pay only for pages with text.", "version": "1.0", "x-build-id": "z7BF4vpxcCQ6rvnUS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/appdata-labs~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-appdata-labs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/appdata-labs~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-appdata-labs-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/appdata-labs~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-appdata-labs-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Links to the PDFs to read, up to 100 MB each and 200 per run. The link must open without signing in; password-protected PDFs cannot be read. A bad entry is skipped with a reason; the rest still run.", "default": [ "https://raw.githubusercontent.com/mozilla/pdf.js/master/web/compressed.tracemonkey-pldi-09.pdf", "https://raw.githubusercontent.com/ocrmypdf/OCRmyPDF/main/tests/resources/linn.pdf", "https://raw.githubusercontent.com/ocrmypdf/OCRmyPDF/main/tests/resources/skew.pdf" ], "items": { "type": "string" } }, "maxPagesPerPdf": { "title": "Pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Read at most this many pages from each PDF, from page 1. Up to 2,000. Pages beyond the limit are not read or charged.", "default": 50 }, "ocrScannedPages": { "title": "OCR scanned pages", "type": "boolean", "description": "On by default: a page with no text layer (a scan or a photo) is rendered and read by OCR, and its row says method \"ocr\". Off: such pages come back empty and uncharged — faster when you know the PDFs are digital.", "default": true }, "languages": { "title": "Languages", "type": "array", "description": "The language(s) of the text, as Tesseract codes. English is built in and fastest; other languages load on first use. Pick more than one only for mixed-language documents — each extra language slows reading.", "items": { "type": "string", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "nld", "pol", "tur", "rus", "ukr", "ara", "hin", "tha", "vie", "ind", "jpn", "kor", "chi_sim", "chi_tra" ], "enumTitles": [ "English", "Spanish", "French", "German", "Italian", "Portuguese", "Dutch", "Polish", "Turkish", "Russian", "Ukrainian", "Arabic", "Hindi", "Thai", "Vietnamese", "Indonesian", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)" ] }, "default": [ "eng" ] }, "maxTextBytesPerRow": { "title": "Max text per row (bytes)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Long text is split across several rows of at most this many bytes, at paragraph and line breaks, so each row fits an AI agent's context and drops straight into a RAG pipeline. The page is still charged once. 0 keeps each page whole in one row.", "default": 3000 } } }, "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 } } } } } } } } } }