{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown Extractor with OCR (Tables, Bulk)", "description": "Extract text, LLM-ready Markdown, tables, metadata and per-page content from PDF URLs in bulk. Scanned pages are OCR'd automatically with Tesseract inside the Actor, no API key and no cloud OCR. Page ranges, password PDFs, dataset and CSV input.", "version": "0.1", "x-build-id": "1CQ9btaTOySjDnphu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/latamdatatools~pdf-text-ocr-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-latamdatatools-pdf-text-ocr-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/latamdatatools~pdf-text-ocr-extractor/runs": { "post": { "operationId": "runs-sync-latamdatatools-pdf-text-ocr-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/latamdatatools~pdf-text-ocr-extractor/run-sync": { "post": { "operationId": "run-sync-latamdatatools-pdf-text-ocr-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "PDF URLs", "type": "array", "description": "One public PDF URL per line (reports, invoices, papers, contracts, scanned documents...).", "items": { "type": "string" } }, "ocrMode": { "title": "OCR (scanned pages)", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto = OCR only pages without a text layer (scans, photos). Always = OCR every page (e.g. broken text layers). Never = text layer only. OCR runs with Tesseract inside the Actor; no document is sent to any other service.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned text. More languages = slower OCR.", "items": { "type": "string", "enum": [ "eng", "spa", "por", "fra", "deu", "ita", "nld", "pol", "rus", "tur", "chi_sim", "jpn" ], "enumTitles": [ "English", "Spanish", "Portuguese", "French", "German", "Italian", "Dutch", "Polish", "Russian", "Turkish", "Chinese (simplified)", "Japanese" ] }, "default": [ "eng" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 150, "maximum": 400, "type": "integer", "description": "300 is best for most scans; 200 is faster for clean documents.", "default": 300 }, "markdown": { "title": "LLM-ready Markdown", "type": "boolean", "description": "Markdown with headings (by font size), paragraphs, bullet lists and tables, with page markers. Ideal for RAG and LLM prompts.", "default": true }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables with ruling lines and return them as rows (and as Markdown tables).", "default": true }, "includePages": { "title": "Text per page", "type": "boolean", "description": "Add a list with the text of every page (with OCR flag and table count).", "default": true }, "pageRange": { "title": "Page range", "type": "string", "description": "Optional, e.g. 1-5, 8, 10- (empty = all pages, up to the max below)." }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Longer PDFs are cut at this page (marked truncated).", "default": 500 }, "password": { "title": "PDF password (optional)", "type": "string", "description": "For password-protected PDFs you are allowed to open. Used for every PDF of the run." }, "datasetId": { "title": "Dataset (from another Actor run)", "type": "string", "description": "Optional: extract the PDFs whose URLs are in an Apify dataset. Use \"URL field\" to say which field holds them." }, "csvUrl": { "title": "CSV file URL", "type": "string", "description": "Optional: a public CSV with a header row (Google Sheets links work if shared as \"Anyone with the link\")." }, "urlField": { "title": "URL field", "type": "string", "description": "Field / CSV column with the PDF URL (dot notation for nested fields).", "default": "url" }, "keepFields": { "title": "Fields to keep from the source", "type": "array", "description": "Copy these dataset / CSV fields into each result (under \"source\").", "items": { "type": "string" } }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Bigger downloads are stopped (not charged).", "default": 100 } } }, "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 } } } } } } } } } }