{ "openapi": "3.0.1", "info": { "title": "PDF to Excel: Invoice & Table Extractor", "description": "PDF to Excel, CSV or JSON rows. Invoices: supplier, number, dates, VAT, totals and one row per line item, with totals cross-checked. Any other PDF: every table becomes rows. No AI, no API key. $6 per 1,000 pages with data ($4.50 on Business); empty pages and failed files free.", "version": "1.0", "x-build-id": "UXVAXL5wzcsJbD5B4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/egra_van~pdf-invoice-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-egra_van-pdf-invoice-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/egra_van~pdf-invoice-table-extractor/runs": { "post": { "operationId": "runs-sync-egra_van-pdf-invoice-table-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/egra_van~pdf-invoice-table-extractor/run-sync": { "post": { "operationId": "run-sync-egra_van-pdf-invoice-table-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": "Links to PDF files: invoices, bills, purchase orders, price lists, statistical tables, reports. Google Drive, Dropbox, OneDrive/SharePoint, Box and GitHub share links are converted to direct downloads (share them as 'Anyone with the link').", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "kvStoreFileNames": { "title": "…or PDFs in a key-value store", "type": "array", "description": "Names of PDF files uploaded to an Apify key-value store. Use 'storeIdOrName/fileName', or just 'fileName' together with the store below (default: this run's store).", "items": { "type": "string" } }, "kvStoreId": { "title": "Key-value store ID or name", "type": "string", "description": "Store that holds the files above." }, "datasetId": { "title": "…or dataset with PDF URLs", "type": "string", "description": "Apify dataset (for example the output of a crawler) whose items contain PDF URLs." }, "datasetUrlField": { "title": "Dataset URL field", "type": "string", "description": "Field of the dataset items that holds the PDF URL.", "default": "url" }, "mode": { "title": "What to extract", "enum": [ "auto", "invoice", "tables" ], "type": "string", "description": "Auto treats a PDF as an invoice when page 1 says invoice / bill to / factura / Rechnung / facture and an item table or invoice fields are found; otherwise every table becomes rows.", "default": "auto" }, "tableDetection": { "title": "Table detection", "enum": [ "auto", "lines", "text" ], "type": "string", "description": "Keep 'Auto' unless you get extra small tables you do not need.", "default": "auto" }, "parseNumbers": { "title": "Convert numbers", "type": "boolean", "description": "Turn '1,234.50', '1.234,50', '$12.00' and '(15.00)' into numbers (decimal comma or point is detected per document), so they sum correctly in Excel. Percentages and codes with leading zeros stay as text.", "default": true }, "dateOrder": { "title": "Date order for dates like 03/04/2026", "enum": [ "auto", "DMY", "MDY" ], "type": "string", "description": "Invoice dates are returned as YYYY-MM-DD. Only matters when day and month are both 12 or less.", "default": "auto" }, "saveExcel": { "title": "Save one Excel file for the run", "type": "boolean", "description": "Also saves OUTPUT.xlsx in the run's key-value store: a sheet with all invoice lines, a sheet with one row per invoice, and one sheet per table. The dataset itself can be exported to CSV, Excel or JSON as usual.", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Only for password-protected PDFs (the same password is tried on every file)." }, "maxPagesPerDocument": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Read only the first N pages of each PDF (0 = all pages).", "default": 0 }, "maxDocuments": { "title": "Max PDFs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of PDFs in one run.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (not charged).", "default": 50 } } }, "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 } } } } } } } } } }