Dext Prepare vs invoice2data

Dext Prepare captures receipts and invoices and extracts their details for bookkeeping. Documents can come in through the mobile apps, computer upload, supplier invoice fetch, or email. Dext says its AI extracts supplier, date, tax, and total with 99.9% accuracy, and the product can apply learned categorisation rules and flag duplicate transactions. It includes line-item extraction, purchase-order matching, and approval routing. Dext says it connects to 36+ accounting platforms, e-commerce platforms, and more than 11,500 banks and financial institutions; named examples include Xero, QuickBooks, Sage, Shopify, PayPal, and Stripe. The annual Business plan is £290 a year, billed at £24.17 per month, excludes VAT, and includes 250 documents per month for five users. There is no free plan; a 14-day free trial requires no credit card. Access is available on Android, iOS, web, and as a Chrome or Edge extension. Dext says it is certified to ISO/IEC 27001:2022 and encrypts stored data with AES-256 and communications with TLS 1.2 or higher.

invoice2data is a command-line tool and Python library that extracts structured information from PDF invoices for accounting workflows. It reads invoice text using selectable backends, including pdfium, pdftotext, pdfminer, pdfplumber, and OCR tools. YAML or JSON templates identify fields and can specify custom fields and multiple regular expressions for each one. The command-line tool can export extracted results as CSV, JSON, or XML and rename PDFs based on their contents. Optional plugins support invoice line items and tables, with Camelot available for advanced table parsing. Optional AI features can help draft templates or extract fields when template matching fails. AI does not run unless a provider is configured; the default mock provider has no network access. Listed providers include OpenAI, DeepSeek, Mistral, Gemini, and Ollama, which can run locally. Local OCR options include docTR and PaddleOCR. The project is free under the MIT License, with pip and conda installation routes. It runs on Linux, macOS, Windows, and self-hosted systems.