Parseur automates text extraction from PDFs, emails, and other documents. Users upload a document to analyze and suggest fields for extraction, then adjust for specific needs. It supports imports from emails, PDFs including scanned ones, spreadsheets, text files, and HTML pages via app upload, email, API, Zapier, Make, or Power Automate. The web app provides control over extraction settings, document flow monitoring, exception resolution, and access management. An API enables programmatic document submission, webhook data receipt, and REST integration. Parseur handles documents up to 100 pages, image formats like PNG and JPEG, multi-row tables, locale-based number and date formats, and multiple languages.
Processes large PDFs faster with improved accuracy
Handles image formats for scanned receipts and ID cards
Automatically detects date and number formats across locales
Supports documents up to 100 pages with better layout awareness
AI-powered translations may have minor inaccuracies
Requires enabling image processing in mailbox settings
Existing mailboxes need manual switch to new AI engine
