[warrendlee1]

docparser and most ocr services require the document layout be the same/similar for each template you make.

extractio doesn't require the user to make any templates and can be used for any generic document layout.

A perfect use case for extractio would be resumes - candidates submit many different resume layouts, but it would be able to parse out the name, positions, email, etc. without making a template for each layout.

[andrewio]

Any AI-powered PDF parser doesn't require documents to use "the same layout".

I'm building Pariso (parsio.io) that can parse invoices, receipts etc. They all may have different layout :)

[dnl01]

Great tool! Why do you think tools like Docparser exist when Parsio seems to eliminate all the work that a user would do to build templates. Seems like a no-brainer.

What have you seen as the most common use case for something like Parsio vs Docparser?

[andrewio]

Docparser has been on the market for years and has a solid customer base, despite the rise of more sophisticated AI-powered tools for data extraction. The switching cost for customers is relatively high in terms of the effort required.

As for the use cases, we have all kind of it.

For emails, our customers parse submitted forms and leads to Google Sheets and CRM, extract booking data from Airbnb confirmations, exporting Etsy orders to Trello, extract and filiter HARO queries.

For PDFs and scanned documents, we have businesses parsing invoices, receipts, quotes, contracts, business cards etc.