It would help if there were a node for:
My use case:
It can extract essential data from Word, PDF and image files. Currently, I'm using it to extract billed items, total amount and other details as printed on CVS receipts. This information is then processed into a Google Sheet to track my pharmacy expenses and maintain my finances. A Docparser node here would help me automate this process.
As soon a PDF is uploaded into “Pharmacy” Dropbox, send it to Docparser. After extracting data, send it back to Google Sheets
Any resources to support this?
Are you willing to work on this?