Document Unerstanding - Extrcting text from pdf

Hi team,

I am trying to extract text from the PDF by using document understanding process, the sentance text is “Productname - 5 units as per POXXXX” , here i need to extract “5”.
I can able to get the text only for templet trained document, But some of the files the data extracted as “units, As per,…Etc” because of sentance length is getting changed.

Can you help me how do i get the text even changing the position.


Hi @shaikmdrafi

Is it scanned PDF or not?


This is digital PFD we are trying to extract the data.

@shaikmdrafi You can use a regular expression to fetch the numeric value

Happy automation

Best Regards,

1 Like