Extracting information from webpage

Help
1

I have a web page which has unstructured content. We have to extract some info from the text.This information changes for different items ; lets say it is a online Policy document and there are multiple policies; We have to extract 5 fields. Is it possible to do that using UiPath and ABBYY.All the examples I am seeing is extraction of PO or Invoice.Not sure if this type of extraction is possible.

2

Hi @joelkris,

If that is web you can use Get Text, Get Full Text or even Get OCR text to read that particular text, you just have to make sure that your selector are stable.

See these -

Thanks,
Prankur

3

thanks.I should have been little more clear in the question. Since the data is in different wording in the unstructured content ,in WorkFusion world we can train an ML Model to extract the data .I do not see this feature in UiPath, UiPath Flexi capture is most suited for extracting Invoices ,PO etc. But not to understanding the content and using NLP and intelligence to extract. Atleast I did not find any where this use case mentioned.