Dynamic OCR data Extraction from PDF

I’m testing out a usecase where we extract data from images, furthermore it’s unstructured data, so I’ve been manually scrapping the data position of each image but I was wondering if anyone could help me think of a way to loop it effectively?

I thought of using anchor base and find ocr text but the thing is the only commonality would be the email address’ @ on the image. If anyone has a suggestion please do let me know! Thanks.

Hi @strqsr,

Can you share screenshot of the data?

Thanks & Regards,

It’s just a bunch of random images that has an email address, I’m trying to see if it’s possible to extract the details that are in common e.g: email address/phone no.