Select tables from image/pdf to plain text

I want to copy numerical tables from images(using OCR) or selecting from a PDF to paste as plain text for GPT. Would it be possible?

The current OCR I am using mixes all the rows/columns

PopClip doesn’t have any way to input images, it only works on text selections.

You can use TextSniper to do this. You can grab text from anything on your screen, image, video, pdf and then paste it anywhere you want. Unfortunately it does not pop a window like Popclip and let you choose the app you want, you have to have the app you want to paste it to. It is availble on Setapp.

1 Like

@usernamenyc could you explain more of what you’re trying to accomplish? i.e. when you extract the OCR from an image, in the format you’re hoping for… what are you trying to have GPT product for you?

Not sure if this will help but based on the info you gave, another tool that does not require a subscription, which has a really solid OCR function is called iShot Pro. I paid the $4.50 for the annual subscription but you might be able to get by on their Lite version. ¯\__(ツ)_/¯

Here’s a little screencast to show you the OCR tool in action. Hope this helps!

1 Like