Is there a way to pull (save) a presentation as slides from a video?

Question

Python

There are several training videos on youtube with presentations, but the presentations themselves are no longer freely available.
I want to upload presentations with text from these video clips so that at the output I have "test + pictures" in the form of slides, those that were shown in the video.
Separately, in principle, all this has already been implemented:
1) Scene detection and saving frames as pictures,
2) text recognition in pictures.
Maybe someone has already done this, or met ready-made implementations. Ideally, you don't have to write your own video presentation extractor.
Maybe there are already ready-made solutions (albeit paid ones). Need for personal needs, Video slide content: Russian + English.
If you don’t know about ready-made solutions, you can advise articles on where to look in order to build such a combine. Didn't work with openCV. To recognize pictures in slides, I plan to use some kind of ready-made recognition tool (while I was thinking on Abbyy).