[Python] Is there a way of skipping image text when extracting data from a PDF

So am trying to scrap data from a patent.pdf but I keep scraping the figure(images) text and some I actually scrap major lines of blank spaces. NB am not using any web scraping tool I have used the Pdf-plumber and the other pdf scrapers I need to extract the data only for NLP but I need the text only

Continue reading...