Detect the content type of multiple PDF in a Folder

so far I am using PyPDF2 in anaconda platform to place a watermark in 20000+ pdfs. The code is working for the majority of PDF files but there are a few of them where the content is a poorly scanned image from reports.

I want to know if there is a tool within python or any other way where I can analyse the content of the PDF and determine if the PDF is an image or is a pdf file with text characters. This will allow me to know which files have this defect and place them in other folder.

Thanks

I added my code.

import PyPDF2 #this library requires to be installed
import os


if __name__ == "__main__":


    ROOT_PATH = "."
    #STAMP_PATH = "." + "/stamped/"
    TEMPLATE_PATH = "."
    
    STAMP_PATH = "."
        
    
    count = 0
    
    for dirName, subdirList, fileList in os.walk(ROOT_PATH):
        
        files=[]

        print('Found directory: %s' % dirName)
        for fileName in fileList:

            if fileName.find('.pdf') > 0:
                count += 1

                print('tHandling %s - %s  %s' % (count, dirName, fileName))

                files.append(fileName)


#=======================main code part ==========================================                
                file= open(fileName,'rb')
                reader = PyPDF2.PdfFileReader(file)
                page= reader.getPage(0)
                
                
                water = open(TEMPLATE_PATH + 'StampTemplate1109.pdf','rb')
                reader2 = PyPDF2.PdfFileReader(water)
                waterpage = reader2.getPage(0)
                
                #command to merge parent PDF first page with PDF watermark page
                page.mergeTranslatedPage(waterpage, 0, -20, expand=True)
                
                
                writer =PyPDF2.PdfFileWriter()
                writer.addPage(page)
                
                #add rest of PDF pages
                for pageNum in range(1, reader.numPages): # this will give length of book
                 pageObj = reader.getPage(pageNum)
                 writer.addPage(pageObj)
                 
                #return the parent PDF file with the watermark 
                # here we are writing so 'wb' is for write binary
                resultFile = open(STAMP_PATH + 'Reviewed ' + fileName,'wb')
                
                writer.write(resultFile)
                file.close()
                resultFile.close()
#==============================================================================                

    print "TOTAL OF %s PROCESSED" % count