[Tutor] scratching my head

[Clayton Kirkwood]

Hey, been awhile, but I ran into os.walk and it fit what I needed to do for
an issue I've had for a long time: I have tons of pictures in my top
directory of pictures which are duplicated into properly named
subdirectories. Please see issues above my questions with large gaps below. 
TIA,
Clayton


#Program to find duplicated pictures in my picture directory tree
#Presumably, if the file exists in a subdirectory I can remove if from the
parent picture directory
#
#Clayton Kirkwood
#01Aug15

import os
from os.path import join,  getsize

main_dir = "/users/Clayton/Pictures"
directory_file_list = {}
duplicate_files = 0
top_directory_file_list = 0

for dir_path, directories, files in os.walk(main_dir):
    for file in files:
#        print( " file = ", file)
#       if( ("(\.jpg|\.png|\.avi|\.mp4)$") not in file.lower() ):
#        if(  (".jpg" or ".png" or ".avi" or ".mp4" )  not in file.lower()
):
#
#why don't these work?, especially the last one. How am I to capture all
camera and video types
#except by the drudgery below. I should be able to just have a list, maybe
from a file, that lists all
#off the types and do something like if master_list not in file.lower()





        if(  ".jpg" not in file.lower() and
             ".png" not in file.lower() and
             ".avi" not in file.lower() and
             ".mp4" not in file.lower() ):

            print( "file ", file, "doesn't contain .jpg or .png or .avi or
.mp4" )
#            del files[file]
#
#I get an error on int expected here. If I'm able to access by string, why
wouldn't I be able to
#acess in the del?





    directory_file_list[dir_path] = files       #this is a list
#    print(dir_path, directory_file_list[dir_path])
#print( main_dir )
for directory_path in directory_file_list.keys():
    if( directory_path == main_dir ):
        top_directory_file_list = directory_file_list[directory_path]
        continue
#    print( directory_path, ":", directory_file_list[directory_path])
    file_list = directory_file_list[directory_path]
#    print(file_list)
    for file in file_list:
#        pass
        print( "looking at file  ", file, "  in top_directory_file_list  ",
top_directory_file_list )
        if file in top_directory_file_list:
#error: arg of type int not iterable
#yet it works for the for loops





            print( "file ", file, " found in both directory_path ",
directory_path, " and ", main_dir)
            duplicate_files =+ 1
        pass
    break