Old script for finding duplicate files by name in a directory tree

find_dupes.py

#!/usr/bin/python

import errno, sys, os

DEBUG = 0

"""
def make_sure_path_exists(path):
    if DEBUG:
        print path
    try:
        os.makedirs(path, 0755)
    except OSError as exception:
        if exception.errno != errno.EEXIST:
            raise
"""

def process_file(needle, tree):
    # split needle into path & filename
    arrpath = needle.split("/")
    filename = arrpath[-1]
    path = ""
    if DEBUG:
        print "looking for needle..."
    if (len(arrpath) >= 2):
      path = "/".join(arrpath[0:-1])
    # find that file elsewhere, if found return the found full path
    n = ""
    d = ""
    for target in tree:
        if (target[1] == filename) and (target[0] != path):
            if DEBUG:
                print "found a {%s} in path: %s instead of %s" % (filename, target[0], path)
            n = needle
            d = target[0] + "/" + target[1]
    return [n, d]



try:
    input_file = sys.argv[1]
except:
    print 'usage: finddupefiles.py <file with list of files to find dupes of> (in directory to search for)'
    sys.exit(2)

# get file names from input file
list_filenames = []
with open(input_file) as filenames:
    for line in filenames:
        line = line.strip()
        list_filenames.append(line)

# create list of directory [path, filename]
starting_directory = '.'
dir_tree = []
for root, dirs, files in os.walk(starting_directory):
    for name in files:
        if DEBUG:
             print "%s\t%s\t(%s)" % (root, name, os.path.join(root, name))
        dir_tree.append([root, name])

# go through needles
file_dupes = open(os.path.join(starting_directory, "dupes_found"), 'w+')
for needle in list_filenames:
    if DEBUG:
        print 'needle: %s' % needle
    x, y = process_file(needle, dir_tree)
    if x:
        _template = """{target} found at {found}\n"""
        _context = { "target": x, 
                     "found": y }
        file_dupes.write(_template.format(**_context))