Python reorganizing a messed-up photo Library!

Posted by

Python is a neat tool that can be used to achieve variety of automation tasks. This time around it is here to save all the photographers out there.

If you are a photographer either hobby or professional, you can relate to directory/Folder containing tons and tons of pictures in random folders. If you can relate to this the blog is for you.

It has been said many times that necessity is the mother of invention. This python code came to existence due to a messed-up photo Library living on my own system. There were about 45000 photos spread across a ton of folders.

What does this code do?

The code looks at all the files in a given folder and it sub folders, it then moves all the file into folders structured as Year -> Month -> File

The code first attempts to read the files EXIF data for “Taken date”. In case the “Taken date” is not present it tries to look for YYYYMM (e.g. 202004) string in the name of the file. Finally, the code picks the File creation date when the file is missing both EXIF data for “Taken date” and YYYYMM (e.g. 202004) string in the file name.

The code will leave behind empty folders under the photo Library root. In most cases you can just delete all except “Structured” folder

The code also removes any files lower than the size defined

This is how your photo Library will look like post the execution

For those of you who do not want the hassle of setting up the python and dependence you can use the MSI to install as a application

How to Run:

Execute the code or Install as a application using the above MSI

  • Select the directory/folder containing pictures
  • Enter the small file size
  • That is it, just Wait and watch


import datetime
import os
import shutil
import time
import exifread
import wx
# Get Dir dialog
def get_dir(what):
    frame = wx.Frame(None, -1, '')
    frame.SetSize(0, 0, 200, 50)
    open_file_dialog = wx.DirDialog(frame, what, "", style=wx.DD_DEFAULT_STYLE)
    return open_file_dialog.GetPath()
def get_size():
    frame = wx.Frame(None, -1, '')
    frame.SetSize(0, 0, 200, 50)
    open_file_dialog = wx.TextEntryDialog(frame, "Files below this Size will be removed. Enter a file size in bytes:",
    size = open_file_dialog.GetValue()
    size = int(size)
    return size
# Question dialog
def question(message):
    u_sel = wx.MessageBox(message, 'Question?', wx.YES_NO | wx.NO_DEFAULT | wx.ICON_EXCLAMATION)
    return u_sel
# warning dialog
def warning(message):
    wx.MessageBox(message, 'Warning', wx.OK | wx.ICON_WARNING)
def read_dateTaekn(file):
    months_name = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
    cmy = []
    with open(file, 'rb') as fh:
        tags = exifread.process_file(fh, stop_tag="EXIF DateTimeOriginal")
        dateTaken = tags["EXIF DateTimeOriginal"]
        dateTaken = str(dateTaken)
        dateTaken = dateTaken.split(':')
        year = dateTaken[0]
        month = dateTaken[1]
        month_index = int(month) - 1
        month = months_name[month_index]
        return cmy
def get_files(directory):
    paths = []
    for root, directories, files in os.walk(directory):
        for filename in files:
            filepath = os.path.join(root, filename)
    return paths
def get_cmy(file):
    cmy = []
    creat_time = os.path.getmtime(file)
    creat_time = time.ctime(creat_time)
    creat_time = creat_time.split()
    return cmy
def move_to_cmy_dir(file_list, path, type):
    fixed_path = path + "/" + "Structured/" + type + "/"
    for file in file_list:
            print("Current Location:", file)
            file_name = os.path.basename(file)
            creat_mon_yer = get_cmy_form_name(file)
            new_path = fixed_path + "/" + str(creat_mon_yer[1]) + "/" + str(creat_mon_yer[0]) + "/" + file_name
            print("New Location:", new_path)
            shutil.move(file, new_path)
        except PermissionError:
def pre_new_dir_struc(path, file_list, type):
    fixed_path = path + "/" + "Structured/"
    except FileExistsError:
        print("file/Directory already exists")
    fixed_path = fixed_path + type + "/"
    except FileExistsError:
        print("file/Directory already exists")
    cmys = []
    all_files = file_list
    print("Reading file create times")
    for file in all_files:
    years = []
    months = []
    for cmy in cmys:
    years = unique_list(years)
    for year in years:
        m = []
        for cmy in cmys:
            if year in cmy:
    if len(years) == len(months):
        print("Creating Directory Structure")
        i = len(years)
        while i > 0:
            i = i - 1
            year = years[i]
            month = months[i]
                os.mkdir(fixed_path + str(year))
            except FileExistsError:
                print("file/Directory already exists")
            for m in month:
                out_path = fixed_path + str(year) + "/" + m
                    print("file/Directory already exists")
def get_cmy_form_name(file):
    year =
    months_num = ['01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12']
    months_name = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
    file_name = os.path.basename(file)
    cmy = []
    cmy_set = False
        cmy = read_dateTaekn(file)
        cmy_set = True
    while (not cmy_set):
        if year >= 1981:
            for num in months_num:
                datestr = str(year) + num
                if datestr in file_name:
                    month_name_index = int(num) - 1
                    month = months_name[month_name_index]
                    cmy_set = True
            if len(cmy) == 0:
                cmy = get_cmy(file)
        year = year - 1
    return cmy
def unique_list(list):
    unique_list = []
    for x in list:
        if x not in unique_list:
    return unique_list
def remove_small_files(file_list, size):
    for file in file_list:
        file_szie = os.path.getsize(file)
        if file_szie <= size:
def small_file_count(file_list, size):
    count = 0
    for file in file_list:
        file_szie = os.path.getsize(file)
        if file_szie <= size:
            print(file, ":", file_szie)
            count = count + 1
    message = "Number of small files Found: " + str(count)
    return count
def filter_image_files(file_list):
    image_files = list()
    ext_list = [".jpg", ".jpeg", ".jpe.jif", ".jfif", ".jfi", ".png", ".gif", ".webp", ".tiff", ".tif", ".psd", ".raw",
                ".arw", ".cr2", ".nrw", ".k25", ".bmp", ".dib", ".heif", ".heic", ".ind", ".indd", ".indt", ".jp2",
                ".j2k", ".jpf", ".jpx", ".jpm", ".mj2", ".svg", ".svgz", ".ai", ".eps"]
    for file in file_list:
        file_ext = os.path.splitext(file)[1]
        if file_ext.lower() in ext_list:
    return image_files
def filter_video_files(file_list):
    video_files = list()
    ext_list = [".webm", ".mpg", ".mp2", ".mpeg", ".mpe", ".mpv", ".ogg", ".mp4", ".m4p", ".m4v", ".avi", ".wmv",
                ".mov", ".qt", ".flv", ".swf", ".mkv.", ".rm", ".3gp"]
    for file in file_list:
        file_ext = os.path.splitext(file)[1]
        if file_ext.lower() in ext_list:
    return video_files
def filter_other_files(file_list):
    other_files = list()
    ext_list = [".webm", ".mpg", ".mp2", ".mpeg", ".mpe", ".mpv", ".ogg", ".mp4", ".m4p", ".m4v", ".avi", ".wmv",
                ".mov", ".qt", ".flv", ".swf", ".mkv.", ".rm", ".3gp", ".jpg", ".jpeg", ".jpe.jif", ".jfif", ".jfi",
                ".png", ".gif", ".webp", ".tiff", ".tif", ".psd", ".raw", ".arw", ".cr2", ".nrw", ".k25", ".bmp",
                ".dib", ".heif", ".heic", ".ind", ".indd", ".indt", ".jp2", ".j2k", ".jpf", ".jpx", ".jpm", ".mj2",
                ".svg", ".svgz", ".ai", ".eps"]
    for file in file_list:
        file_ext = os.path.splitext(file)[1]
        if file_ext.lower() not in ext_list:
    return other_files
app = wx.App()
current_path = get_dir("Photo Library Location")
size = get_size()
file_list = get_files(current_path)
if small_file_count(file_list, size) > 0:
    message = "Are you sure you want to remove all files smaller than " + str(size) + " bytes?"
    if question(message) == 2:
        remove_small_files(file_list, size)
file_list = get_files(current_path)
file_type = "Photos"
image_files = filter_image_files(file_list)
pre_new_dir_struc(current_path, image_files, file_type)
move_to_cmy_dir(image_files, current_path, file_type)
file_type = "Videos"
video_files = filter_video_files(file_list)
pre_new_dir_struc(current_path, video_files, file_type)
move_to_cmy_dir(video_files, current_path, file_type)
file_type = "Other"
other_files = filter_other_files(file_list)
pre_new_dir_struc(current_path, other_files, file_type)
move_to_cmy_dir(other_files, current_path, file_type)

One comment

Comments are closed.