如何在保持文件夹结构的同时仅复制非重复文件？

Question

我正在尝试在两个文件夹之间查找重复项，并且只将唯一的图像文件复制到“dest”文件夹中。我可以使用下面的代码复制所有非重复项，但是它不维护源目录结构。我认为 OS.walk 返回 3 个元组，但它们没有链接，所以不确定如何重新构建子目录？

例子：

import shutil, os
from difPy import dif
source = input('Input source folder:')
dest = input('Input backup \ destination folder:')

ext = ('.jpg','.jpeg','.gif','.JPG','.JPEG','.GIF')

search = dif(source, dest)
result = search.result
result


dupes = []
srcfiles = []
filecount = []
failed = []
removed = []

for i in result.values(): 
        dupes.append(i['location'])

for dirpath, subdirs, files in os.walk(source):
    for x in files:
        if x.endswith(ext):
            srcfiles.append(os.path.join(dirpath, x))

for f in srcfiles:
                if f not in dupes:
                        shutil.copy(f, dest)
                        print('File copied successfully - '+f)
                        filecount.append(f)
                else:
                        print('File not copied successfully !!!! - '+f)
                        failed.append(f)

我也尝试过将 shutil.copytree 函数与忽略列表一起使用，但是它需要一个新文件夹并且无法使忽略列表函数工作

shutil.copytree 示例：

for i in result.values(): 
        df = []
        df.append(i['filename'])

def ignorelist(source, df):
        return [f for f in df if os.path.isfile(os.path.join(source, f))]

shutil.copytree(source, destnew, ignore=ignorelist)

Answer 1

这个函数 ignorelist 应该可以解决问题：

import shutil, os
from difPy import dif
source = input('Input source folder:')
dest = input('Input backup  destination folder:')

ext = ('.jpg','.jpeg','.gif')

search = dif(source, dest)

dupes = list(value['location'] for value in search.result.values())

def ignorelist(source, files):
    return list(file for file in files
                    if (os.path.isfile(os.path.join(source, file))
                         and (os.path.join(source, file) in dupes
                              or not file.lower().endswith(ext))))

shutil.copytree(source, dest, ignore=ignorelist)

另一种“更手动”的方式是

import shutil, os
from difPy import dif
source = input('Input source folder:').rstrip('/\')
dest = input('Input backup  destination folder:').rstrip('/\')

ext = ('.jpg','.jpeg','.gif')

search = dif(source, dest)

dupes = list(value['location'] for value in search.result.values())

srcfiles = []
copied = []
failed = []
skipped = []

for dirpath, subdirs, files in os.walk(source):
    for file in files:
        if file.lower().endswith(ext):
            srcfile = os.path.join(dirpath,file)
            srcfiles.append(srcfile)
            if srcfile in dupes:
                print('File not copied (duplicate) - '+srcfile)
                skipped.append(srcfile)
            else:
                try:
                    destfile = os.path.join(dest,srcfile[len(source)+1:])
                    os.makedirs(os.path.dirname(destfile), exist_ok=True)
                    shutil.copy(srcfile,destfile)
                    print('File copied successfully - '+srcfile)
                    copied.append(srcfile)
                except Exception as err:
                    print('File not copied (error %s) - %s' % (str(err),srcfile))
                    failed.append(f)

Answer 2

我更改了一些变量名称以使它们更具描述性。你所说的failed 实际上只是一个未复制的文件列表，因为它们是重复的，而不是尝试复制但失败的文件。

import shutil, os
from difPy import dif

source = input('Input source folder: ')
dest = input('Input backup  destination folder: ')

# Remove trailing path separators if they exist:
if source.endswith(('/', '\')):
    source = source[:-1]
if dest.endswith(('/', '\')):
    dest = dest[:-1]

# Use the correct path separator to
# ensure correct matching with dif results:
if os.sep == '/':
    source = source.replace('\', os.sep)
elif os.sep == '\':
    source = source.replace('/', os.sep)

source_directory_length = len(source) + 1

ext = ('.jpg','.jpeg','.gif','.JPG','.JPEG','.GIF')

search = dif(source, dest)
result = search.result

# Set comprehension:
dupes = {duplicate['location'] for duplicate in result.values()}

copied = []
not_copied = []
for dirpath, subdirs, files in os.walk(source):
    for file in files:
        if file.endswith(ext):
            source_path = os.path.join(dirpath, file)
            if source_path not in dupes:
                # get subdirectory of source directory that this file is in:
                file_length = len(file) + 1
                # Get subdirectory relative to the source directory:
                subdirectory = source_path[source_directory_length:-file_length]
                if subdirectory:
                    dest_directory = os.path.join(dest, subdirectory)
                    # ensure directory exists:
                    os.makedirs(dest_directory, exist_ok=True)
                else:
                    dest_directory = dest
                dest_path = os.path.join(dest_directory, file)
                shutil.copy(source_path, dest_path)
                print('File copied successfully -', source_path)
                copied.append(source_path)
            else:
                print('File not copied -', source_path)
                not_copied.append(source_path)

Answer 3

import sysrsync

source = input('Input source folder:')
dest = input('Input backup  destination folder:')
sysrsync.run(source=source,
             destination=dest,
             sync_source_contents=False)

来自：https://github.com/gchamon/sysrsync