def collect_sub_files(source_root_directory, move_target_directory):
"""
遍历所有子文件，然后移动到另一个地方，避免有些下载的文件嵌套太深
可以批量把某个文件夹下的所有文件移动到指定的目录下
:param source_root_directory: 检查的路径
:param move_target_directory: 统一移动到的路径
:return:
"""
if not os.path.isdir(move_target_directory):
# 文件不存在则创建
os.makedirs(move_target_directory)
sub_file_paths = u_file.get_all_sub_files(source_root_directory)
for sub_file_path in sub_file_paths:
if os.path.isdir(sub_file_path):
log.info('The file is directory: {}'.format(sub_file_path))
continue
sub_file_name = os.path.split(sub_file_path)[1]
sub_file_name_suffix = os.path.splitext(sub_file_name)[1]
if sub_file_name_suffix != '.jpg' and sub_file_name_suffix != '.hdr':
log.info('The file is not hdr file: {}'.format(sub_file_name))
continue
move_target_file_path = os.path.join(move_target_directory,
sub_file_name)
if os.path.isfile(move_target_file_path):
log.warn('The move target file is exist: {}'.format(
move_target_file_path))
continue
log.info('move file: {} --> file: {}'.format(sub_file_path,
move_target_file_path))
os.replace(sub_file_path, move_target_file_path)
def get_all_image_paths(image_directory: str, use_cache: bool = True, contain_dir=False) -> list:
"""
递归获取某个文件夹下的所有图片和文件夹
:param image_directory: 图片路径
:param use_cache: 是否使用缓存
:param contain_dir: 返回值是否包含目录
:return: 图片绝对路径列表
"""
log.info('begin get all image files from path: {}'.format(image_directory))
if not os.path.isdir(image_directory):
log.error('The image directory is not exist: {}'.format(image_directory))
return []
# 构建cache文件夹并检查是否存在cache
cache_file_path = get_cache_path(image_directory, 'image_paths', 'txt')
cache_file_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), cache_file_path)
if use_cache and os.path.isfile(cache_file_path):
# 存在缓存文件直接使用缓存
log.info('read all image file from cache: {}'.format(cache_file_path))
return u_file.read_file_as_list(cache_file_path)
# 如果cache目录不存在，则创建
if not os.path.isdir(os.path.split(cache_file_path)[0]):
log.info('create the cache directory: {}'.format(cache_file_path))
os.makedirs(os.path.split(cache_file_path)[0])
all_files = u_file.get_all_sub_files(image_directory, contain_dir=contain_dir)
# 将结果存入cache
cache_file_path_handler = open(cache_file_path, 'w+', encoding='utf-8')
for file in all_files:
cache_file_path_handler.writelines(file + '\n')
cache_file_path_handler.close()
log.info('get_all_image_files finish. file size: {}'.format(len(all_files)))
return all_files
def delete_file():
delete_picture_paths = u_file.get_all_sub_files(r'result-delete')
for delete_picture_path in delete_picture_paths:
base_filename = os.path.split(delete_picture_path)[1]
for index in range(30):
source_filename = base_filename.replace('-1', '-' + str(index))
source_path = os.path.join(r'result', source_filename)
if not os.path.isfile(source_path):
break
log.info('move file: {}'.format(source_path))
def arrange():
image_paths = os.path.abspath(r'./result')
sub_files = u_file.get_all_sub_files(image_paths)
log.info('The sub files size is :{}'.format(len(sub_files)))
for sub_file in sub_files:
# 按照名称和映射关系分组
for (path_key, path_value) in PATH_MAP.items():
if sub_file.find(path_key) >= 0:
move_target_file = sub_file.replace('result', path_value)
log.info('move the file from: {} -> {}'.format(
sub_file, move_target_file))
if not os.path.isdir(os.path.dirname(move_target_file)):
os.makedirs(os.path.dirname(move_target_file))
os.replace(sub_file, move_target_file)
break
def copy_first_picture():
picture_paths = u_file.get_all_sub_files(r'result')
first_picture_paths = []
for picture_path in picture_paths:
if picture_path.find('-1.jpg') >= 0:
first_picture_paths.append(picture_path)
log.info('first picture size: {}'.format(len(first_picture_paths)))
for first_picture_path in first_picture_paths:
copy_file_path = os.path.join(r'result-copy',
os.path.split(first_picture_path)[1])
log.info('copy file: {}'.format(copy_file_path))
if os.path.isfile(copy_file_path):
log.info('The file is exist: {}'.format(copy_file_path))
continue
shutil.copy(first_picture_path, copy_file_path)
def replace_file_name(source_root_directory, replace_ad_str):
"""
一般用来去掉下载文件中的广告
:param replace_ad_str: 需要替换掉的广告文字
:param source_root_directory: 处理的文件夹
:return:
"""
sub_file_paths = u_file.get_all_sub_files(source_root_directory)
for sub_file_path in sub_file_paths:
move_target_file_path = sub_file_path.replace(replace_ad_str, '')
if os.path.isfile(move_target_file_path):
log.warn(
'The target file is exist: {}'.format(move_target_file_path))
continue
log.info('rename file: {} --> file: {}'.format(sub_file_path,
move_target_file_path))
os.replace(sub_file_path, move_target_file_path)
def generate_gitbook_summary(source_dir):
"""
生成gitbook的summary目录文件，通过遍历文件目录树实现
:param source_dir: source_dir
:return:
"""
sub_file_paths = u_file.get_all_sub_files(source_dir, contain_dir=True)
summary_content = ''
sub_file_paths.sort()
exclude_paths = [
'.git', '.idea', 'assets', 'temp', 'node_modules', '_book'
]
for sub_file_path in sub_file_paths:
relative_path = sub_file_path.replace(source_dir + '\\', '')
# 过滤掉非markdown文件
ignore = False
for exclude_path in exclude_paths:
if sub_file_path.find(exclude_path) >= 0:
ignore = True
if ignore:
continue
path_depth = relative_path.count('\\')
menu = ' ' * path_depth
if os.path.isfile(sub_file_path):
if sub_file_path.find('.md') >= 0:
menu += '- [{}]({})'.format(
os.path.split(relative_path)[1].replace('.md', ''),
relative_path)
else:
continue
else:
menu += '- {}'.format(relative_path.split('\\')[-1])
summary_content += menu + "\n"
u_file.write_content(r'cache\result.md', summary_content)
print(summary_content)
def modify_picture_suffix(source_directory):
"""
批量修改图片后缀名，垃圾微信报错GIF图片有问题
:param source_directory: 需要处理的文件夹路径
:return:
"""
sub_file_paths = u_file.get_all_sub_files(source_directory)
min_gif_picture_size = 500 * 1024
for sub_file_path in sub_file_paths:
if os.path.isdir(sub_file_path):
log.info('The file is directory: {}'.format(sub_file_path))
continue
if os.path.getsize(sub_file_path) < min_gif_picture_size:
log.info('The file size is small. file: {}, size: {}'.format(
sub_file_path, os.path.getsize(sub_file_path)))
continue
sub_file_name = os.path.split(sub_file_path)[1]
sub_file_name_suffix = os.path.splitext(sub_file_name)[1]
move_target_file_path = sub_file_path.replace(sub_file_name_suffix,
".gif")
log.info('move file: {} --> file: {}'.format(sub_file_path,
move_target_file_path))
os.replace(sub_file_path, move_target_file_path)
def test_get_all_sub_files():
root_path = r'D:\BaiduNetdiskDownload\最新免费国外hdr环境高清贴图批量下载_By佐邦视觉'
file_paths = u_file.get_all_sub_files(root_path)
u_log.info('file size: {}'.format(len(file_paths)))