0.准备条件：文件夹为中文名，图片内含有多个下划线。
处理目标：处理成为一个
“公共标|逗号| 一个句子"的形式。
1.（统计中文，准备翻译）文件夹结构作为数据统计入excel
import os
import pandas as pd
def find_image_folders(parent_directory):
"""
遍历父目录，寻找所有包含图片的子目录。
返回一个包含有图片的文件夹名称的列表。
"""
image_folders = []
for root, dirs, files in os.walk(parent_directory):
for file in files:
if file.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff', '.webp')):
folder_name = os.path.basename(root)
if folder_name not in image_folders:
image_folders.append(folder_name)
break # 一旦找到图片，停止搜索该目录
return image_folders
def create_excel_file(parent_directory, folder_names):
"""
在父目录中创建一个Excel文件，列出文件夹名称。
"""
df = pd.DataFrame(folder_names, columns=["文件夹名称"])
output_path = os.path.join(parent_directory, "文件夹名统计.xlsx")
df.to_excel(output_path, index=False)
return output_path
# 使用方法
parent_directory = input("请输入父目录的路径: ")
image_folders = find_image_folders(parent_directory)
excel_file_path = create_excel_file(parent_directory, image_folders)
print(f"Excel文件已创建在: {excel_file_path}")
2.根据表格第一行的中文，批量黏贴进chatgpt进行翻译。
3.在每个文件夹下建立txt，txt名根据excel的第二列数据（翻译完的英文）。
import os
import openpyxl
from pathlib import Path
def create_text_file(folder_path, file_name):
with open(Path(folder_path) / f"{file_name}.txt", 'w') as f:
pass
def find_and_create_files(excel_path, parent_dir):
# 加载Excel文件
workbook = openpyxl.load_workbook(excel_path)
sheet = workbook.active
# 读取第一列和第二列数据
folder_names = [cell.value for cell in sheet['A'] if cell.value is not None]
file_titles = [cell.value for cell in sheet['B'] if cell.value is not None]
# 遍历父目录下的所有子目录
for root, dirs, files in os.walk(parent_dir):
for dir_name in dirs:
if dir_name in folder_names:
index = folder_names.index(dir_name)
create_text_file(Path(root) / dir_name, file_titles[index])
def main():
excel_path = input("请输入Excel表格的完整路径: ")
parent_dir = input("请输入父目录的完整路径: ")
find_and_create_files(excel_path, parent_dir)
if __name__ == "__main__":
main()
4.根据txt名批量命名文件，删去乱码
import os
import re
UNWANTED_UNITS = ["undefined", "皮皮", "zly324"]
IMAGE_EXTENSIONS = [".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff"]
# 检查文件是否为图片
def is_image_file(filename):
_, ext = os.path.splitext(filename)
return ext.lower() in IMAGE_EXTENSIONS
# 获取文件夹内第一个txt文件的名称（不包括扩展名）
def get_first_txt_title(path):
try:
for file in os.listdir(path):
if file.endswith(".txt"):
return os.path.splitext(file)[0]
except Exception as e:
print(f"在'{path}'检查txt文件时发生错误：{e}")
return None
# 生成唯一的新文件名
def generate_unique_filename(path, filename, ext):
new_file_path = os.path.join(path, filename + ext)
counter = 1
while os.path.exists(new_file_path):
new_file_path = os.path.join(path, f"{filename}({counter}){ext}")
counter += 1
return new_file_path
# 重命名图片文件
def rename_image_files(path, prefix):
if not prefix: # 如果没有找到txt文件或文件夹中没有txt文件
print(f"在'{path}'中未找到txt文件或txt文件为空，跳过重命名操作。")
return
try:
files = [f for f in os.listdir(path) if is_image_file(f) and os.path.isfile(os.path.join(path, f))]
counter = 1
for file in files:
filename, ext = os.path.splitext(file)
# 乱码类
if re.search(r'[a-f0-9]{32}', filename) or not '_' in filename:
renamed = f"({counter})"
counter += 1
else:
parts = re.split(r'[_]+', filename)
parts.pop(0) # 删除第一个单元
# 删除特定的单元
parts = [part for part in parts if part not in UNWANTED_UNITS]
# 删除所有带数字的单元
parts = [part for part in parts if not any(char.isdigit() for char in part)]
# 删除特定规则的元素
while parts and re.search(r'^[a-f0-9\-]{32,}$', parts[-1]):
parts.pop(-1)
while parts and len(parts[-1]) <= 4:
parts.pop(-1)
renamed = '_'.join(parts)
# 添加前缀
renamed = f"{prefix}_{renamed}"
# 生成唯一的文件名
new_file_path = generate_unique_filename(path, renamed, ext)
os.rename(os.path.join(path, file), new_file_path)
print(f"在'{path}'中重命名完成。")
except Exception as e:
print(f"在'{path}'中重命名过程中发生错误：{e}")
# 遍历并重命名子文件夹中的图片文件
def rename_images_in_subfolders(root_path):
for subdir, dirs, _ in os.walk(root_path):
prefix = get_first_txt_title(subdir)
if prefix:
rename_image_files(subdir, prefix)
# 主函数
def main():
root_path = input("请输入总文件夹地址: ")
rename_images_in_subfolders(root_path)
if __name__ == "__main__":
main()
5.根据txt名批量命名文件，删去乱码
import os
import re
UNWANTED_UNITS = ["undefined", "皮皮", "zly324"]
IMAGE_EXTENSIONS = [".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff"]
# 检查文件是否为图片
def is_image_file(filename):
_, ext = os.path.splitext(filename)
return ext.lower() in IMAGE_EXTENSIONS
# 获取文件夹内第一个txt文件的名称（不包括扩展名）
def get_first_txt_title(path):
try:
for file in os.listdir(path):
if file.endswith(".txt"):
return os.path.splitext(file)[0]
except Exception as e:
print(f"在'{path}'检查txt文件时发生错误：{e}")
return None
# 生成唯一的新文件名
def generate_unique_filename(path, filename, ext):
new_file_path = os.path.join(path, filename + ext)
counter = 1
while os.path.exists(new_file_path):
new_file_path = os.path.join(path, f"{filename}({counter}){ext}")
counter += 1
return new_file_path
# 重命名图片文件
def rename_image_files(path, prefix):
if not prefix: # 如果没有找到txt文件或文件夹中没有txt文件
print(f"在'{path}'中未找到txt文件或txt文件为空，跳过重命名操作。")
return
try:
files = [f for f in os.listdir(path) if is_image_file(f) and os.path.isfile(os.path.join(path, f))]
counter = 1
for file in files:
filename, ext = os.path.splitext(file)
# 乱码类
if re.search(r'[a-f0-9]{32}', filename) or not '_' in filename:
renamed = f"({counter})"
counter += 1
else:
parts = re.split(r'[_]+', filename)
parts.pop(0) # 删除第一个单元
# 删除特定的单元
parts = [part for part in parts if part not in UNWANTED_UNITS]
# 删除所有带数字的单元
parts = [part for part in parts if not any(char.isdigit() for char in part)]
# 删除特定规则的元素
while parts and re.search(r'^[a-f0-9\-]{32,}$', parts[-1]):
parts.pop(-1)
while parts and len(parts[-1]) <= 4:
parts.pop(-1)
renamed = '_'.join(parts)
# 添加前缀
renamed = f"{prefix}_{renamed}"
# 生成唯一的文件名
new_file_path = generate_unique_filename(path, renamed, ext)
os.rename(os.path.join(path, file), new_file_path)
print(f"在'{path}'中重命名完成。")
except Exception as e:
print(f"在'{path}'中重命名过程中发生错误：{e}")
# 遍历并重命名子文件夹中的图片文件
def rename_images_in_subfolders(root_path):
for subdir, dirs, _ in os.walk(root_path):
prefix = get_first_txt_title(subdir)
if prefix:
rename_image_files(subdir, prefix)
# 主函数
def main():
root_path = input("请输入总文件夹地址: ")
rename_images_in_subfolders(root_path)
if __name__ == "__main__":
main()
6.下划线处理：第一个转逗号加空格，后面的转空格
import os
import shutil
def copy_directory(src, dst):
"""复制 src 目录到 dst 目录。"""
try:
shutil.copytree(src, dst)
except FileExistsError:
print(f"备份目录 '{dst}' 已存在。")
def rename_image_files(directory):
"""重命名图片文件，第一个下划线转换为逗号加空格，其他下划线转换为空格。"""
for root, dirs, files in os.walk(directory):
for file in files:
if file.lower().endswith(('.png', '.jpg', '.jpeg', '.gif')):
parts = file.split('_')
if len(parts) > 1:
new_file_name = parts[0] + ', ' + ' '.join(parts[1:])
else:
new_file_name = file
if new_file_name != file:
original_file_path = os.path.join(root, file)
new_file_path = os.path.join(root, new_file_name)
increment = 1
while os.path.exists(new_file_path):
file_name, file_extension = os.path.splitext(new_file_name)
new_file_name = f"{file_name} ({increment}){file_extension}"
new_file_path = os.path.join(root, new_file_name)
increment += 1
os.rename(original_file_path, new_file_path)
print(f"文件 {original_file_path} 已重命名为 {new_file_path}")
def delete_specified_files(directory):
"""删除所有txt和excel文件。"""
for root, dirs, files in os.walk(directory):
for file in files:
if file.lower().endswith(('.txt', '.xlsx')):
os.remove(os.path.join(root, file))
print(f"文件 {file} 已删除。")
def main():
input_directory = input("请输入要处理的目录路径: ")
if not os.path.exists(input_directory):
print(f"指定的目录 {input_directory} 不存在。")
return
backup_directory = os.path.join(input_directory, "_backup")
print(f"正在创建备份目录: {backup_directory}")
copy_directory(input_directory, backup_directory)
print("正在重命名备份目录中的图片文件...")
rename_image_files(backup_directory)
print("正在删除备份目录中的txt和excel文件...")
delete_specified_files(backup_directory)
print("操作完成。")
if __name__ == "__main__":
main()
标签：流程,MJ,parts,file,path,directory,精品,txt,os From： https://www.cnblogs.com/zly324/p/17915061.html