typora删除多余图片

import os
import re
import shutil
from bs4 import BeautifulSoupimport warningswarnings.filterwarnings('ignore')
# 定义正则表达式用于匹配.md文件中的图片引用语句
pattern = re.compile(r'!\[.*]\((.*)\)')# 获取所有.md文件中的图片引用路径
references = set()
md_filepath = input("请输入 Markdown 文件所在目录的路径 : ")
# md_filepath = r'{}'.format(md_filepath)for file in os.listdir(md_filepath):if file.endswith('.md'):  # 扫描该路径下的所有.md文件，并查找其中的图片with open(os.path.join(md_filepath, file), 'r', encoding='utf-8') as f:text = f.read()references.update(pattern.findall(text))soup = BeautifulSoup(text, 'html.parser')for img in soup.find_all('img'):src = img.get('src')if src:references.add(os.path.join(md_filepath, src))print(f"在此路径中的所有.md文件中总共找到的所有图片{len(references)}张\n")
hyperlink_pattern = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\$\$,]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
print("寻找到的超链接:")
print([item for item in references if hyperlink_pattern.search(item)])
# C:\Users\asssio\Desktop\mark
# 删除包含超链接的元素
references_new = [item for item in references if not hyperlink_pattern.search(item)]
print(f"在此路径中的所有.md文件中总共找到引用图片{len(references_new)}张")
print("寻找到的实际链接:")
print(references_new)usedImages = set()
for each in references_new:usedImages.add(each.split('/')[-1])# 获取.assets目录的路径
assets_filepath = input("请输入.assets目录的路径: ")# 遍历.assets目录中的所有文件，将未被引用的图片移动到 delete 目录中
if not os.path.exists(os.path.join(assets_filepath, 'delete')):os.mkdir(os.path.join(assets_filepath, 'delete'))allImageNum = 0
deleteNum = 0
for file in os.listdir(assets_filepath):allImageNum += 1# print(file)if file not in usedImages:shutil.move(os.path.join(assets_filepath, file), os.path.join(assets_filepath, 'delete'))print(f"移动图片{file}到delete文件夹中")deleteNum += 1print(f"assert文件夹中总共有图片{allImageNum}张\n总共移动{deleteNum}张图片到delete中")

运行结果