Python实现一键整理百度云盘中重复无用文件

import sqlite3
import pandas as pd

file_dict = {}  
con = sqlite3.connect('BaiduYunCacheFileV0.db')
cursor = con.cursor()  
cursor.execute("select * from cache_file") 
values = cursor.fetchall()

df = pd.DataFrame(values,columns=["id","fid","parent_path","server_filename","file_size","md5","isdir","category","server_mtime","local_mtime","reserved1","reserved2","reserved3","reserved4","reserved5","reserved6","reserved7","reserved8","reserved9"])
df.to_excel("data.xlsx")

df["server_filename"].duplicated()

0         False
1         False
2         False
3         False
4         False
          ...  
379563    False
379564    False
379565     True
379566     True
379567    False
Name: server_filename, Length: 379568, dtype: bool


df[df["server_filename"].duplicated()]["server_filename"]
188             WE_rk_nos06.txt
252                   django.po
254                   django.po
255                   django.po
256                   django.po
                  ...          
378517                video.mp4
378518            top_level.txt
378543    Blog_articleinfo.xlsx
379565                     apps
379566              职业培训规划.mmap
Name: server_filename, Length: 152409, dtype: object