Python实现删除重复文件的示例代码

import os
import hashlib

def hash_file(filename):
    """Return the SHA-1 hash
    of the file content."""
    h = hashlib.sha1()
    with open(filename, 'rb') as f:
        while True:
            chunk = f.read(4096)
            if not chunk:
                break
            h.update(chunk)
    return h.hexdigest()

def remove_duplicate_files(path):
    """Remove duplicates files in the directory."""
    files_hash = {}
    i=0
    j=0
    sum=len(os.listdir(path))
    for dirpath, dirnames, filenames in os.walk(path):
        for filename in filenames:
            j=j+1
            print("执行进度为：",100*j/sum,"%")
            file_path = os.path.join(dirpath, filename)
            file_hash = hash_file(file_path)
            if file_hash in files_hash:
                os.remove(file_path)
                i=i+1
                # print(i)
            else:
                files_hash[file_hash] = file_path
    print("文件总数为：",sum)
    print("此处处理的重复文件数目为：",i)

remove_duplicate_files("Y:\图片合集")

import os
import re


class file_clean:
    def __init__(self, folder, filerege):
        self.folder = folder
        self.filerege = filerege
        self.folder_generator = os.walk(self.folder)

    # 删除所有文件夹及子文件夹下指定文件
    def del_all_file(self):
        for folder, subfolder, file_list in self.folder_generator:
            for file in file_list:
                if self.filerege == '*':
                    del_all_file = os.path.join(folder, file)
                    os.remove(del_all_file)
                elif re.findall(self.filerege, file):
                    del_all_file = os.path.join(folder, file)
                    print(del_all_file)
                    os.remove(del_all_file)

    # 只删除所有文件夹下的指定文件
    def del_file(self):
        for folder, subfolder, file_list in self.folder_generator:
            if os.path.dirname(folder) == os.path.dirname(self.folder):
                for file in file_list:
                    if self.filerege == '*':
                        del_file = os.path.join(folder, file)
                        os.remove(del_file)
                    elif re.findall(self.filerege, file):
                        del_file = os.path.join(folder, file)
                        print(del_file)
                        os.remove(del_file)


if __name__ == '__main__':
    # 选择文件夹路径 D盘C盘目录需要使用双斜杠r'D:\\', '\.wedrive'
    go = file_clean(r'D:\eong', '\.WeDrive')
    # 选择要执行的函数类型del_all_file删除件夹及子文件夹下指定文件，del_file只删除当前选择文件夹的指定文件
    go.del_file()

import os 
import hashlib 
import logging 
import sys 
 
def logger(): 
 """ 获取logger""" 
 logger = logging.getLogger() 
 if not logger.handlers: 
 # 指定logger输出格式 
 formatter = logging.Formatter('%(asctime)s %(levelname)-8s: %(message)s') 
 # 文件日志 
 file_handler = logging.FileHandler("test.log") 
 file_handler.setFormatter(formatter) # 可以通过setFormatter指定输出格式 
 # 控制台日志 
 console_handler = logging.StreamHandler(sys.stdout) 
 console_handler.formatter = formatter # 也可以直接给formatter赋值 
 # 为logger添加的日志处理器 
 logger.addHandler(file_handler) 
 logger.addHandler(console_handler) 
 # 指定日志的最低输出级别，默认为WARN级别 
 logger.setLevel(logging.INFO) 
 return logger 
 
def get_md5(filename): 
 m = hashlib.md5() 
 mfile = open(filename, "rb") 
 m.update(mfile.read()) 
 mfile.close() 
 md5_value = m.hexdigest() 
 return md5_value 
 
def get_urllist(): 
 #替换指定的文件夹路径即可 
 base = ("F:\\pythonFile\\煎蛋网\\无聊图\\jpg\\") 
 list = os.listdir(base) 
 urlList=[] 
 for i in list: 
 url = base + i 
 urlList.append(url) 
 return urlList 
 
if __name__ == '__main__': 
 log = logger() 
 md5List =[] 
 urlList =get_urllist() 
 for a in urlList: 
 md5 =get_md5(a) 
 if (md5 in md5List): 
  os.remove(a) 
  print("重复：%s"%a) 
  log.info("重复：%s"%a) 
 else: 
  md5List.append(md5) 
  # print(md5List) 
  print("一共%s张照片"%len(md5List))