Python文件处理、os模块、glob模块

open(file, mode='r')

open(file, mode='r', buffering=-1, encoding=None, errors=None, newline=None, closefd=True, opener=None)

f = open(r'/Users/mac/desktop/jupyter/pythonCourseware/32.txt', mode='r')# read模式打开文件
data = f.read() # 读取文件内容，向操作系统发起读请求，会被操作系统转成具体的硬盘操作，将内容由硬盘读入内存
print(data)
# 由于Python的垃圾回收机制只回收引用计数为0的变量，但是打开文件还占用操作系统的资源，所以我们需要回收操作系统的资源资源
# del f 只是回收变量f
f.close()

# write模式打开文件
f = open(r'/Users/mac/desktop/jupyter/pythonCourseware/32.txt', mode='w')
f.write("""name = 'nick'
pwd = '123'""")
f.close()

with open('32.txt', 'rt', encoding='utf8') as f:
    print(f.read())

with open('32.txt', 'rb') as fr, \
        open('35r.txt', 'wb') as fw:
    f.write(f.read())

# rt: read by text
# windows的操作系统默认编码为gbk，因此需要使用utf8编码
f = open('32.txt', mode='rt', encoding='utf8')
data = f.read()
print(data) # nick最帅吗
print(type(data)} # <class 'str'>
f.close()

# rb: read by bytes
f = open('32.txt', mode='rb')
data = f.read()
print(data) # b'aaa\nbbb\nccc\nnick\xe6\x9c\x80\xe5\xb8\x85\xe5\x90\x97'
print(type(data)) # <class 'bytes'>
f.close()

fname = input("请输入要打开的文件名称:")
fo = open(fname, "r")
print(type(fo))  # <class '_io.TextIOWrapper'>
for line in fo:
    print(line)
fo.close()

f = open('32.txt', mode='rt', encoding='utf8')
print(f.readable())  #True 判断文件是否可读
data1 = f.readline()
data2 = f.readlines()
print(data1) # aaa
print(data2) # ['bbb\n', 'ccc\n', 'nick最帅吗']
f.close()

f = open('34w.txt', mode='wt', encoding='utf8')
print(f"f.readable(): {f.readable()}") #False
f.write('nick 真帅呀\n')  # '\n'是换行符
f.write('nick,nick, you drop, I drop.')
f.write('nick 帅的我五体投地')
f.flush()  # 立刻将文件内容从内存刷到硬盘
f.close()

f = open('34a.txt', mode='wb')
f.write('nick 帅的我五体投地'.encode('unicode_escape') )  # 编码成bytes类型再写入
print(type('nick 帅的我五体投地'.encode('unicode_escape'))) #<class 'bytes'>
f.close()

try:
    import requests

    response = requests.get( '/file/upload/202211/11/gjvm3aw2m2t.jpg')
    data = response.content

    f = open('mv.jpg', 'wb')
    f.write(data)
    print('done...')
    f.close()
except Exception as e:
    print(e, '报错了，那就算了吧，以后爬虫处会详细介绍')

# at
f = open('34a.txt', mode='at', encoding='utf8')
print(f.readable()) # False
f.write('nick 真帅呀\n')  # '\n'是换行符
f.write('nick,nick, you drop, I drop.')
f.write('nick 帅的我五体投地')
f.close()

# r+t
with open('32.txt', 'r+', encoding='utf-8') as fr:
    print(fr.readable())  # True
    print(fr.writable())  # True

f.seek(0) # 回到文件开头

f = open('32.txt', 'rb+')
print(f.write(b'0123456789abcdef')) # 16
print(f.seek(5))  # 移动到文件的第六个字节 # 5
print(f.read(1))  # b'5'
print(f.seek(-3, 2))  # 移动到文件的倒数第三字节 # 13
print(f.read(1)) # b'd'

with open('32.txt', 'rb') as fr:
    fr.seek(4, 0)
    print(fr.tell() )  # 4

with open('32.txt', 'ab') as fr:
    fr.truncate(2)  # 截断2个字节后的所有字符，如果3个字节一个字符，只能截断2/3个字符，还会遗留1/3个字符，会造成乱码

import os

with open('37r.txt') as fr, open('37r_swap.txt', 'w') as fw:
    data = fr.read()  # 全部读入内存,如果文件很大,会很卡
    data = data.replace('tank', 'tankSB')  # 在内存中完成修改

    fw.write(data)  # 新文件一次性写入原文件内容

# 删除原文件
os.remove('37r.txt')
# 重命名新文件名为原文件名
os.rename('37r_swap.txt', '37r.txt')

import os

with open('37r.txt') as fr, open('37r_swap.txt', 'w') as fw:
     for line in fr: # 循环读取文件内容，逐行修改
        line = line.replace('jason', 'jasonSB')
        fw.write(line)  # 新文件写入原文件修改后内容

os.remove('37r.txt')
os.rename('37r_swap.txt', '37r.txt')

import os

import os
import os.path

"""获取指定目录及其子目录下的 py 文件路径说明：l 用于存储找到的 py 文件路径 get_py 函数，递归查找并存储 py 文件路径于 l"""
l = []


def get_py(path, l):
    file_list = os.listdir(path)  # 获取path目录下所有文件
    for filename in file_list:
        path_tmp = os.path.join(path, filename)  # 获取path与filename组合后的路径
        if os.path.isdir(path_tmp):  # 如果是目录
            get_py(path_tmp, l)  # 则递归查找
        elif filename[-3:].upper() == '.PY':  # 不是目录,则比较后缀名
            l.append(path_tmp)


path = input('请输入路径:').strip()
get_py(path, l)
print('在%s目录及其子目录下找到%d个py文件\n分别为：\n' % (path, len(l)))
for filepath in l:
    print(filepath + '\n')

import os

vedio_list = []

def search_file(start_dir, target) :
    os.chdir(start_dir)
    
    for each_file in os.listdir(os.curdir) :
        ext = os.path.splitext(each_file)[1]
        if ext in target :
            vedio_list.append(os.getcwd() + os.sep + each_file + os.linesep) 
        if os.path.isdir(each_file) :
            search_file(each_file, target) # 递归调用
            os.chdir(os.pardir) # 递归调用后切记返回上一层目录

start_dir = input('请输入待查找的初始目录：')
program_dir = os.getcwd()

target = ['.mp4', '.avi', '.rmvb']

search_file(start_dir, target)

f = open(program_dir + os.sep + 'vedioList.txt', 'w')
f.writelines(vedio_list)
f.close()

import os

path = input('请输入文件路径(结尾加上/)：')

# 获取该目录下所有文件，存入列表中
fileList = os.listdir(path)

n = 0
for i in fileList:
    # 设置旧文件名（就是路径+文件名）
    oldname = path + os.sep + fileList[n]  # os.sep添加系统分隔符

    # 设置新文件名
    newname1 = path + os.sep + 'a' + str(n + 1) + '.JPG'

    os.rename(oldname, newname1)  # 用os模块中的rename方法对文件改名c:\
    print(oldname, '======>', newname1)

    n += 1

import glob

file = glob.glob(r'C:\工具\*\*\pan*.exe')
print(type(file))  # <class 'list'>
print(file)  # ['C:\\工具\\PanDownload_v2.1.3\\PanDownload\\PanDownload.exe']

#获取上级目录的所有.py文件
print (glob.glob(r'../*.py')) #相对路径

import glob

#父目录中的.py文件
f = glob.iglob(r'../*.py')
print ( f ) # <generator object iglob at 0x00B9FF80>
for py in f:
   print  (py)