Python常用模块

import json

dic = {'k1':'v1','k2':'v2','k3':'v3'}
str_dic = json.dumps(dic)#将Python中的类型转换为字符串
# 序列化：将一个字典转换成一个字符串

print(type(str_dic),str_dic)
dic2 = json.loads(str_dic)#字符串转回原本的类型
print(type(dic2),dic2)
# 反序列化：将一个字符串格式的字典转换成一个字典

list_dic = [1,['a','b','c'],3,{'k1':'v1','k2':'v2'}]
str_dic = json.dumps(list_dic)

print(type(str_dic),str_dic)
list_dic2 = json.loads(str_dic)
print(type(list_dic2),list_dic2)

import json

data = {'name':'马牛逼','sex':'female','age':88}
json_dic2 = json.dumps(data,sort_keys=True,indent=2,separators=
(',',':'),ensure_ascii=False)
print(json_dic2)

序列化：
import json
v = {'k1':'yh','k2':'小马过河'}
f = open('xiaoma.txt',mode='w+',encoding='utf-8') #文件不存在就会生成
val = json.dump(v,f,ensure_ascii=False)
data=f.read()
print(type(data))
print(val)
f.close()
----------------结果：

None
#dump将内容序列化，并写入打开的文件中。

反序列化：
import json
f = open('xiaoma.txt',mode='r',encoding='utf-8')
data = json.load(f)
f.close()
print(data,type(data))
---------------结果:
{'k1': 'yh', 'k2': '小马过河'} 

import pickle
dic = {'k1':'v1','k2':'v2','k3':'v3'}
str_dic = pickle.dumps(dic)
print(str_dic)

dic2 = pickle.loads(str_dic)
print(dic2)

import time
struct_time = time.localtime(1000000000)
print(struct_time)
f = open('pickle_file','wb')
pickle.dump(struct_time,f)
f.close()

f = open('pickle_file','rb')
struct_time2 = pickle.load(f)
print(struct_time2.tm_year)

import shelve
f = shelve.open('shelve_file')
f['key'] = {'int':10,'str':'hello','float':0.123}
f.close()

f1 = shelve.open('shelve_file')
ret = f1['key']
f1.close()
print(ret)

import shelve
f1 = shelve.open('shelve_file',flag='r')
ret = f1['key']
f1.close()
print(ret)

import shelve
f1 = shelve.open('shelve_file')
print(f1['key'])
f1['key']['k1'] = 'v1'
print(f1['key'])
f1.close()

f2 = shelve.open('shelve_file',writeback=True) #开启后才能写生效

f2['key']['k1'] = 'hello'
print(f2['key'])
f2.close()

# 简单的数据库

import sys,shelve

def print_help():
'存储（增加）、查找、更新（修改）、循环打印、删除、退出、帮助'
    print('The available commons are: ')
    print('store : Stores information about a person')
    print('lookup : Looks up a person from ID numbers')
    print("update : Update a person's information from ID number")
    print('print_all: Print all informations')
    print("delete : Delete a person's information from ID number")
    print('quit : Save changes and exit')
    print('? : Print this message')
    
def store_people(db):
    pid = input('Please enter a unique ID number: ')
    person = {}
    person['name'] = input('Please enter the name: ')
    person['age'] = input('Please enter the age: ')
    person['phone'] = input('Please enter the phone: ')
    db[pid] = person
    print("Store information: pid is %s, information is %s" % (pid, person))
    
def lookup_people(db):
    pid = input('Please enter the number: ')
    field = input('What would you like to know? (name, age, phone) ')
    if pid in db.keys():
        value = db[pid][field]
        print("Pid %s's %s is %s" % (pid, field, value))
    else:
        print('Not found this number')
        
def update_people(db):
    pid = input('Please enter the number: ')
    field = input('What would you like to update? (name, age, phone) ')
    newvalue = input('Enter the new information: ')
    if pid in db.keys():
        value = db[pid]
        value[field] = newvalue
        print("Pid %s's %s update information is %s" % (pid, field,newvalue))
    else:
        print("Not found this number, can't update")
        
def delete_people(db):
    pid = input('Please enter the number: ')
    if pid in db.keys():
        del db[pid]
        print("pid %s's information delete done" % pid)
    else:
        print( "Not found this number, can't delete")
        
def print_all_people(db):
    print( 'All information are: ')
    for key, value in db.items():
        print(key, value)
        
def enter_cmd():
    cmd = input('Please enter the cmd(? for help): ')
    cmd = cmd.strip().lower()
    return cmd
    
def main():
    database = shelve.open('database201803.dat', writeback=True)
    try:
        while True:
            cmd = enter_cmd()
            if cmd == 'store':
                store_people(database)
            elif cmd == 'lookup':
                lookup_people(database)
            elif cmd == 'update':
                update_people(database)
            elif cmd == 'print_all':
                print_all_people(database)
            elif cmd == 'delete':
                delete_people(database)
            elif cmd == '?':
                print_help()
            elif cmd == 'quit':
                return
    finally:
        database.close()
if __name__ == '__main__':
    main()

import hashlib

md5 = hashlib.md5()
md5.update('how to use md5 in python hashlib?'.encode('utf-8'))
print(md5.hexdigest())

import hashlib

sha1 = hashlib.sha1()
sha1.update('how to use md5 '.encode('utf-8'))
sha1.update('in python hashlib?'.encode('utf-8'))
print(sha1.hexdigest())

#注册部分修改
    with open("db.txt", "a", encoding="utf-8") as write_file:
        md5=hashlib.md5()
        md5.update(user_name.encode('utf-8'))
        md5.update(user_password.encode('utf-8'))
        user_password_md5=md5.hexdigest()
        user_info = user_name + ":" + user_password_md5 + "\n
        write_file.write(user_info)
        print("注册成功")
        
#登录部分修改
    while True:
        # 确保用户密码正确
        user_password = input("请输入登录密码；\n")
        flag2 = False
        for dict4 in list1:
            md5 =hashlib.md5()
            md5.update(user_name.encode('utf-8'))
            md5.update(user_password.encode('utf-8'))
            user_password_md5=md5.hexdigest()
            if dict4["username"] == user_name and dict4["password"] ==user_password_md5:
                flag2 = True

name    | password
--------+----------
michael | 123456
bob     | abc999
alice   | alice2008

username | password
---------+---------------------------------
michael  | e10adc3949ba59abbe56e057f20f883e
bob      | 878ef96e86145580c38c87f0410ad153
alice    | 99b1c2188db85afee403b1536010c2c9

[default]
ServerAliveInterval = 45
Compression = yes
CompressionLevel = 9
ForwardX11 = yes

[bitbucket.org]
User = hg

[topsecret.server.com]
Port = 50022
ForwardX11 = no

import configparser

conf = configparser.ConfigParser()

conf['default'] = {'ServerAliveInterval':'45',
                 'Compression':'yes',
                 'CompressionLevel':'9',
                 'ForwardX11':'yes'
                 }
conf['bitbucket.org'] = {'User':'hg'}
conf['topsecret.server.com'] = {'Port':'50022',
                             'ForwardX11':'no'
                               }
with open('config','w') as config:
    conf.write(config)

import configparser

conf = configparser.ConfigParser()
conf.read('config')

secs = conf.sections()
print(secs)
for sec in secs:
    print(sec,conf.options(sec))

import configparser

conf = configparser.ConfigParser()
conf.read('config')

secs = conf.sections()
print(secs)
for sec in secs:
    print(sec,conf.options(sec))

serveraliveinterval=conf.get('default','serveraliveinterval')
print(serveraliveinterval)
user=conf.get('bitbucket.org','user')
print(user)

import configparser

conf = configparser.ConfigParser()
conf.read('config')

# 使用has_section来判断是否有这个section配置项，option可以使用has_option方法来判断是否存在
if not conf.has_section('ABC'):
    # 如果没有则添加这个section
    conf.add_section("ABC")
    # 并在该section下添加一个名叫abc的option项
    conf.set("ABC", "abc", "123")
conf.set('topsecret.server.com','ip','192.168.1.1')
    # 将这些修改写入到配置文件中
with open('config', 'w+') as f:
    conf.write(f)

import configparser

conf = configparser.ConfigParser()
conf.read('config')
# 删除ABC section，包含下面所有的option都会一并删除
conf.remove_section('ABC')
# 删除topsecret.server.com下的ip ，其他option不会受影响
conf.remove_option('topsecret.server.com', 'ip')

with open('config', 'w+') as f:
conf.write(f)

import configparser

conf = configparser.ConfigParser()
conf.read('config')

secs = conf.sections()
print(secs)
for sec in secs:
    print(sec,conf.options(sec))
    
serveraliveinterval=conf.get('default','serveraliveinterval')
print(serveraliveinterval)
user=conf.get('bitbucket.org','user')
print(user)

import configparser

conf = configparser.ConfigParser()
conf.read('config')

# 使用has_section来判断是否有这个section配置项，option可以使用has_option方法来判断是否存在

if not conf.has_section('ABC'):
    # 如果没有则添加这个section
    conf.add_section("ABC")
    # 并在该section下添加一个名叫abc的option项
    conf.set("ABC", "abc", "123")
conf.set('topsecret.server.com','ip','192.168.1.1')
    # 将这些修改写入到配置文件中
with open('config', 'w+') as f:
    conf.write(f)

import configparser

conf = configparser.ConfigParser()
conf.read('config')
# 删除ABC section，包含下面所有的option都会一并删除
conf.remove_section('ABC')
# 删除topsecret.server.com下的ip ，其他option不会受影响
conf.remove_option('topsecret.server.com', 'ip')

with open('config', 'w+') as f:
    conf.write(f)

import logging
#日志的五个等级
logging.debug('debug message')
logging.info('info message')
logging.warning('warning message')
logging.error('error message')
logging.critical('critical message')

import logging

logging.basicConfig(level=logging.DEBUG,
                  format='%(asctime)s %(filename)s[line:%(lineno)d] %
(levelname)s %(message)s',
                    datefmt='%a, %d %b %Y %H:%M:%S',
                    filename='test.log',
                    filemode='w')
                    
logging.debug('debug message')
logging.info('info message')
logging.warning('warning message')
logging.error('error message')
logging.critical('critical message')

import logging

logger = logging.getLogger()

# 创建一个handler，用于写入日志文件
fh = logging.FileHandler('test.log',encoding='utf-8')
# 再创建一个handler，用于输出到控制台
ch = logging.StreamHandler()

formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

fh.setFormatter(formatter)

ch.setFormatter(formatter)

logger.addHandler(fh) #logger对象可以添加多个fh和ch对象
logger.addHandler(ch)
logger.debug('logger debug message')
logger.info('logger info message')
logger.warning('logger warning message')
logger.error('logger error message')
logger.critical('logger critical message')

"""
logging配置
"""

import os
import logging.config

# 定义三种日志输出格式 开始

standard_format = '[%(asctime)s][%(threadName)s:%(thread)d][task_id:%(name)s][%(filename)s:%(lineno)d]' \
                  '[%(levelname)s][%(message)s]' #其中name为getlogger指定的名字
                  
simple_format = '[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d]%(message)s'

id_simple_format = '[%(levelname)s][%(asctime)s] %(message)s'

# 定义日志输出格式 结束

logfile_dir = os.path.dirname(os.path.abspath(__file__)) # log文件的目录

logfile_name = 'all2.log' # log文件名

# 如果不存在定义的日志目录就创建一个
if not os.path.isdir(logfile_dir):
    os.mkdir(logfile_dir)
    
# log文件的全路径
logfile_path = os.path.join(logfile_dir, logfile_name)

# log配置字典
LOGGING_DIC = {
    'version': 1,
    'disable_existing_loggers': False,
    'formatters': {
        'standard': {
            'format': standard_format
        },
        'simple': {
            'format': simple_format
        },
    },
    'filters': {},
    'handlers': {
        #打印到终端的日志
        'console': {
            'level': 'DEBUG',
            'class': 'logging.StreamHandler', # 打印到屏幕
            'formatter': 'simple'
        },
        #打印到文件的日志,收集info及以上的日志
        'default': {
            'level': 'DEBUG',
            'class': 'logging.handlers.RotatingFileHandler', # 保存到文件
            'formatter': 'standard',
            'filename': logfile_path, # 日志文件
            'maxBytes': 1024*1024*5, # 日志大小 5M
            'backupCount': 5,
            'encoding': 'utf-8', # 日志文件的编码，再也不用担心中文log乱码了
        },
    },
    'loggers': {
        #logging.getLogger(__name__)拿到的logger配置
        '': {
            'handlers': ['default', 'console'], # 这里把上面定义的两个handler都加上，即log数据既写入文件又打印到屏幕
            'level': 'DEBUG',
            'propagate': True, # 向上（更高level的logger）传递
        },
    },
}
def load_my_logging_cfg():
    logging.config.dictConfig(LOGGING_DIC) # 导入上面定义的logging配置
    logger = logging.getLogger(__name__) # 生成一个log实例
    logger.info('It works!') # 记录该文件的运行状态
    
if __name__ == '__main__':
    load_my_logging_cfg()

注意：


#1、有了上述方式我们的好处是：所有与logging模块有关的配置都写到字典中就可以了，更加清晰，方便管理


#2、我们需要解决的问题是：
    1、从字典加载配置：logging.config.dictConfig(settings.LOGGING_DIC)
    
    2、拿到logger对象来产生日志
    logger对象都是配置到字典的loggers 键对应的子字典中的
    按照我们对logging模块的理解，要想获取某个东西都是通过名字，也就是key来获取的
    于是我们要获取不同的logger对象就是
    logger=logging.getLogger('loggers子字典的key名')
    
    
但问题是：如果我们想要不同logger名的logger对象都共用一段配置，那么肯定不能在loggers子字典中定义n个key
'loggers': {
        'l1': {
            'handlers': ['default', 'console'], #
            'level': 'DEBUG',
            'propagate': True, # 向上（更高level的logger）传递
        },
        'l2: {
            'handlers': ['default', 'console' ],
            'level': 'DEBUG',
            'propagate': False, # 向上（更高level的logger）传递
        },
        'l3': {
            'handlers': ['default', 'console'], #
            'level': 'DEBUG',
            'propagate': True, # 向上（更高level的logger）传递
        },
}


#我们的解决方式是，定义一个空的key
    'loggers': {
        '': {
            'handlers': ['default', 'console'],
            'level': 'DEBUG',
            'propagate': True,
        },
}

这样我们再取logger对象时
logging.getLogger(__name__)，不同的文件__name__不同，这保证了打印日志时标识信息不同，但是拿着该名字去loggers里找key名时却发现找不到，于是默认使用key=''的配置

from collections import namedtuple
point = namedtuple('point',['x','y'])
p = point(1,2)
print(p.x)

from collections import deque

q = deque(['a','b','c'])
q.append('x')
q.appendleft('y')

print(q)

# 不用defaultdict的方式
li = [11,22,33,44,55,77,88,99,90]

result = {}
for row in li:
    if row < 66:
        if 'key1' not in result:
            result['key1']=[]
        result['key1'].append(row)
    else:
        if 'key2' not in result:
            result['key2']=[]
        result['key2'].append(row)
print(result)


# 用defaultdict的方式
from collections import defaultdict

li = [11,22,33,44,55,77,88,99,90]
result=defaultdict(list)
print(result)
for row in li:
    if row > 66:
        result['key1'].append(row)
    else:
        result['key2'].append(row)
        
print(result)

from collections import Counter

c = Counter('qazxswqazxswqazxswsxaqwsxaqws')
print(c)

import time

# 第一种时间格式，时间戳的形式
print(time.time())

# 第二种时间格式，格式化的时间
print(time.strftime('%Y-%m-%d %X'))
print(time.strftime('%Y-%m-%d %H-%M-%S'))

# 第三种时间格式，结构化的时间，是一个元组
print(time.localtime())

import time
# 格式化时间 ----> 结构化时间
ft = time.strftime('%Y/%m/%d %H:%M:%S')
print('ft',ft)
st = time.strptime(ft,'%Y/%m/%d %H:%M:%S')
print('st',st)
# 结构化时间 ---> 时间戳
t = time.mktime(st)
print('t',t)

# 时间戳 ----> 结构化时间
t = time.time()
st = time.localtime(t)
print('st',st)
# 结构化时间 ---> 格式化时间
ft = time.strftime('%Y/%m/%d %H:%M:%S',st)
print('ft',ft)

import time

#结构化时间 --> %a %b %d %H:%M:%S %Y串
#time.asctime(结构化时间) 如果不传参数，直接返回当前时间的格式化串
print(time.asctime(time.localtime(1550312090.4021888)))

#时间戳 --> %a %d %d %H:%M:%S %Y串
#time.ctime(时间戳) 如果不传参数，直接返回当前时间的格式化串
print(time.ctime(1550312090.4021888))

import time

start_time=time.mktime(time.strptime('2017-09-11 08:30:00','%Y-%m-%d
%H:%M:%S'))
end_time=time.mktime(time.strptime('2019-09-12 11:00:50','%Y-%m-%d
%H:%M:%S'))
dif_time=end_time-start_time
struct_time=time.gmtime(dif_time)
print('过去了%d年%d月%d天%d小时%d分钟%d秒'%(struct_time.tm_year-1970,struct_time.tm_mon-1,
struct_time.tm_mday-1,struct_time.tm_hour,

struct_time.tm_min,struct_time.tm_sec))

import time

for i in range(0,101,2):
    time.sleep(0.1)
    char_num = i//2
    per_str = '\r%s%% : %s\n' % (i, '*' * char_num) \
        if i == 100 else '\r%s%% : %s' % (i,'*'*char_num)
    print(per_str,end='', flush=True)

import time
print("游戏开始加载")
for i in range(0, 101, 2):
    time.sleep(0.1)
    char_num = i // 2
    per_str = '\r[%s' % ('#' * char_num)
    
    print(per_str+"%s" % "_" *(50 - char_num), "%s%%]" % i, end='')
print("")

# datatime模块
import datetime
now_time = datetime.datetime.now() # 现在的时间
# 只能调整的字段：weeks days hours minutes seconds
print(datetime.datetime.now() + datetime.timedelta(weeks=3)) # 三周后
print(datetime.datetime.now() + datetime.timedelta(weeks=-3)) # 三周前
print(datetime.datetime.now() + datetime.timedelta(days=-3)) # 三天前
print(datetime.datetime.now() + datetime.timedelta(days=3)) # 三天后
print(datetime.datetime.now() + datetime.timedelta(hours=5)) # 5小时后
print(datetime.datetime.now() + datetime.timedelta(hours=-5)) # 5小时前
print(datetime.datetime.now() + datetime.timedelta(minutes=-15)) # 15分钟前
print(datetime.datetime.now() + datetime.timedelta(minutes=15)) # 15分钟后
print(datetime.datetime.now() + datetime.timedelta(seconds=-70)) # 70秒前
print(datetime.datetime.now() + datetime.timedelta(seconds=70)) # 70秒后
current_time = datetime.datetime.now()
# 可直接调整到指定的 年 月 日 时 分 秒 等

print(current_time.replace(year=1977)) # 直接调整到1977年
print(current_time.replace(month=1)) # 直接调整到1月份
print(current_time.replace(year=1989,month=4,day=25)) # 1989-04-25
18:49:05.898601

# 将时间戳转化成时间
print(datetime.date.fromtimestamp(1232132131)) # 2009-01-17

import random

print(random.random()) # 大于0且小于1之间的小数
print(random.uniform(1,3)) # 大于1小于3的小数

print(random.randint(1,5)) # 大于等于1且小于等于5之间的整数
print(random.randrange(1,10,2)) # 大于等于1且小于10之间的奇数

ret = random.choice([1,'23',[4,5]]) # 1或者23或者[4,5]
print(ret)

a,b = random.sample([1,'23',[4,5]],2) # 列表元素任意2个组合 sample(seq, n) 从
序列seq中选择n个随机且独立的元素
print(a,b)
# 发牌

item = [1,3,5,7,9]
random.shuffle(item) # 打乱次序
print(item)

import random

def v_code():

    code = ''
    for i in range(5):
    
        num=random.randint(0,9)
        alf=chr(random.randint(65,90)) #chr() 用一个范围在 range（256）内的（就是0～255）整数作参数，返回一个对应的字符。返回值是当前整数对应的 ASCII 字符。
        add=random.choice([num,alf])
        code="".join([code,str(add)])
        
    return code
    
print(v_code())

def get_code():
    code = ''
    for i in range(5):
        num = random.randint(0, 9)
        alf = chr(random.randint(65, 90))  # 用ASCII码来返回大小写的字母
        add = random.choice([num, alf])
        code = ''.join([code, str(add)])
    # print(code)
    return code

def fight_whit_the_landowner():  # 斗地主游戏代码
    print("斗地主游戏即将开始")
    time_line()
    ci_shu = 0
    farmer1 = []
    farmer2 = []
    landowner = []
    card = []
    for i in range(1, 14):
        if i == 11:
            i = 'J'
        elif i == 12:
            i = 'Q'
        elif i == 13:
            i = 'K'
        elif i == 1:
            i = 'A'
    for i in range(1, 14):
        card.append("♠" + str(i))
        card.append("♣" + str(i))
        card.append("♦" + str(i))
        card.append("♥" + str(i))
    card.append('大王')
    card.append('小王')
    for i in range(1, 10):
        random.shuffle(card)

    while ci_shu < 51:
        farmer1.append(card[1])
        farmer2.append(card[ci_shu + 2])
        landowner.append(card[ci_shu + 3])
        ci_shu += 3
    print('''底牌：%s''' % card[52:55])
    landowner.append(card[52:55])
    print('''一号农民的牌：%s''' % farmer1)
    print('''二号农民的牌：%s''' % farmer2)
    print('''地主的牌：%s''' % landowner)
    choice = input("输入again重新来一局，输入quit退出")
    if choice == 'again':
        fight_whit_the_landowner()
    elif choice == 'quit':
        return
    else:
        return
        
fight_with_landowner()

import os

print(os.stat('.\config')) # 当前目录下的config文件的信息

# 运行结果
# os.stat_result(st_mode=33206, st_ino=2814749767208887, st_dev=1788857329,
st_nlink=1, st_uid=0, st_gid=0, st_size=185, st_atime=1550285376,
st_mtime=1550285376, st_ctime=1550285376)

import re

print(re.findall('\w','上大人123asdfg%^&*(_ \t \n)'))
print(re.findall('\W','上大人123asdfg%^&*(_ \t \n)'))

print(re.findall('\s','上大人123asdfg%^&*(_ \t \n)'))
print(re.findall('\S','上大人123asdfg%^&*(_ \t \n)'))

print(re.findall('\d','上大人123asdfg%^&*(_ \t \n)'))
print(re.findall('\D','上大人123asdfg%^&*(_ \t \n)'))

print(re.findall('\A上大','上大人123asdfg%^&*(_ \t \n)'))
print(re.findall('^上大','上大人123asdfg%^&*(_ \t \n)'))

print(re.findall('666\z','上大人123asdfg%^&*(_ \t \n)666'))
print(re.findall('666\Z','上大人123asdfg%^&*(_ \t \n)666'))
print(re.findall('666$','上大人123asdfg%^&*(_ \t \n)666'))

print(re.findall('\n','上大人123asdfg%^&*(_ \t \n)'))
print(re.findall('\t','上大人123asdfg%^&*(_ \t \n)'))

import re

print(re.findall('a.b', 'ab aab a*b a2b a牛b a\nb'))
print(re.findall('a.b', 'ab aab a*b a2b a牛b a\nb',re.DOTALL))

print(re.findall('a?b', 'ab aab abb aaaab a牛b aba**b'))

print(re.findall('a*b', 'ab aab aaab abbb'))
print(re.findall('ab*', 'ab aab aaab abbbbb'))

print(re.findall('a+b', 'ab aab aaab abbb'))

print(re.findall('a{2,4}b', 'ab aab aaab aaaaabb'))

print(re.findall('a.*b', 'ab aab a*()b')) #贪婪
print(re.findall('a.*?b', 'ab a1b a*()b, aaaaaab'))
# .*? 此时的?不是对左边的字符进行0次或者1次的匹配,
# 而只是针对.*这种贪婪匹配的模式进行一种限定:告知他要遵从非贪婪匹配 推荐使用!

# []: 括号中可以放任意一个字符,一个中括号代表一个字符
# - 在[]中表示范围,如果想要匹配上- 那么这个-符号不能放在中间.
# ^ 在[]中表示取反的意思.
print(re.findall('a.b', 'a1b a3b aeb a*b arb a_b'))
print(re.findall('a[abc]b', 'aab abb acb adb afb a_b'))
print(re.findall('a[0-9]b', 'a1b a3b aeb a*b arb a_b'))
print(re.findall('a[a-z]b', 'a1b a3b aeb a*b arb a_b'))
print(re.findall('a[a-zA-Z]b', 'aAb aWb aeb a*b arb a_b'))
print(re.findall('a[0-9][0-9]b', 'a11b a12b a34b a*b arb a_b'))
print(re.findall('a[*-+]b','a-b a*b a+b a/b a6b'))
print(re.findall('a[-*+]b','a-b a*b a+b a/b a6b'))
print(re.findall('a[^a-z]b', 'acb adb a3b a*b'))

# 分组：() 制定一个规则,将满足规则的结果匹配出来
print(re.findall('(.*?)_sb', 'cs_sb zhao_sb 日天_sb'))
print(re.findall('href="(.*?)"','点击'))

print(re.findall('compan(y|ies)','Too many companies have gone bankrupt, and
the next one is my company'))
print(re.findall('compan(?:y|ies)','Too many companies have gone bankrupt,
and the next one is my company'))
# 分组() 中加入?: 表示将整体匹配出来而不只是()里面的内容

import re

# findall 全部找到返回一个列表
print(re.findall('a','aghjmnbghagjmnbafgv'))

# search 只到找到第一个匹配然后返回一个包含匹配信息的对象,该对象可以通过调用group()方法
得到匹配的字符串,如果字符串没有匹配，则返回None
print(re.search('sb|chensong', 'chensong sb sb demon 日天'))
print(re.search('chensong', 'chensong sb sb barry 日天').group())

# match：None,同search,不过在字符串开始处进行匹配,完全可以用search+^代替match
print(re.match('sb|chensong', 'chensong sb sb demon 日天'))
print(re.match('chensong', 'chensong sb sb barry 日天').group())

# split 分割 可按照任意分割符进行分割,中括号里面写的所有符号都可以进行分割
print(re.split('[:：,;；，]','1;3,c,a：3'))

# sub 替换
print(re.sub('帅哥','sb','陈松是一个帅哥'))

# complie 根据包含的正则表达式的字符串创建模式对象。可以实现更有效率的匹配。
obj = re.compile('\d{2}')
print(obj.search('abc123eeee').group())
print(obj.findall('1231232aasd'))

ret = re.finditer('\d','asd123affess32432') # finditer返回一个存放匹配结果的迭代器
print(ret)
print(next(ret).group())
print(next(ret).group())
print([i.group() for i in ret])

import re

ret = re.search("<(?P\w+)>\w+","hello")
#利用?P的方式可以给匹配的东西添加一个标签名称，一次可以匹配多个内容，利用标签名称可以去取
print(ret.group('tag_name'))
print(ret.group())

ret = re.search(r"<(\w+)>\w+","hello")
# 如果不给组起名字，也可以用\序号来找到对应的组，表示要找的内容和前面的组内容一致
# 获取的匹配结果可以直接用group(序号)拿到对应的值
print(ret.group(1))
print(ret.group())

# 爬取小姐姐图片
https://www.3gbizhi.com/meinv/index_1.html

# 1.找个网站
# 2.找一下页面的规律
# 3.找一下图片链接和图片名
# 4.想办法下载
import os
import re
from urllib.request import Request, urlopen, urlretrieve

path = os.getcwd() + os.sep + "bizhi"


def download(n):
    if not os.path.isdir(path):
        os.makedirs(path)
    for i in range(1,n+1):
        url=f"https://www.3gbizhi.com/meinv/index_{str(i)}.html"
        print(url)
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.64 Safari/537.36'
        }
        request=Request(url=url,headers=headers)
        content=urlopen(request).read().decode("utf-8")
        # lazysrc="(.*?jpg)"
        # img alt="(.*?)"
        link=re.findall('lazysrc="(.*?jpg)"',content)
        name=re.findall('img alt="(.*?)"',content)
        ziplist=list(zip(name,link))
        for imgurl in ziplist:
            urlretrieve(imgurl[1],f'{path}{os.sep}{imgurl[0]}.jpg')
def main():
    n=int(input("请输入要下载的页数:"))
    download(n)
    print("下载完成，请查看文件夹")
if __name__ == '__main__':
    main()

# 爬取豆瓣top250
https://movie.douban.com/top250?start=0&filter=

import shutil

shutil.copyfileobj(open('config','r'),open('config.new','w'))

import shutil

shutil.copyfile('config','config1') # 目标文件无需存在

import shutil

shutil.copymode('config','config1') # 目标文件必须存在

import shutil

shutil.copystat('config','config1') # 目标文件必须存在

import shutil

shutil.copy('config','config1') # 目标文件必须存在

import shutil

shutil.copytree('folder1', 'folder2', ignore=shutil.ignore_patterns('*.pyc',
'tmp*'))
# 目标目录不能存在，注意对folder2目录父级目录要有可写权限，ignore的意思是排除
# 硬链接

shutil.copytree('f1', 'f2', symlinks=True,
ignore=shutil.ignore_patterns('*.pyc', 'tmp*'))
# 软链接

import shutil

shutil.rmtree('folder1')

import shutil

shutil.move('folder1', 'folder3')

# 将 /data 下的文件打包放置当前程序目录
import shutil
ret = shutil.make_archive("data_bak", 'gztar', root_dir='/data')

# 将 /data下的文件打包放置 /tmp/目录
import shutil
ret = shutil.make_archive("/tmp/data_bak", 'gztar', root_dir='/data')

import zipfile

# 压缩
z = zipfile.ZipFile('laxi.zip', 'w')
z.write('a.log')
z.write('data.data')
z.close()

# 解压
z = zipfile.ZipFile('laxi.zip', 'r')
z.extractall(path='.')
z.close()

import tarfile

# 压缩文件
t = tarfile.open('/tmp/egon.tar','w')
t.add('/test1/a.py',arcname='a.bak')
t.add('/test1/b.py',arcname='b.bak')
t.close()

# 解压缩文件
t = tarfile.open('/tmp/egon.tar','r')
t.extractall('/egon')
t.close()