Python ---- each module

1. serialization module (very, very important)

Serialization: a data structure (list, dict ....) is converted into a sequence specific (special string) process.

# l1 = [1, 2, 3]
# ret = str(l1)
# print(ret,type(ret))
# print(eval(ret))  # 不让用

# 文件存取时,遇到的矛盾.
# dic ={'username': '太白', 'password': 123}

# dic = {1: {'username': '太白', 'password': 123,'status': False},
#        2:{'username': 'alex', 'password': 123,'status': False}
#        }

# 这个字典能放在全局么?
# with open('register.json',encoding='utf-8',mode='w') as f1:
#     f1.write(str(dic))
# with open('register',encoding='utf-8') as f1:
#     ret = f1.read()
#     print(ret,type(ret))
#
# # 数据结构 --- > str() 存储在文件, 读取出来时,反转不回去.
# # 网络传输.
# l1 = [i for i in range(100000)]
# # 凡是数据通过网络传出去最终的格式必须bytes
# s1 = str(l1)
# b1 = s1.encode('utf-8')
# print(b1)  # b1可以发送出去
#
# s2 = b1.decode('utf-8')
# print(s2,type(s2))
# s2 转化不成列表了.

# 我们现在要解决的问题: 如果有一种特殊的字符串,这个字符串可以与任何的数据结构互相转换.

Category sequence module:

# 序列化模块: 将一中数据结构转化成特殊的序列(特殊的字符串,bytes)并且还可以反转回去.

    json模块: 是所有语言公认的一种序列.最最常用的
    所以支持的python数据结构有限: int str bool dict list(tuple),None,float

     None  ---> Null ----> NUll
     dict  --->
     pickle模块: 只能python语言中使用的,序列化模块:
     支持python所有的数据类型以及对象.
     shevle模块(不讲): 课下了解(只能是文件存取).

json serialization:

Two pairs of four methods:

dumps, loads mainly used for network transmission can be used to access the file.

import json
# dumps,loads 主要用于网络传输,可以用于文件的存取.
# dic = {'username': '太白', 'password': 123,'status': False}
# ret = json.dumps(dic)
# # print(ret,type(ret))

# ret_dict = json.loads(ret)
# print(ret_dict)

# 特殊的参数
# dic = {'username': '太白', 'password': 123,'status': False}
# # print(dic)
# ret = json.dumps(dic,ensure_ascii=False,sort_keys=True)
# print(ret,type(ret))
# import json
# dic = {'username': '太白', 'password': 123,'status': False}
# s_dict = json.dumps(dic)
# with open('jsonlx.json',encoding='utf-8',mode='w') as f1:
#     f1.write(s_dict)
#
# with open('jsonlx.json',encoding='utf-8') as f2:
#     content = f2.read()
#     print(json.loads(content))

How plurality of data storage to a file?

# 错误演示:
# import json
# dic1 = {'username': '太白', 'password': 123,'status': False}
# dic2 = {'username': 'alex', 'password': 123,'status': False}
# dic3 = {'username': 'ly', 'password': 123,'status': False}
# with open('jsonmore.json',encoding='utf-8',mode='a') as f1:
#     # f1.write(json.dumps(dic1))
#     # f1.write(json.dumps(dic2))
#     # f1.write(json.dumps(dic3))
#     f1.write(f'{json.dumps(dic1)}{json.dumps(dic2)}{json.dumps(dic3)}')

#
# with open('jsonmore.json',encoding='utf-8') as f1:
#     ret = json.loads(f1.read())
#     print(ret)

# 正确做法:

import json
# dic1 = {'username': '太白', 'password': 123,'status': False}
# dic2 = {'username': 'alex', 'password': 123,'status': False}
# dic3 = {'username': 'ly', 'password': 123,'status': False}
# with open('jsonmore.json',encoding='utf-8',mode='a') as f1:
#     f1.write(f'{json.dumps(dic1)}\n{json.dumps(dic2)}\n{json.dumps(dic3)}')

# with open('jsonmore.json',encoding='utf-8') as f1:
#     for line in f1:
#         ret = json.loads(line)
#         print(ret,type(ret))

pickle serialization:

dumps, loads can only be a network transmission

import pickle

# dumps,loads  只能是网络传输
# l1 = ['wusir', '太白', '小黑', 666]
# ret = pickle.dumps(l1)
# # print(ret)
#
# l2 = pickle.loads(ret)
# print(l2,type(l2))

dump load data structure to access the file.

import pickle
# l1 = ['wusir', '太白', '小黑', 666]
# with open('pickle练习.pickle',mode='wb') as f1:
#     pickle.dump(l1,f1)

# with open('pickle练习.pickle', mode='rb') as f1:
#     ret = pickle.load(f1)
#     print(ret,type(ret))

# 多个数据写入文件
l1 = ['wusir', '太白', '小黑1', 666]
l2 = ['wusir', '太白', '小黑2', 666]
l3 = ['wusir', '太白', '小黑3', 666]
# with open('pickle练习1.pickle',mode='wb') as f1:
# #     pickle.dump(l1,f1)
# #     pickle.dump(l2,f1)
# #     pickle.dump(l3,f1)
#
# with open('pickle练习1.pickle', mode='rb') as f1:
#     ret1 = pickle.load(f1)
#     ret2 = pickle.load(f1)
#     ret3 = pickle.load(f1)
#     print(ret1,ret2,ret3)

2.os module

# 目录: 文件夹.
# 工作目录,当前目录,父级目录: day17

import os
# print(os.getcwd())  # D:\s23\day17 绝对路径  ***
# os.chdir(r'D:\s23\day9')
# print(os.getcwd())
# print(os.curdir)
# print(os.pardir)

# 和文件夹相关  ***
import os
# os.makedirs('dirname1/dirname2/dirname3/dirname4')  # 多级目录
# os.removedirs('dirname1/dirname2/dirname3/dirname4') # 截止到有文件的那层
# os.mkdir(r'd:\abc') # 单级目录
# os.rmdir('abc')
# print(os.listdir(r'D:\s23\day15'))

#
# os.remove()  删除一个文件  ***
# os.rename("oldname","newname")  重命名文件/目录  ***
# print(os.stat(r'D:\s23\day17\01 昨日内容回顾.py'))

# path 和路径相关  ***
# print(os.path.abspath('04 os模块.py'))  # D:\s23\day17\01 昨日内容回顾.py
# print(os.path.split(os.path.abspath('01 昨日内容回顾.py')))  # ('D:\\s23\\day17', '01 昨日内容回顾.py')
# print(os.path.dirname(r'D:\s23\day9\01 初始函数.py'))  # 获取父级目录
# print(os.path.dirname(os.path.abspath('01 昨日内容回顾.py')))
# print(__file__)  # 动态获取当前文件的绝对路径
# 获取当前文件的爷爷级的目录
# print(os.path.dirname(os.path.dirname(__file__)))
# print(os.path.basename(r'D:\s23\day9\01 初始函数.py'))  # 获取文件名
# print(os.path.exists(r'D:\s23\day9\02 初始函数.py'))
# 判断是否是绝对路径
# print(os.path.isabs(r'D:\s23\day9\01 初始函数.py'))
# print(os.path.isabs(r'day17/01 昨日内容回顾.py'))
# 判断该路径是否是一个文件路径
# print(os.path.isfile(r'D:\s23\day9\01 初始函数.py'))
# print(os.path.isfile(r'D:\s23\day9'))
# print(os.path.isdir(r'D:\s23\day17\dirname1\dirname2'))
# print(os.path.exists(r'D:\s23\day17\dirname1\dirname2'))
# 判断是否是一个目录(文件夹)
# print(os.path.isdir(r'D:\s23\day17\02 序列化模块.py'))
# D:\s23\day16\评论文章
# path = os.path.join('D:','s23','day20','随便')
# print(path)
# par_dir = os.path.dirname(__file__)
# print(par_dir)  # D:/s23/day17
# path = r'D:\s23\day17\db\lydata'
# path = par_dir + '\db' +'\lydata'
# path = os.path.join(par_dir,'db','lydata')
# with open(path,encoding='utf-8',mode='a') as f1:
#     f1.write('李业在红浪漫消费998元')

# print(os.path.getatime('D:\s23\day17\db\lydata'))
# print(os.path.getmtime('D:\s23\day17\db\lydata'))
# print(os.path.getsize('D:\s23\day17\db\lydata'))

# print(os.stat(r'D:\s23\day17\01 昨日内容回顾.py'))

3.sys module

import sys
# sys.path  ***
# print(sys.version)  # 版本

# for i in range(3):
#     print(i)
# # exit()  # 强制退出
# # quit()
# for i in range(5):
#     print(i)

# print(sys.platform)

4.hashlib module

Encryption module, digest algorithm, hash algorithm, and so on. It is a collection of a bunch of encryption algorithms.

liye | zmdsb

Bai | 123

Stored in clear text, a security risk.

How hashlib encryption?

1. One type of data bytes to encrypt a hexadecimal number returned by the same length hashlib.
2. The process is irreversible.
3. The same type of data bytes by the same absolute numbers obtained by the same encryption method.
4. They are not the same type of data bytes identical digital absolutely the same encryption method obtained.

Hit library: 111111, 123456, 000000,19980123,

{ '202cb962ac59075b964b07152d234b70': 123456}

hashlib uses:

1. Password encryption.
2. File consistency check.

Password encryption:

# 密码加密
# md5
# ret = hashlib.md5()
# ret.update('123'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

# ret = hashlib.md5()
# ret.update('123'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))
#
# ret = hashlib.md5()
# ret.update('223'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

# ret = hashlib.md5()
# ret.update('22fdslkafjdsklfdsjalfaklfjdslkfjdslkfjdsalf;dsajkfldsjf3'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

# 撞库

# ret = hashlib.md5()
# ret.update('123456*@qwe'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

# 加固定盐
# ret = hashlib.md5('xxx教育'.encode('utf-8'))
# ret.update('123456'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

# 加动态的盐
# username = input('输入用户名:').strip()
# password = input('输入密码').strip()
# ret = hashlib.md5(username[::2].encode('utf-8'))
# ret.update(password.encode('utf-8'))
# s = ret.hexdigest()
# print(s)

# sha系列: 安全系数高,耗时高.
# 加盐,加动态盐
# ret = hashlib.sha512()
# ret.update('123456fdklsajflsdfjsdlkafjafkl'.encode('utf-8'))
# s = ret.hexdigest()
# print(s,type(s))

Check the consistency of the file:

 low版
 import hashlib
 ret = hashlib.md5()
 with open('MD5文件校验',mode='rb') as f1:
     content = f1.read()
     ret.update(content)
# print(ret.hexdigest())
#
# ret = hashlib.md5()
# with open('MD5文件校验1',mode='rb') as f1:
#     content = f1.read()
#     ret.update(content)
# print(ret.hexdigest())

# ret = hashlib.md5()
# with open(r'D:\s23\day17\python-3.7.4rc1-embed-win32.zip',mode='rb') as f1:
#     content = f1.read()
#     ret.update(content)
# print(ret.hexdigest())
# d9c18c989c474c7629121c9d59cc429e
# d9c18c989c474c7629121c9d59cc429e


# 分步update
# s1 = '老男孩教育 最好的python 讲师 是 太白'
#
# # 1
# ret = hashlib.md5()
# ret.update(s1.encode('utf-8'))
# print(ret.hexdigest())
#
#
# # 2
# ret = hashlib.md5()
# ret.update('老男孩教育'.encode('utf-8'))
# ret.update(' 最好的python'.encode('utf-8'))
# ret.update(' 讲师 是'.encode('utf-8'))
# ret.update(' 太白'.encode('utf-8'))
# print(ret.hexdigest())  # 90c56d265a363292ec70c7074798c913



高大上版
import hashlib
def md5_file(path):
    ret = hashlib.md5()
    with open(path,mode='rb') as f1:
        while 1:
            content = f1.read(1024)
            if content:
                ret.update(content)
            else:
                return ret.hexdigest()


print(md5_file(r'D:\s23\day17\python-3.7.4rc1-embed-win32.zip'))

5 summary

Built-in modules: serialization module is very, very important!

json very, very important!

dumps loads network transfer, file access (a plurality of data, a single data line)

dump load: a single data file access structure

​ pickle:python.

dumps loads of network transmission

dump load: File Access (a plurality of data, a single data line)

os, sys: *** more practice,

hashlib: password encryption, file get consistency check.