Python就业班——正则表达式与综合实战

#!/usr/bin/env python3
# coding=utf-8
# Version:python3.6.1
# Project:practice
# File:Python就业班——正则表达式与综合实战.py
# Data:2020/8/1 19:17
# Author:LGSP_Harold

# （默认）贪婪匹配：在整个表达式匹配成功的前提下，尽可能多的匹配
# 非贪婪匹配：在整个表达式匹配成功的前提下，以最少的匹配字符


# re模块

# compile(pattern, flags = 0)
# 使用任何可选的标记来编译正则表达式的模式，然后返回一个正则表达式对象

# match(pattern, string, flags = 0)
# 尝试使用带有可选的标记的正则表达式的模式来匹配字符串。如果匹配成功，就返回匹配对象；如果失败，就返回None

import re

# # 将正则表达式编译
# # pattern = re.compile(r'hello')
# pattern = re.compile(r'hello', re.I)
#
# print(dir(pattern))
#
# # 通过match进行匹配
# # rest = pattern.match('hello, world!')
# rest = pattern.match('Hello, world!')
# print(rest)
# print(dir(rest))
# print('string:', rest.string)


# # findall(pattern, string [, flags])
# # 查找字符串中所有（非重复）出现的正则表达式模式，并返回一个匹配列表
#
# # 找出以下字符串中的数字
# # content = 'one1two22three3four4five5six698'
# content = 'one1two22Three3four4five5six698'
# # pattern = re.compile(r'\d+')
# # pattern = re.compile(r'[a-z]+')
# pattern = re.compile(r'[a-z]+', re.I)
# rest = pattern.findall(content)
# print(rest)


# # search(pattern, string [, flags])
# # 所有可选标记搜索字符串中第一次出现的正则表达式模式。如果匹配成功，则返回匹配对象；如果失败，则返回None
# content = 'hello world!'
# p = re.compile(r'world')
# rest = p.search(content)
# print(rest)


# # group()与groups()的使用
# # group(num)返回整个匹配对象或编号为num的特点子组
# # groups()返回一个包含所有匹配子组的元组（如果没有成功匹配，返回一个空元组）
#
# def test_group():
#     content = 'hello world'
#     p = re.compile(r'world')
#     rest = p.search(content)
#     print(rest)
#     if rest:
#         print(rest.group())
#         print(rest.groups())
#
#
# def test_id_card():
#     # p = re.compile(r'^(\d{6})(\d{4})(\d{2})(\d{2})(\d{3})([0-9]|X)$')
#     p = re.compile(r'^(\d{6})(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})(\d{3})([0-9]|X)$')
#     id1 = '11010119900307387X'
#     id2 = '110101199003070652'
#     rest1 = p.search(id2)
#     # print(rest1.group(1))
#     # print(rest1.group(2))
#     # print(rest1.group(3))
#     # print(rest1.group(4))
#     # print(rest1.groups())
#     print(rest1.groupdict())


# # split(pattern, string, max=0)
# # 根据正则表达式的模式分隔符，split函数将字符串分割为列表，然后返回成功匹配的列表，分割最多操作max次（默认分割所有匹配成功的位置）
# content = 'one1two22three3four4five5six698'
# p = re.compile(r'\d+')
# rest = p.split(content)
# # rest = p.split(content, 2)
# print(rest)


# # sub(pattern, repl, string, max=0)
# # 使用repl替换string中每一个匹配的子串后返回替换后的字符串，最多操作max次（默认替换所有）
# content = 'one1two22three3four4five5six698'
# p = re.compile(r'\d+')
# rest = p.sub('@', content)
# print(rest)
#
# # 更换位置
# content2 = 'hello world'
# p2 = re.compile(r'(\w+) (\w+)')
# rest_pos = p2.sub(r'\2 \1', content2)
# print(rest_pos)
#
#
# # 替换并改变内容
# def f(m):
#     return m.group(2).upper() + ' ' + m.group(1)
#
#
# rest_change = p2.sub(f, content2)
# print(rest_change)
#
# # 使用匿名函数进行替换
# rest_lamb = p2.sub(lambda m: m.group(2).upper() + ' ' + m.group(1), content2)
# print(rest_lamb)


if __name__ == '__main__':
    # test_group()
    # test_id_card()
    pass