Python实战之正则表达式RE/re学习笔记及简单练习

# .,w,s,d,,^,$
# *,+,?,{n},{n,},{n,m}

# re模块用于对python的正则表达式的操作。
#
# 字符:
#
#   . 匹配除换行符以外的任意字符
#   w 匹配字母或数字或下划线或汉字
#   s 匹配任意的空白符
#   d 匹配数字
#    匹配单词的开始或结束
#   ^ 匹配字符串的开始
#   $ 匹配字符串的结束
#
# 次数:
#
#   * 重复零次或更多次
#   + 重复一次或更多次
#   ? 重复零次或一次
#   {n} 重复n次
#   {n,} 重复n次或更多次
#   {n,m} 重复n到m次


import re
# match(pattern, string, flags=0)
# 从起始位置开始根据模型去字符串中匹配指定内容,匹配单个
# 正则表达式
# 要匹配的字符串
# 标志位,用于控制正则表达式的匹配方式
# strings = re.match('d+','123df45')
# print(strings)
# print(strings.group())
# print(strings.groups())
# <_sre.SRE_Match object; span=(0, 3), match='123'>
# 123
# ()



#根据模型去字符串中匹配指定内容,匹配单个
# obj = re.search('d+','u9f34k')
# print(obj)
# print(obj.group())
# <_sre.SRE_Match object; span=(1, 2), match='9'>
# 9




# group和groups
# a = '123abc456'
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).group())
# # 123abc456
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).groups())
# # ('123', 'abc', '456')
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(0))
# # 123abc456
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(1))
# # 123
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(2))
# #abc
# print(re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(3))
# #456


# findall(pattern, string, flags=0)
# 上述两中方式均用于匹配单值,即:只能匹配字符串中的一个,如果想要匹配到字符串中所有符合条件的元素,则需要使用 findall。
# a = '123abc567'
# obj = re.findall('d+',a)
# print(obj)
# print()
# ['123', '567']


# sub(pattern, repl, string, count=0, flags=0)
# 用于替换匹配的字符串

# content = '123abc456'
# new_content = re.sub('d+','sb',content)
# # sbabcsb
# print(new_content)
# new = re.sub('d+','xxoo',content,3)
# print(new)
# xxooabcxxoo

content = "'1 - 2 * ((60-30+1*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2) )'"
# new_content = re.split('*',content)
# print(new_content)
# # ["'1 - 2 ", ' ((60-30+1', '(9-2', '5/3+7/3', '99/4', '2998+10', '568/14))-(-4', '3)/(16-3', "2) )'"]
# new_content2 = re.split('*',content,1)
# print(new_content2)
# # ["'1 - 2 ", " ((60-30+1*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2) )'"]
#
# new_content3 = re.split('*',content,3)
# print(new_content3)
# # ["'1 - 2 ", ' ((60-30+1', '(9-2', "5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2) )'"]



# new_content = re.split('[+-*/]+',content)
# print(new_content)
# ["'1 ", ' 2 ', ' ((60', '30', '1', '(9', '2', '5', '3', '7', '3', '99', '4', '2998', '10', '568', '14))', '(', '4', '3)', '(16', '3', "2) )'"]


# inpp = '1-2*((60-30 +(-40-5)*(9-2*5/3 + 7 /3*99/4*2998 +10 * 568/14 )) - (-4*3)/ (16-3*2))'
# inpp = re.sub('s*','',inpp)
# print(inpp)
# # 1-2*((60-30+(-40-5)*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2))
#
# new_content = re.split('(([+-*/]?d+[+-*/]?d+){1})',inpp, 1)
# print(new_content)
原文地址:https://www.cnblogs.com/william126/p/7123529.html