# 单个字符匹配

import re

# \w 与 \W   #字母数字下划线，  非

# print(re.findall('\w', '太白jx 12*() _'))  # ['太', '白', 'j', 'x', '1', '2', '_']

# print(re.findall('\W', '太白jx 12*() _'))  # [' ', '*', '(', ')', ' ']

# \s 与\S      space   非space

# print(re.findall('\s','太白barry*(_ \t \n'))  # [' ', '\t', ' ', '\n']

# print(re.findall('\S','太白barry*(_ \t \n'))  # ['太', '白', 'b', 'a', 'r', 'r', 'y', '*', '(', '_']

# \d 与 \D     数字  非数字

# print(re.findall('\d','1234567890 alex *（_'))  # ['1', '2', '3', '4', '5', '6', '7', '8', '9', '0']

# print(re.findall('\D','1234567890 alex *（_'))  # [' ', 'a', 'l', 'e', 'x', ' ', '*', '（', '_']

# \A 与 ^   行首

# print(re.findall('\Ahel','hello 太白金星 -_- 666'))  # ['hel']

# print(re.findall('^hel','hello 太白金星 -_- 666'))  # ['hel']

# \Z 与 $  行尾

# print(re.findall('666\Z','hello 太白金星 *-_-* \n666'))  # ['666']

# print(re.findall('666\Z','hello 太白金星 *-_-* \n666'))  # []

# print(re.findall('666$','hello 太白金星 *-_-* \n666'))  # ['666']

# \n 与 \t

# print(re.findall('\n','hello \n 太白金星 \t*-_-*\t \n666'))  # ['\n', '\n']

# print(re.findall('\t','hello \n 太白金星 \t*-_-*\t \n666'))  # ['\t', '\t']

.匹配任意字符

print(re.findall('a.b','babb'))

print(re.findall('a.b','abb a%b a1b aab a7b a+b a b a\nb'))

print(re.findall('a.b','abb a%b a1b aab a7b a+b a b a\nb',re.DOTALL))

print(re.findall('a.bb','abb abb aaab'))

? 匹配0个或者1个由左边字符定义的片段

print(re.findall('a?b','abbzab abb aab'))  # [ab b ab ab b ab]

print(re.findall('a?b','ab'))  # [ab]

* 匹配0个或者多个左边字符表达式

print(re.findall('a*b','b ab aaaaaab abbbbbbb'))

['b', 'ab', 'aaaaaab', 'ab', 'b', 'b', 'b', 'b', 'b', 'b']

+ 匹配1个或者多个左边字符表达式

print(re.findall('a+b','b ab aaaaaab abb'))  # ['ab', 'aaaaaab', 'ab']

{m,n}  匹配m个至n个左边字符表达式

print(re.findall('a{1,3}b','aaab ab aab abbb aaz aabb'))

.* 贪婪匹配 从头到尾.

print(re.findall('a.*b','aab ab aaaaab a!!!@#$bz')) # [aab aaaaab a!!!@#$b]

# .*?  非贪婪匹配 从头到尾.

print(re.findall('a.*?b','aab ab aaaaab a!!!@#$bz')) #

[]

print(re.findall('a[abc]b','aab abb acb'))

print(re.findall('a[0-9]b','a1b a2b a3b  acb ayb'))

print(re.findall('a[a-z]b','a1b a2b a3b  acb ayb adb'))

print(re.findall('a[A-Z]b','a1b a2b a3b  aAb aDb aYb'))

print(re.findall('a[a-zA-Z]b','aab aAb aWb aqb a1b'))  # 大小写字母

print(re.findall('a[A-z]b','aab aAb aWb aqb a1b'))

print(re.findall('a[0-9][0-9]b','a1b a2b a29b a56b a456b'))

print(re.findall('a[-+*/]b','a+b a-b a*b a/b a6b')) 单纯的想表示- 一定要放在最前面

print(re.findall('.*?_sb','wusir_sb alex_sb 日天_sb'))    #['wusir_sb', ' alex_sb', ' 日天_sb']

print(re.findall('(.*?)_sb','wusir_sb alex_sb 日天_sb'))  # ['wusir', ' alex', ' 日天']

print(re.findall('company|companies','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'))

print(re.search('alex','re alex alex 太白'))

# print(re.search('alex','re aaaelx 太白'))  # 找不到，返回None

ret = re.search('alex','re alex alex 太白')  # <_sre.SRE_Match object; span=(3, 7), match='alex'>

print(ret.group())   # alex

print(re.match('barry','barry fdlfjsadfkl ').group())   # 同样用group()取值

print(re.match('barry','qbarry fdlfjsadfkl '))

s1 = 'wusir;太白,alex|日天!小虎'

print(re.split('[;,|!]',s1))

print(re.sub('barry', '太白金星', 'barry是最好的讲师，barry就是一个普通老师，请不要将barry当男神对待。',2)) # 2代表替换两个

#   太白金星是最好的讲师，太白金星就是一个普通老师，请不要将barry当男神对待

#  制定一个统一的规则

obj = re.compile('\d{2}')  # 制定一个统一的匹配规则

print(obj.findall('fdsafsda4312fdsdf324'))

print(obj.findall('123fksldjf3432fdsjlkf453')) # ['12', '34', '32', '45']

ret = re.finditer('\d', 'ds3sy4784a')

print(ret)

print(next(ret).group())   #

print(next(ret).group())    #

print([i.group() for i in ret]) # ['7', '8', '4']

s1 = '深圳电话：0755-546123546 深圳地址：广东..'

print(re.search('\d+-\d+',s1).group())

# 命名分组

# 分组基础上定规则 ?P<组名>

ret = re.search('(?P<quhao>\d+)-(?P<num>\d+)',s1)

print(ret.group('quhao'))

print(ret.group('num'))