import re
# \w与\W
print(re.findall('\w', 'hello egon 123')) # ['h', 'e', 'l', 'l', 'o', 'e', 'g', 'o', 'n', '1', '2', '3']
print(re.findall('\W', 'hello egon 123')) # [' ', ' ']
# \s与\S
print(re.findall('\s', 'hello egon 123')) # [' ', ' ', ' ', ' ']
print(re.findall('\S', 'hello egon 123')) # ['h', 'e', 'l', 'l', 'o', 'e', 'g', 'o', 'n', '1', '2', '3']
# \n \t都是空,都可以被\s匹配
print(re.findall('\s', 'hello \n egon \t 123')) # [' ', '\n', ' ', ' ', '\t', ' ']
# \n与\t
print(re.findall(r'\n', 'hello egon \n123')) # ['\n']
print(re.findall(r'\t', 'hello egon\t123')) # ['\n']
# \d与\D
print(re.findall('\d', 'hello egon 123')) # ['1', '2', '3']
print(re.findall('\D', 'hello egon 123')) # ['h', 'e', 'l', 'l', 'o', ' ', 'e', 'g', 'o', 'n', ' ']
# \A与\Z
print(re.findall('\Ahe', 'hello egon 123')) # ['he'],\A==>^
print(re.findall('123\Z', 'hello egon 123')) # ['he'],\Z==>$
# ^与$
print(re.findall('^h', 'hello egon 123')) # ['h']
print(re.findall('3$', 'hello egon 123')) # ['3']
# .
print(re.findall('a.b', 'a1b')) # ['a1b']
print(re.findall('a.b', 'a1b a*b a b aaab')) # ['a1b', 'a*b', 'a b', 'aab']
print(re.findall('a.b', 'a\nb')) # []
print(re.findall('a.b', 'a\nb', re.S)) # ['a\nb']
print(re.findall('a.b', 'a\nb', re.DOTALL)) # ['a\nb']同上一条意思一样
# 重复匹配：| * | ? | .* | .*? | + | {n,m} |
# *
print(re.findall('ab*', 'bbbbbbb')) # []
print(re.findall('ab*', 'a')) # ['a']
print(re.findall('ab*', 'abbbb')) # ['abbbb']
# ?
print(re.findall('ab?', 'a')) # ['a']
print(re.findall('ab?', 'abbb')) # ['ab']
# 匹配所有包含小数在内的数字
print(re.findall('\d+\.?\d*', "asdfasdf123as1.13dfa12adsf1asdf3")) # ['123', '1.13', '12', '1', '3']
# .*默认为贪婪匹配
print(re.findall('a.*b', 'a1b22222222b')) # ['a1b22222222b']
# .*?为非贪婪匹配：推荐使用
print(re.findall('a.*?b', 'a1b22222222b')) # ['a1b']
# +
print(re.findall('ab+', 'a')) # []
print(re.findall('ab+', 'abbb')) # ['abbb']
# {n,m}
print(re.findall('ab{2}', 'abbb')) # ['abb']
print(re.findall('ab{2,4}', 'abbb')) # ['abb']
print(re.findall('ab{1,}', 'abbb')) # 'ab{1,}' ===> 'ab+'
print(re.findall('ab{0,}', 'abbb')) # 'ab{0,}' ===> 'ab*'
#字符集[]
ret=re.findall('a[bc]d','acd')
print(ret)#['acd']
ret=re.findall('[a-z]','acd')
print(ret)#['a', 'c', 'd']
ret=re.findall('[.*+]','a.cd+')
print(ret)#['.', '+']
#在字符集里有功能的符号: - ^ \
ret=re.findall('[1-9]','45dha3')
print(ret)#['4', '5', '3']
ret=re.findall('[^ab]','45bdha3')
print(ret)#['4', '5', 'd', 'h', '3']
ret=re.findall('[\d]','45bdha3')
print(ret)#['4', '5', '3']
# \# print(re.findall('a\\c','a\c')) #对于正则来说a\\c确实可以匹配到a\c,但是在python解释器读取a\\c时，会发生转义，然后交给re去执行，所以抛出异常
print(re.findall(r'a\\c', 'a\c')) # r代表告诉解释器使用rawstring，即原生字符串，把我们正则内的所有符号都当普通字符处理，不要转义
print(re.findall('a\\\\c', 'a\c')) # 同上面的意思一样，和上面的结果一样都是['a\\c']
# ():分组
print(re.findall('ab+', 'ababab123')) # ['ab', 'ab', 'ab']
print(re.findall('(ab)+123', 'ababab123')) # ['ab']，匹配到末尾的ab123中的ab
print(re.findall('(?:ab)+12 