re模块

import re

ret = re.findall('\d+', '15548jhbsbcvjsbcv1548')
print(ret)
ret = re.search('\d+', '15548jhbsbcvjsbcv1548')
print(ret)  #变量
print(ret.group())


"""
split
sub
subn
match
compile
finditer
"""
ret = re.split('\d+','aaaa222bbbb')
print(ret)
ret = re.split('(\d+)','aaaa222bbbb')
print(ret)

#sub 替换
ret = re.sub('\d+', 'H', 'aaaa222bbbb',1)
print(ret)


#subn 返回元组，说明替换次数
ret = re.subn('\d+', 'H', 'aaaa222bbbb555')
print(ret)

#match  要从头开始找，不然返回None，和seach前面加^一样
#match  一般用来规定这个字符号必须是什么样的，seach用来寻找这个字符串中是不是含有满足条件的子内容
ret = re.match('\d+', 'aaaa222bbbb555')
print(ret)


#compile    节省代码时间工具
    #假如同一个正则表达式要被使用多次
    #节省了多次解析同一个正则表达式的时间
ret = re.compile('\d+')
print(ret.search('aaa25151'))
print(ret.findall('aaa155151'))


print("*************************")
#finditer   节省空间
ret = re.finditer('\d+','fwdwfv15155')
for i in ret:
    print(i.group())


print("*"*10)
#先compile  再finditer
ret = re.compile('\d+')
res = ret.finditer('fdcafdag5151fewf51511')
for r in res:
    print(r.group())



#分组命名
import re
ret = re.search('\d(\d)\d(\w+)(?P<name1>\d)(\w)\d(\d)\d(\w+)(\d)(?P<name2>\w)\d(\d)\d(\w+)(\d)(\w)',
                '123abc45678sad_415ada12515fwefwe455wee415egwe')
print(ret.group('name1'))
print(ret.group('name2'))

#分组命名的引用
exp = '<abc>ahgcgkh<abh>,kl,k</abc>'
ret = re.search('<(?P<tag>\w+)>.*?</(?P=tag)>',exp)
print(ret)