Python正则表达式分组

>>> s='<div><a href="https://support.google.com/chrome/?p=ui_hotword_search" rel="external nofollow"  target="_blank">更多</a><p>dfsl</p></div>'
>>> print re.search(r'<a.*>(.*)</a>',s).group(1)
更多

>>> print re.match(r'.*<a.*>(.*)</a>',s).group(1)
更多

>>> s = "ip='230.192.168.78',version='1.0.0'"
>>> re.search(r"ip='(?P<ip>\d+\.\d+\.\d+\.\d+).*", s)
>>> res.group('ip')#通过命名分组引用分组
'230.192.168.78'

#通过命名分组进行后向引用
>>> re.search(r'(?P<name>go)\s+(?P=name)\s+(?P=name)', 'go go go').group('name')
'go'
#通过默认分组编号进行后向引用
>>> re.search(r'(go)\s+\1\s+\1', 'go go go').group()
'go go go'

>>> s = 'abc.xyz'
>>> re.sub(r'(.*)\.(.*)', r'\2.\1', s)
'xyz.abc'

(?=pattern)

(?<=pattern)

>>> s1='''char *a="hello world"; char b='c'; /* this is comment */ int c=1; /* t
his is multiline comment */'''
>>> re.findall( r'(?<=/\*).+?(?=\*/)' , s1 ,re.M|re.S)
[' this is comment ', ' this is multiline comment ']

(?!pattern)

(?<!pattern)

#提取不是.txt结尾的文件
>>> f1 = 'aaa.txt'
>>> re.findall(r'.*\..*$(?<!txt$)',f1)
[]

#提取不以数字开头的文件
>>> re.findall(r'^(?!\d+).*','1txt.txt')
[]

#提取不以数字开头不以py结尾的文件
>>> re.findall(r'^(?!\d+).+?\..*$(?<!py$)','test.py')
[]

>>> re.findall(r'^(?!\d+).+?\..*$(?<!py$)','test.txt')
['test.txt']