Python正则表达式

1.常用符号

.	匹配任意字符
*	匹配前一个字符0次或无限次
?	匹配前一个字符0次或1次
.*	贪心算法
.*?	非贪心算法
()	括号内的数据作为结果返回

.的用法

import re
a = 'xy123'
b = re.findall('x.',a)
print b#['xy']

*的用法

import re
a = 'xy123'
b = re.findall('x*',a)
print b#['x', '', '', '', '', '']

?的用法

import re
a = 'xy123'
b = re.findall('x.*?',a)
print b#['x']

.*的用法

import re
a = 'xy123xy456xy789xy987xy654xy321'
print re.findall('xy.*xy', a)   #['xy123xy456xy789xy987xy654xy']
print re.findall('xy.*?xy', a)  #['xy123xy', 'xy789xy', 'xy654xy']

()的用法

import re
a = 'xy123xy456xy789xy987xy654xy321'
print re.findall('xy.*?xy', a)#['xy123xy', 'xy789xy', 'xy654xy']
print re.findall('xy(.*?)xy', a)#['123', '789', '654']

re.S的用法

import re
a = '''xy123'
    xy456xy789xy987xy654xy321'''
print re.findall('xy.*?xy', a)#['xy456xy', 'xy987xy']
print re.findall('xy(.*?)xy', a)#['456', '987']

print re.findall('xy.*?xy', a, re.S)#["xy123'
    xy", 'xy789xy', 'xy654xy']
print re.findall('xy(.*?)xy', a, re.S)#["123'
    ", '789', '654']

search用法

import re
a = 'xy123xy456xy789xy987'
print re.search('xy(.*?)xy456xy(.*?)xy', a).group()#xy123xy456xy789xy
print re.search('xy(.*?)xy456xy(.*?)xy', a).group(1)#123
print re.search('xy(.*?)xy456xy(.*?)xy', a).group(2)#789

print re.findall('xy(.*?)xy456xy(.*?)xy', a)[0][0]#123

sub用法

import re
a = 'xy123xy'
print re.sub('xy(.*?)xy','XY%dXY'%321, a)#XY321XY

匹配数字

import re
a = 'xy123xy'
print re.findall('(d+)', a)#['123']