一些regular的tips:
1 非贪婪flag
[ ' 2 ' ]
>>> re . findall ( r " a( \d +) " , " a23b " )
[ ' 23 ' ]
注意比较这种情况:
[ ' 23 ' ]
>>> re . findall ( r " a( \d +?)b " , " a23b " ) #如果前后均有限定条件,则非匹配模式失效
[ ' 23 ' ]
2 如果你要多行匹配,那么加上re.S和re.M标志
re.S:.将会匹配换行符,默认.逗号不会匹配换行符
[]
>>> re . findall ( r " a( \d +)b.+a( \d +)b " , " a23b \n a34b " , re . S )
[( ' 23 ' , ' 34 ' )]
>>>
re.M:^$标志将会匹配每一行,默认^只会匹配符合正则的第一行;默认$只会匹配符合正则的末行
[ ' 23 ' ]
>>> re . findall ( r " ^a( \d +)b " , " a23b \n a34b " , re . M )
[ ' 23 ' , ' 34 ' ]
但是,如果没有^标志,
[ ' 23 ' , ' 43 ' ]
可见,是无需re.M
import re
n='''12 drummers drumming,
11 pipers piping, 10 lords a-leaping'''
p=re.compile('^\d+')
p_multi=re.compile('^\d+',re.MULTILINE) #设置 MULTILINE 标志
print re.findall(p,n) #['12']
print re.findall(p_multi,n) # ['12', '11']
============================
import re
a = 'a23b'
print re.findall('a(\d+?)',a) #['2']
print re.findall('a(\d+)',a) #['23']
print re.findall(r'a(\d+)b',a) #['23']
print re.findall(r'a(\d+?)b',a) # ['23']
============================
b='a23b\na34b'
''' . 匹配非换行符的任意一个字符'''
print re.findall(r'a(\d+)b.+a(\d+)b',b) #[]
print re.findall(r'a(\d+)b',b,re.M) # ['23', '34']
print re.findall(r'^a(\d+)b',b,re.M) # ['23', '34']
print re.findall(r'a(\d+)b',b) #['23','34'] 可以匹配多行
print re.findall(r'^a(\d+)b',b) # ['23'] 默认^只会匹配符合正则的第一行
print re.findall(r'a(\d+)b$',b) # ['34'] 默认$只会匹配符合正则的末行
print re.findall(r'a(\d+)b',b,re.M) #['23', '34']
print re.findall(r'a(\d+)b.?',b,re.M) # ['23', '34'] 表达式中的'.'匹配除换行符以外的字符,'?'匹配前一个字符0次或1次
print re.findall(r"a(\d+)b", "a23b\na34b") # ['23', '34']
============================
注:Python3.4中,print为函数,需要加括号