Python正则表达re模块之findall()函数详解

def findall(pattern, string, flags=0):
    """Return a list of all non-overlapping matches in the string.

    If one or more capturing groups are present in the pattern, return
    a list of groups; this will be a list of tuples if the pattern
    has more than one group.

    Empty matches are included in the result."""

    return _compile(pattern, flags).findall(string)

import re
kk = re.compile(r'\d+')
kk.findall('one1two2three3four4')
#[1,2,3,4]
 
#注意此处findall()的用法，可传两个参数;
kk = re.compile(r'\d+')
re.findall(kk,"one123")
#[1,2,3]

import re
 
str = 'aabbabaabbaa'

# 一个"."就是匹配除 \n (换行符)以外的任意一个字符
print(re.findall(r'a.b',str))#['aab', 'aab']

# *前面的字符出现0次或以上
print(re.findall(r'a*b',str))#['aab', 'b', 'ab', 'aab', 'b']

# 贪婪，匹配从.*前面为开始到后面为结束的所有内容
print(re.findall(r'a.*b',str))#['aabbabaabb']

# 非贪婪，遇到开始和结束就进行截取，因此截取多次符合的结果，中间没有字符也会被截取
print(re.findall(r'a.*?b',str))#['aab', 'ab', 'aab']

# 非贪婪，与上面一样，只是与上面的相比多了一个括号，只保留括号的内容
print(re.findall(r'a(.*?)b',str))#['a', '', 'a']
 
str = '''aabbab
         aabbaa
         bb'''     #后面多加了2个b

# 没有把最后一个换行的aab算进来
print(re.findall(r'a.*?b',str))#['aab', 'ab', 'aab']

# re.S不会对\n进行中断
print(re.findall(r'a.*?b',str,re.S))#['aab', 'ab', 'aab', 'aa\n         b']

str = 'aabbabaabbaa'

print(re.findall(r'a.b',str))
#['aab', 'aab']

print(re.findall(r'a*b',str))
#['aab', 'b', 'ab', 'aab', 'b']

print(re.findall(r'a.*b',str))
#['aabbabaabb']

print(re.findall(r'a.*?b',str))
#['aab', 'ab', 'aab']

print(re.findall(r'a(.*?)b',str))
#['a', '', 'a']

import re

string="abcdefg  acbdgef  abcdgfe  cadbgfe"

#不带括号
regex=re.compile("((\w+)\s+\w+)")
print(regex.findall(string))
#输出：[('abcdefg  acbdgef', 'abcdefg'), ('abcdgfe  cadbgfe', 'abcdgfe')]

regex1=re.compile("(\w+)\s+\w+")
print(regex1.findall(string))
#输出：['abcdefg', 'abcdgfe']

regex2=re.compile("\w+\s+\w+")
print(regex2.findall(string))
#输出：['abcdefg  acbdgef', 'abcdgfe  cadbgfe']

str = '''aabbab
         aabbaa
         bb'''

print(re.findall(r'a.*?b',str))
#['aab', 'ab', 'aab']

print(re.findall(r'a.*?b',str,re.S))
#['aab', 'ab', 'aab', 'aa\n         b']