Python正則表達re模組之findall()函數詳解

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]
 
#注意此處findall()的用法，可傳兩個引數;
kk = re.compile(r'd+')
re.findall(kk,"one123")
#[1,2,3]

import re
 
str = 'aabbabaabbaa'

# 一個"."就是匹配除 n (換行符)以外的任意一個字元
print(re.findall(r'a.b',str))#['aab', 'aab']

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

# 貪婪，匹配從.*前面為開始到後面為結束的所有內容
print(re.findall(r'a.*b',str))#['aabbabaabb']

# 非貪婪，遇到開始和結束就進行擷取，因此擷取多次符合的結果，中間沒有字元也會被擷取
print(re.findall(r'a.*?b',str))#['aab', 'ab', 'aab']

# 非貪婪，與上面一樣，只是與上面的相比多了一個括號，只保留括號的內容
print(re.findall(r'a(.*?)b',str))#['a', '', 'a']
 
str = '''aabbab
         aabbaa
         bb'''     #後面多加了2個b

# 沒有把最後一個換行的aab算進來
print(re.findall(r'a.*?b',str))#['aab', 'ab', 'aab']

# re.S不會對n進行中斷
print(re.findall(r'a.*?b',str,re.S))#['aab', 'ab', 'aab', 'aan         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"

#不帶括號
regex=re.compile("((w+)s+w+)")
print(regex.findall(string))
#輸出：[('abcdefg  acbdgef', 'abcdefg'), ('abcdgfe  cadbgfe', 'abcdgfe')]

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

regex2=re.compile("w+s+w+")
print(regex2.findall(string))
#輸出：['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', 'aan         b']