Python -- 正则表达式(1)

import re    #import re模块是为了使用正则表达式，正则表达式本身是一种专门匹配字符串的语言

#正则表达式的方法：
#findall(): 所有结果都返回到一个列表里
#search():返回匹配到的第一个对象(object)，对象可以调用group()返回结果
#match():只在字符串开始匹配
#......

ret = re.findall('aa','aaaaa')
print(ret)

#正则表达式元字符 .  ^  $  *  +  ?  {}  []  |  ()  \
#. 代指除换行符外的任意1个字符
ret1 = re.findall('y..','Thank you very much')
print(ret1)

#^ 指定匹配一定要从字符串头开始，不能取中间
ret2 = re.findall('^y..','Thank you very much')
print(ret2)

#$ 指定匹配一定要从字符串末开始，不能取中间
ret3 = re.findall('.ch$','Thank you very much')
print(ret3)

#.* 指任意0或多个字符
ret4 = re.findall('ab.*','aaaabhghabfb')
print(ret4)

#+ 指任意1或多个字符
ret4 = re.findall('a+b','aaabhghabfb')
print(ret4)

#? 0或1个?前的字符
ret5 = re.findall('a?b','aaabhghabfb')
print(ret5)

#{} 字符重复次数，可以是个范围
ret6 = re.findall('a{2}b','aaabhghabfb')
print(ret6)

ret7 = re.findall('a{1,2}b','aaabhghabfb')
print(ret7)

#[] []中的字符进行多选一,[]中的特殊字符，除\ ^ -这个三个外，其他会被取消特殊功能，当做普通字符看待
ret8 = re.findall('a[a,b,c,d]','aaabhghabfb')
print(ret8)

ret9 = re.findall('a[a-d]','aaabhghabfb')
print(ret9)

#^放在[]里，表示取反
ret10 = re.findall('[^ab]','aaabhghabfb')
print(ret10)

#\后跟元字符去除特殊功能
#\后跟部分普通符增加特殊功能
ret10 = re.findall('[^ab]','aaabhghabfb')
print(ret10)

#\b 匹配一个特殊字符边界
ret11 = re.findall(r'\bI','Hello, Iam a LIST.')
print(ret11)

# 匹配\的方式
ret12 = re.findall(r'\\','ab\cd\e.')
print(ret12)

ret13 = re.findall('\\\\','ab\cd\e.')
print(ret13)

ret14 = re.search('(?P<id>\d{3})w(?P<name>\w{3})','weeew34ttt123wooo')
print(ret14.group())
print(ret14.group('id'))
print(ret14.group('name'))

# | 或

print(re.search('(as)|3','as3').group())   #这里as用()括起来看作一个整体，as3既有as也有3，那个先匹配到先打印哪个
print(re.search('(as)|3','3as').group())

ret15 = re.match('asd','asdqwewqewqerg')
print(ret15)

ret16 = re.match('asd','fasdqwewqewqerg')
print(ret16)

ret17 = re.split('[dw]','fasdqwewqewqerg')    #用d分割完后，用w分
print(ret17)

ret18 = re.sub('a..x','sb','hfalexewqewqe')    #用于替换
print(ret18)

ret19 = re.compile('\.com')
print(ret19.findall('fasdsa.comewrew'))

ret20 = re.subn('\d','sb','hfale4xe6wqewqe')    #用于多次替换，并返回替换次数
print(ret20)

ret21 = re.finditer('\d','dsad2fd324a')
print(ret21)
print(next(ret21).group())

输出：

['aa', 'aa']
['you', 'y m']
[]
['uch']
['abhghabfb']
['aaab', 'ab']
['ab', 'ab', 'b']
['aab']
['aab', 'ab']
['aa', 'ab', 'ab']
['aa', 'ab', 'ab']
['h', 'g', 'h', 'f']
['h', 'g', 'h', 'f']
['I']
['\\', '\\']
['\\', '\\']
123wooo
123
ooo
as
3
<re.Match object; span=(0, 3), match='asd'>
None
['fas', 'q', 'e', 'qe', 'qerg']
hfsbewqewqe
['.com']
('hfalesbxesbwqewqe', 2)
<callable_iterator object at 0x000002887BD469E8>
2