Python3 正则表达式

 #!/usr/bin/python
 
import re
print(re.match('www', 'www.dida100.com').span()) # 在起始位置匹配
print(re.match('com', 'www.dida100.com')) # 不在起始位置匹配

 #!/usr/bin/python3
import re
 
line = "Cats are smarter than dogs" # .* 表示任意匹配除换行符（\n、\r）之外的任何单个或多个字符 # (.*?) 表示"非贪婪"模式，只保存第一个匹配到的子串
matchObj = re.match( r'(.*) are (.*?) .*', line, re.M|re.I)
 
if matchObj:
   print ("matchObj.group() : ", matchObj.group())
   print ("matchObj.group(1) : ", matchObj.group(1))
   print ("matchObj.group(2) : ", matchObj.group(2))
else:
   print ("No match!!")

 #!/usr/bin/python3
 
import re
 
print(re.search('www', 'www.dida100.com').span()) # 在起始位置匹配
print(re.search('com', 'www.dida100.com').span()) # 不在起始位置匹配

 #!/usr/bin/python3
 
import re
 
line = "Cats are smarter than dogs"
 
searchObj = re.search( r'(.*) are (.*?) .*', line, re.M|re.I)
 
if searchObj:
   print ("searchObj.group() : ", searchObj.group())
   print ("searchObj.group(1) : ", searchObj.group(1))
   print ("searchObj.group(2) : ", searchObj.group(2))
else:
   print ("Nothing found!!")

 #!/usr/bin/python3
 
import re
 
line = "Cats are smarter than dogs"
 
matchObj = re.match( r'dogs', line, re.M|re.I)
if matchObj:
   print ("match --> matchObj.group() : ", matchObj.group())
else:
   print ("No match!!")
 
matchObj = re.search( r'dogs', line, re.M|re.I)
if matchObj:
   print ("search --> matchObj.group() : ", matchObj.group())
else:
   print ("No match!!")

 #!/usr/bin/python3
import re
 
phone = "2004-959-559 # 这是一个电话号码" # 删除注释
num = re.sub(r'#.*$', "", phone)
print ("电话号码 : ", num) # 移除非数字的内容
num = re.sub(r'\D', "", phone)
print ("电话号码 : ", num)

 #!/usr/bin/python
 
import re # 将匹配的数字乘以 2
def double(matched):
    value = int(matched.group('value'))
    return str(value * 2)
 
s = 'A23G4HFD567'
print(re.sub('(?P<value>\d+)', double, s))

>>>import re
pattern = re.compile(r'\d+') # 用于匹配至少一个数字
m = pattern.match('one12twothree34four') # 查找头部，没有匹配
print( m )
None
m = pattern.match('one12twothree34four', 2, 10) # 从'e'的位置开始匹配，没有匹配
print( m )
None
m = pattern.match('one12twothree34four', 3, 10) # 从'1'的位置开始匹配，正好匹配
print( m ) # 返回一个 Match 对象
<_sre.SRE_Match object at 0x10a42aac0>
m.group(0) # 可省略 0
'12'
m.start(0) # 可省略 0
3
m.end(0) # 可省略 0
5
m.span(0) # 可省略 0
(3, 5)

>>>import re
pattern = re.compile(r'([a-z]+) ([a-z]+)', re.I) # re.I 表示忽略大小写
m = pattern.match('Hello World Wide Web')
print( m ) # 匹配成功，返回一个 Match 对象
<_sre.SRE_Match object at 0x10bea83e8>
m.group(0) # 返回匹配成功的整个子串
'Hello World'
m.span(0) # 返回匹配成功的整个子串的索引
(0, 11)
m.group(1) # 返回第一个分组匹配成功的子串
'Hello'
m.span(1) # 返回第一个分组匹配成功的子串的索引
(0, 5)
m.group(2) # 返回第二个分组匹配成功的子串
'World'
m.span(2) # 返回第二个分组匹配成功的子串索引
(6, 11)
m.groups() # 等价于 (m.group(1), m.group(2), ...)
('Hello', 'World')
m.group(3) # 不存在第三个分组
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
IndexError: no such group

import re
 
result1 = re.findall(r'\d+','dida100 123 google 456')
 
pattern = re.compile(r'\d+') # 查找数字
result2 = pattern.findall('dida100 123 google 456')
result3 = pattern.findall('run88oob123google456', 0, 10)
 
print(result1)
print(result2)
print(result3)

import re

result = re.findall(r'(\w+)=(\d+)', 'set width=20 and height=10')
print(result)

import re
 
it = re.finditer(r"\d+","12a32bc43jf3") 
for match in it: 
    print (match.group() )

>>>import re
re.split('\W+', 'dida100, dida100, dida100.')
['dida100', 'dida100', 'dida100', '']
re.split('(\W+)', ' dida100, dida100, dida100.') 
['', ' ', 'dida100', ', ', 'dida100', ', ', 'dida100', '.', '']
re.split('\W+', ' dida100, dida100, dida100.', 1) 
['', 'dida100, dida100, dida100.']
 
re.split('a*', 'hello world') # 对于一个找不到匹配的字符串而言，split 不会对其作出分割
['hello world']