Python 正则表达式

import re
print(re.match(‘www‘, ‘www.runoob.com‘).span())  # 在起始位置匹配
print(re.match(‘com‘, ‘www.runoob.com‘))         # 不在起始位置匹配

(0, 3)
None

line = "Cats are smarter than dogs"
 
matchObj = re.match( r‘(.*) are (.*?) .*‘, line)
 
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!!")

matchObj.group() :  Cats are smarter than dogs
matchObj.group(1) :  Cats
matchObj.group(2) :  smarter

line = "Cats are smarter than dogs";
 
searchObj = re.search( r‘(.*) are (.*?) .*‘, line)
 
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!!")

searchObj.group() :  Cats are smarter than dogs
searchObj.group(1) :  Cats
searchObj.group(2) :  smarter

import re
 
phone = "2004-959-559 # 这是一个国外电话号码"
 
# 删除字符串中的 Python注释 
num = re.sub(r‘#.*$‘, "", phone)
print ("电话号码是: ", num)
 
# 删除非数字(-)的字符串 
num = re.sub(r‘\D‘, "", phone)
print ("电话号码是 : ", num)

电话号码是:  2004-959-559 
电话号码是 :  2004959559

>>>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
(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
 
pattern = re.compile(r‘\d+‘)   # 查找数字
result1 = pattern.findall(‘runoob 123 google 456‘)
result2 = pattern.findall(‘run88oob123google456‘, 0, 10)
 
print(result1)
print(result2)

[‘123‘, ‘456‘]
[‘88‘, ‘12‘]

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



12 
32 
43 
3

>>>import re
>>> re.split(‘\W+‘, ‘runoob, runoob, runoob.‘)
[‘runoob‘, ‘runoob‘, ‘runoob‘, ‘‘]
>>> re.split(‘(\W+)‘, ‘ runoob, runoob, runoob.‘) 
[‘‘, ‘ ‘, ‘runoob‘, ‘, ‘, ‘runoob‘, ‘, ‘, ‘runoob‘, ‘.‘, ‘‘]
>>> re.split(‘\W+‘, ‘ runoob, runoob, runoob.‘, 1) 
[‘‘, ‘runoob, runoob, runoob.‘]
 
>>> 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‘]