Python玩转正则表达式，看完这篇你就会了?

(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)

re.match(pattern, string, flags=0)

# -*- coding:utf-8 -*-
import re

print(re.match('www', 'www.csdn.net')) # 在起始位置匹配
print(re.match('net', 'www.csdn.net')) # 不在起始位置匹配

<re.Match object; span=(0, 3), match='www'>
None

# -*- coding:utf-8 -*-
import re

line = u"已赞75，评论12，收藏231"

match_obj = re.match( r'已赞(\d*).评论(\d*).收藏(\d*)', line, re.M|re.I)

if match_obj:
   print ("match_obj.group() : ", match_obj.group())
   print ("match_obj.group(1) : ", match_obj.group(1))
   print ("match_obj.group(2) : ", match_obj.group(2))
   print ("match_obj.group(3) : ", match_obj.group(3))
else:
   print ("No match!!")

match_obj.group() :  已赞75，评论12，收藏231
match_obj.group(1) :  75
match_obj.group(2) :  12
match_obj.group(3) :  231

re.search(pattern, string, flags=0)

# -*- coding:utf-8 -*-
import re

print(re.search('www', 'www.csdn.net'))  # 在起始位置匹配
print(re.search('net', 'www.csdn.net'))  # 不在起始位置匹配

<re.Match object; span=(0, 3), match='www'>
<re.Match object; span=(9, 12), match='net'>

# -*- coding:utf-8 -*-
import re

line = u"作者Clever_Hui，阅读量4155，收藏231，分类专栏python"

search_obj = re.search( r'作者(\w*).阅读量(\d*).收藏(\d*).分类专栏(\w*)', line, re.M|re.I)

if search_obj:
   print ("search_obj.group() : ", search_obj.group())
   print ("search_obj.group(1) : ", search_obj.group(1))
   print ("search_obj.group(2) : ", search_obj.group(2))
   print ("search_obj.group(3) : ", search_obj.group(3))
   print ("search_obj.group(4) : ", search_obj.group(4))
else:
   print ("Nothing found!!!")

search_obj.group() :  作者Clever_Hui，阅读量4155，收藏231，分类专栏python
search_obj.group(1) :  Clever_Hui
search_obj.group(2) :  4155
search_obj.group(3) :  231
search_obj.group(4) :  python

# -*- coding:utf-8 -*-
import re

match_obj = re.match('net', 'www.csdn.net')
rearch_obj = re.search('net', 'www.csdn.net')

if match_obj:
    print('match    -->  ', match_oj)
else:
    print('No match!!!')

if rearch_obj:
     print('search  -->  ', rearch_obj)
else:
    print('No Match!!!')

No match!!!
search  -->   <re.Match object; span=(9, 12), match='net'>

findall(pattern, string, flags=0)

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.

# -*- coding:utf-8 -*-
import re

line = "python = 9999, c = 7890, java = 12345"
ret1 = re.findall(r"\d+", line)
ret2 = re.findall(r"(\w+)\s.\s(\d+)", line)

print(ret1)
print(ret2)

['9999', '7890', '12345']
[('python', '9999'), ('c', '7890'), ('java', '12345')]

re.sub(pattern, repl, string, count=0, flags=0)

sub(pattern, repl, string, count=0, flags=0)
    Return the string obtained by replacing the leftmost
    non-overlapping occurrences of the pattern in string by the
    replacement repl.  repl can be either a string or a callable;
    if a string, backslash escapes in it are processed.  If it is
    a callable, it's passed the Match object and must return
    a replacement string to be used.

# -*- coding:utf-8 -*-
import re

ret = re.sub(r"\d+", '998', "python = 997")
print(ret)

python = 998

# -*- coding:utf-8 -*-
import re

def add(temp):
    strNum = temp.group()
    num = int(strNum) + 1
    return str(num)

ret = re.sub(r"\d+", add, "python = 997")
print(ret)

ret = re.sub(r"\d+", add, "python = 99")
print(ret)

python = 998
python = 100

# -*- coding:utf-8 -*-
import re

s="This is a number 234-235-22-423"
r=re.match(".+(\d+-\d+-\d+-\d+)",s)
print(r.group(1))
# '4-235-22-423'

r=re.match(".+?(\d+-\d+-\d+-\d+)",s)
print(r.group(1))
# '234-235-22-423'

>>> re.match(r"aa(\d+)","aa2343ddd").group(1)
'2343'
>>> re.match(r"aa(\d+?)","aa2343ddd").group(1)
'2'
>>> re.match(r"aa(\d+)ddd","aa2343ddd").group(1) 
'2343'
>>> re.match(r"aa(\d+?)ddd","aa2343ddd").group(1)
'2343'
>>>

>>> mm = "c:\\a\\b\\c"
>>> mm
'c:\\a\\b\\c'
>>> print(mm)
c:\a\b\c
    
>>> re.match("c:\\\\",mm).group()
'c:\\'

>>> ret = re.match("c:\\\\",mm).group()
>>> print(ret)
c:\
    
>>> ret = re.match("c:\\\\a",mm).group()
>>> print(ret)
c:\a
    
>>> ret = re.match(r"c:\\a",mm).group()
>>> print(ret)
c:\a
    
>>> ret = re.match(r"c:\a",mm).group()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
AttributeError: 'NoneType' object has no attribute 'group'
>>>

>>> ret = re.match(r"c:\\a",mm).group()
>>> print(ret)
c:\a

# -*- coding:utf-8 -*-
import re

names = ["name1", "_name", "2_name", "__name__"]

for name in names:
    ret = re.match("[a-zA-Z_]+[\w]*",name)
    if ret:
        print("变量名 %s 符合要求" % ret.group())
    else:
        print("变量名 %s 非法" % name)

变量名 name1 符合要求
变量名 _name 符合要求
变量名 2_name 非法
变量名 __name__ 符合要求

# -*- coding:utf-8 -*-
import re

pwds = ["W123456W", "wwj123456", "W123456789", "w123w", "W12345678abcdefg"]
pwd_pattern_str = "^[A-Z][a-zA-Z0-9]{7,14}$"

for pwd in pwds:
    ret = re.match(pwd_pattern_str, pwd)
    if ret:
        pwd = ret.group()
        print("密码 %s 符合要求,  长度：%s" % (pwd, len(pwd)))
    else:
        print("密码 %s 非法" % pwd)

密码 W123456W 符合要求,  长度：8
密码 wwj123456 非法
密码 W123456789 符合要求,  长度：10
密码 w123w 非法
密码 W12345678abcdefg 非法