python之re模块

import re 
a = re.search(r‘(tina)(fei)haha\2‘,‘tinafeihahafei tinafihahatina‘).group()
print("结果:",a)
================
结果: tinafeihahafei

# 这里强调一下\b的单词边界的理解:
import re 
w = re.findall(‘\btina‘,‘tian tinaaaa‘)
print("结果是:",w)
s = re.findall(r‘\btina‘,‘tian tinaaaa‘)
print("结果是:",s)
v = re.findall(r‘\btina‘,‘tian#tianaaaa‘)
print("结果是:",v)
a = re.findall(r‘\btina\b‘,‘tian#tina@aaa‘)
print("结果是:",a)
==================
结果是: []
结果是: [‘tina‘]
结果是: [‘tina‘]
结果是: [‘tina‘]

import re 
tt = "Tom is a good boy, he is cool,clever,and so on ..."
rr = re.compile(r‘\w*oo\w*‘)
print("执行结果是:",rr.findall(tt))   # 查找所有包含‘oo‘的单词
================
执行结果是: [‘good‘, ‘cool‘]

import re 
a = re.match(‘com‘,‘comwww.runcomoob‘).group()
print("a的结果是:",a)
b = re.match(‘com‘,‘Comwww.baidu‘,re.I)
print("b的结果是:",b)   # re.I 对大小写不敏感
========================
a的结果是: com
b的结果是: Com

import re 
a = re.search(‘\dcom‘,‘www.4comrnuoob.5com‘).group()
print("a的结果是:",a)
b  = re.search(‘com‘,‘python.org‘)
print("b的结果是:",b)
===================
a的结果是: 4com
b的结果是: None

import re 
a = "123abc456"
r = re.search(‘([0-9]*)([a-z]*)([0-9]*)‘,a)
print("r.group(0)的结果",r.group(0))
print("r.group(1)的结果",r.group(1))
print("r.group(2)的结果",r.group(2))
print("r.group(3)的结果",r.group(3)) 
#group(1) 列出第一个括号匹配部分，group(2) 列出第二个括号匹配部分，group(3) 列出第三个括号匹配部分。
=======================
r.group(0)的结果 123abc456
r.group(1)的结果 123
r.group(2)的结果 abc
r.group(3)的结果 456

import re 
p = re.compile(r‘\d+‘)
r = p.findall(‘o1n2m3k4‘)
print("匹配的结果是:",r)
============
匹配的结果是: [‘1‘, ‘2‘, ‘3‘, ‘4‘]
import re 
tt = "Jack is a good boy, he is cool,clever,and so on .... "
rr = re.compile(r‘\w*oo\w*‘)
print("rr.findall(tt)匹配的结果是:",rr.findall(tt))
print("re.findall(r‘(\w)*oo(\w)‘)匹配的结果是:",re.findall(r‘(\w)*oo(\w)‘,tt))
==================
rr.findall(tt)匹配的结果是: [‘good‘, ‘cool‘]
re.findall(r‘(\w)*oo(\w)‘)匹配的结果是: [(‘g‘, ‘d‘), (‘c‘, ‘l‘)]

import re 
iter = re.finditer(r‘\d+‘,‘12 drumm44ers drumming,11 ... 10 ...  ‘)
for i in iter:
    print("匹配结果是:",i)
    print("i.group()匹配结果是:",i.group())
    print("i.span()匹配结果是:",i.span())
==========================================
匹配结果是: <_sre.SRE_Match object; span=(0, 2), match=‘12‘>
i.group()匹配结果是: 12
i.span()匹配结果是: (0, 2)
匹配结果是: <_sre.SRE_Match object; span=(8, 10), match=‘44‘>
i.group()匹配结果是: 44
i.span()匹配结果是: (8, 10)
匹配结果是: <_sre.SRE_Match object; span=(23, 25), match=‘11‘>
i.group()匹配结果是: 11
i.span()匹配结果是: (23, 25)
匹配结果是: <_sre.SRE_Match object; span=(30, 32), match=‘10‘>
i.group()匹配结果是: 10
i.span()匹配结果是: (30, 32)

import re 
rr = re.split(‘\d+‘,‘one1two2three3four4five5‘)
print("rr匹配的结果是:",rr)
wrr = re.split(‘[a-z]+‘,‘one1two2three3four4five5‘)
print("wrr匹配的结果是:",wrr)
================================
rr匹配的结果是: [‘one‘, ‘two‘, ‘three‘, ‘four‘, ‘five‘, ‘‘]
wrr匹配的结果是: [‘‘, ‘1‘, ‘2‘, ‘3‘, ‘4‘, ‘5‘]

import re
text = "JGood is a handsome boy, he is cool, clever, and so on..."
rr = re.sub(r‘\s+‘,‘-‘,text)
print("替换后的结果是:",rr)
========================
替换后的结果是: JGood-is-a-handsome-boy,-he-is-cool,-clever,-and-so-on...

import re 
text  = "JGood is a handsome boy, he is cool, clever, and so on..."
rr = re.sub(r‘\s‘,lambda m:‘[‘+ m.group(0) +‘]‘,text,0)
print("替换后的结果是:",rr)
===========================
替换后的结果是: JGood[ ]is[ ]a[ ]handsome[ ]boy,[ ]he[ ]is[ ]cool,[ ]clever,[ ]and[ ]so[ ]on...

import re
tt = ‘123456abcdef‘
rr = re.subn(‘[1-2]‘,‘A‘,tt)
rr1 = re.sub("g.t","have",‘I get A,I get B,I get C‘)
rr2 = re.subn("g.t","have",‘I get A,I get B,I get C‘)
=====================
re.subn()匹配的结果: (‘AA3456abcdef‘, 2)
re.sub()匹配的结果: I have A,I have B,I have C
re.subn()匹配的结果: (‘I have A,I have B,I have C‘, 3)

import re 
a = re.search(‘[\d]‘,‘abc33‘).group()
print("a匹配的结果是:",a)
p = re.match(‘[\d]‘,‘abc33‘)
print("p匹配的结果是:",p)
b = re.findall(‘[\d]‘,‘abc33‘)
print("b匹配的结果是:",b)
============================
a匹配的结果是: 3
p匹配的结果是: None
b匹配的结果是: [‘3‘, ‘3‘]

import re
a = re.findall(‘a(\d+?)‘,‘a23b‘)
print("a惰性匹配的结果:",a)
b = re.findall(‘a(\d+)‘,‘a23b‘)
print("b贪恋匹配的结果:",b)
==========================
a惰性匹配的结果: [‘2‘]
b贪恋匹配的结果: [‘23‘]

import re 
a = re.match(‘<(.*)>‘,‘<H1>title</H1>‘).group()
print("a是贪婪匹配的结果:",a)
b = re.match(‘<(.*?)>‘,‘<H1>title</H1>‘).group()
print("b是惰性匹配的结果:",b)
==============================
a是贪婪匹配的结果: <H1>title</H1>
b是惰性匹配的结果: <H1>

import re 
a = re.findall(r‘a(\d+)b‘,‘a33333b‘)
print("a是贪婪匹配的结果:",a)
b = re.findall(r‘a(\d+?)b‘,‘a33333b‘)
print("b是惰性匹配的结果:",b)
====================
a是贪婪匹配的结果: [‘33333‘]
b是惰性匹配的结果: [‘33333‘]

import re
rr = re.split(‘a‘,‘1A1a2A3‘,re.I)
print("rr输出的结果是:",rr)
================
rr输出的结果是: [‘1A1‘, ‘2A3‘]

import re
rr = re.split(‘a‘,‘1A1a2A3‘,flags=re.I)
print("rr输出的结果是:",rr)
=================
rr输出的结果是: [‘1‘, ‘1‘, ‘2‘, ‘3‘]

import re
# 方法一:
phone_pat = re.compile(‘^(13\d|14[5|7]|15\d|166|17[3|6|7]|18\d)\d{8}$‘)
while True:
    phone = input(‘请输入你的电话号码:‘)
    res = re.search(phone_pat,phone)
    if res:
       print(‘正常手机号‘)
    else:
       print(‘不是手机号‘)
# 方法二
tel_pat = re.compile(‘^0\d[0-9]{2}|[0-9]{3}-\d[0-9]{8}|[0-9]{7}‘)
while True:
    tel = input(‘请输入你的座机号:‘)
    res = re.search(tel_pat,tel)
    # res1 = re.search(tel_pat1,tel)
    if res:
       print(‘格式正确‘)
    else:
        print(‘格式不正确‘)

import re 
re.search(r"(([01]?\d?\d|2[0-4]\d|25[0-5])\.){3}([01]?\d?\d|2[0-4]\d|25[0-5]\.)","192.168.1.1")

import re  
text = input("Please input your Email address：\n")  
if re.match(r‘^[0-9a-zA-Z_]{0,19}@[0-9a-zA-Z]{1,13}\.[com,cn,net]{1,3}$‘,text):  
#if re.match(r‘[0-9a-zA-Z_]{0,19}@163.com‘,text):  
    print(‘Email address is Right!‘)  
else:  
    print(‘Please reset your right Email address!‘)