Python 模式表达与正则表达式

1.国外手机判断

def iphonenum(txt):
    if len(txt) != 12:
        return False
    for i in range(3):
        if not txt[i].isdecimal():
            return False
    if txt[3] != '-':
        return False
    for j in range(4, 7):
        if not txt[j].isdecimal():
            return False
    if txt[7] != '-':
        return False
    for l in range(8, 12):
        if not txt[l].isdecimal():
            return False
    return True

print('请输入手机号码：', end='')
k =input()
print('判断是否为手机号码：', iphonenum(k))

2.查找文本中的手机号码

def iphonenum(txt):
    if len(txt) != 12:
        return False
    for i in range(3):
        if not txt[i].isdecimal():
            return False
    if txt[3] != '-':
        return False
    for j in range(4, 7):
        if not txt[j].isdecimal():
            return False
    if txt[7] != '-':
        return False
    for l in range(8, 12):
        if not txt[l].isdecimal():
            return False
    return True

mes='Call me at 415-555-1101 tomorrow.415-666-7845 is my office.'
for m in range(len(mes)):
    n = mes[m:m+12]
    if iphonenum(n):
        print('找到的电话号码是：', n)
print('查找完成')

3.判断国内手机号码

def iphonenum(txt):
    if len(txt) != 11:
        return False
    for i in range(11):
        if not txt[i].isdecimal():
            return False
    return True

print('请输入手机号码：', end='')
k =input()
print('判断是否为手机号码：', iphonenum(k))

4.正则表达式
例一：

import re
phonenum = re.compile(r'\d\d\d-\d\d\d-\d\d\d\d')
k = 'my phone Number is 400-410-8888, and my office number is 411-808-9999·'
mo = phonenum.search(k)
print('打印出找到的电话号码：', mo.group())
print(mo.groups())

例二：

import re
phonenum = re.compile(r'(\d\d\d)-(\d\d\d-\d\d\d\d)')
k = 'my phone Number is 400-410-8888, and my office number is 411-808-9999'
mo = phonenum.search(k)
print('1：', mo.group())
print('2：', mo.group(1))
print('3：', mo.group(2))
print('4：', mo.groups())
j,  l = mo.groups()
print('5：', j)
print('6：', l)
m = mo.groups()
n=list(m)
print('7：', n)
o=tuple(n)
print('8：', o)
p='-'.join(o)
print('9：', p)

5.用管道匹配分组

import re
ph = re.compile(r'Batman|Tina Fey')
a = "Batman and Tina Fey"
b = "Tina Fey and Batman"
mo1 = ph.search(a)
mo2 = ph.search(b)
print('1：', mo1.group())
print('2：', mo2.group())

phx = re.compile(r'Bat(man|mil|cop|kk)')
c = "Batman and Batmil and Batcop and Tina"
mo3 = phx.search(c)
print('3：', mo3.group())
print('4：', mo3.groups())
print('5：', mo3.group(1))
print(''' ////////以下是4和5转换为的列表''''')
d =list(mo3.groups())
print('6：',d)
e =mo3.group(1)
f = e.split()
print('7：', f)

6.问号实现可选匹配

import re
px = re.compile(r'Bat(wo)?man')
z = 'The Adventures of Batman'
x = 'The Adventures of Batwoman'
c = 'The Adventures of Batwowoman Batman'
mo1 = px.search(z)
print('1：', mo1.group())
print('1：', mo1.groups())
print('1：', mo1.group(1))
mo2 = px.search(x)
print('2：', mo2.group())
print('2：', mo2.groups())
print('2：', mo2.group(1))
mo3 = px.search(c)
print('3：', mo3.group())
print('3：', mo3.groups())
print('3：', mo3.group(1))

7.星号实现0个或多个匹配

import re
px = re.compile(r'Bat(wo)*man')
z = 'The Adventures of Batman'
x = 'The Adventures of Batwoman'
c = 'The Adventures of Batwowoman Batman'
mo1 = px.search(z)
print('1：', mo1.group())
print('1：', mo1.groups())
print('1：', mo1.group(1))
mo2 = px.search(x)
print('2：', mo2.group())
print('2：', mo2.groups())
print('2：', mo2.group(1))
mo3 = px.search(c)
print('3：', mo3.group())
print('3：', mo3.groups())
print('3：', mo3.group(1))

8.加号实现一个或多个匹配

import re
px = re.compile(r'Bat(wo)+man')
x = 'The Adventures of Batwoman'
c = 'The Adventures of Batwowoman Batman'
mo2 = px.search(x)
print('2：', mo2.group())
print('2：', mo2.groups())
print('2：', mo2.group(1))
mo3 = px.search(c)
print('3：', mo3.group())
print('3：', mo3.groups())
print('3：', mo3.group(1))

9.花括号实现特定次数匹配

import re
px = re.compile(r'Bat(wo){3,5}man')
x = 'The Adventures of Batwowowoman'
c = 'The Adventures of Batwowowowoman Batman'
mo2 = px.search(x)
print('2：', mo2.group())
print('2：', mo2.groups())
print('2：', mo2.group(1))
mo3 = px.search(c)
print('3：', mo3.group())
print('3：', mo3.groups())
print('3：', mo3.group(1))
print('Python正则表达式默认是贪心的，在有二义的情况匹配最长字符 ')
10.findall()使用方法
import re
phonenum = re.compile(r'\d\d\d-\d\d\d-\d\d\d\d')
k = 'my phone Number is 400-410-8888, and my office number is 411-808-9999·411-785-1360,361-879-1360'
mo = phonenum.findall(k)
for i in range(len(mo)):
    k =mo[i]
    print('打印出找到的第'+str(i+1)+'个电话号码：', k)

10.字符分类

'''
\d   0-9的数字
\D   除0-9以外的数字
\w   任何数字字母或下划线字符（匹配单词字符）
\W   除字母，数字和下划线以外的任何字符
\s    空格，制表符，换行符（匹配空白字符）
\S    除空格，制表符，换行符以外的任何字符
'''
print(
'''
\d   0-9的数字
\D   除0-9以外的数字
\w   任何数字字母或下划线字符（匹配单词字符）
\W   除字母，数字和下划线以外的任何字符
\s    空格，制表符，换行符（匹配空白字符）
\S    除空格，制表符，换行符以外的任何字符
''')
import re
ce =re.compile(r'\d+\s+\w')
le = re.compile(r'\d+\s')
qe = re.compile(r'\d+')
ke='11 text,23 your,89 kill'
ve =ce.findall(ke)
print('输出第一次从字符串中提取的列表：', ve)
be = ' '.join(ve)
print('把列表转换为字符串：', be)
ne =le.findall(be)
print('输出第二次从字符串中提取的列表：', ne)
me =[]
for i in range(len(ne)):
    o =ne[i]
    p = o.strip()
    me.append(p)
print('输出去空格过后的数字列表：', me)
tuple1 = tuple(me)
print('输出转换的元组：', tuple1)
str2=' '.join(tuple1)
print('输出字符串：', str2)
we = qe.findall(str2)
print('再次转换为列表：', we)
ee = ''.join(we)
print('把所有数字链接：', ee)

11.建立自己的字符分类

#建立 自己的字符分类
import re
vowe =re.compile(r'[aeirAidR]')
ve = 'Administrator,try agin'
ce = vowe.findall(ve)
print(ce)

12.插入字符和美元字符

import re
ne = re.compile(r'\d$')
ve = re.compile(r'^Hello')
ce = 'Hello World!'
me = "my number is 42"
be =ne.search(me)
ae = ne.findall(me)
print(be)
print(ae)
xe = ve.search(ce)
ze= ve.findall(ce)
print(xe)
print(ze)

13.通配字符

import re
me = re.compile(r'.at')
ne = 'the cat in the hat.sat on the flat mat'
be = me.findall(ne)
k =input('请加入一个以at结尾的单词：')
be.append(k)
print(be)
ve =' '.join(be)
ce=''.join(be)
print(ve)
print(ce)

14.用点-星匹配所有字符

import re
me = re.compile(r'First Name:(.*) Last Name:(.*)')
ne = 'My First Name:Eric Last Name:Qiu'
be =me.search(ne)
print(be)
print(be.group())
print(be.groups())
print(be.group(1))
print(be.group(2))

15句点字符匹配换行

import re
me = re.compile(r'.*')
ve =re.compile(r'.*', re.DOTALL)
ne = 'My First Name:Eric \nLast Name:Qiu'
be = me.search(ne)
ce = ve.search(ne)
print(be.group())
print(ce.group())

16.不区分大小写

import re
me1 = re.compile('RoboCop')
me1 = re.compile('RObOCOP')
me1 = re.compile('robOcop')
me1 = re.compile('RobocOp')
ne = re.compile(r'robocop', re.I)
be = "RoboCop is part man.part machine,all cop"
ve = ne.search(be)
print(ve.group())

17.使用sub()方法替换替换字符

import re
ne = re.compile(r'Agent \w+')
ve = ne.sub('CENSORED','Agent gave is part man.part machine,all cop')
print(ve)