import re

data = 'bat sad bit ad but d fa hat adfad hit ad da d hut aa'

patt = '[bh][uia]t'

m = re.findall(patt,data)

print(m)

data = 'adfass323f sadfa aadfa'

patt = '\w+\s\w+'

m = re.match(patt, data)

m.group()

'adfass323f sadfa'

data = 'adfaf  aa, dadada'

patt = '\w+,\s\w+'

m = re.search(patt, data)

m.group()

'aa, dadada'

data = 'adaas1212dfdfsadfaaf_'

patt = '[_A-Za-z]+[_\w]+'   #有效Python标识符：以下划线和字母开头的非空字符，

m = re.match(patt, data)

m.group()

'adaas1212dfdfsadfaaf_'

data = '3120 De la Cruz Bou levard'

patt = r'\d+.+'     #以数字开头的任何字符串

m = re.match(patt,data)

m.group()

'3120 De la Cruz Bou levard'

data = 'http://www.y.as.sadf.a121.2asasdoo.cc'

patt = r'http://(www\.[\w|\.]+\.(com|cn|org|net|cc))'

m = re.match(patt,data)

m.group(1)

'www.y.as.sadf.a121.2asasdoo.cc'

data = '-123141234'

patt = '[-|+]?\d+$'

m = re.match(patt, data)

m.group()

'-123141234'

data = '123141234L'

patt = '[-|+]?\d+[lL]'

m = re.match(patt, data)

m.group()

'123141234L'

data = '-12310.09'

patt = '[-|+]?\d+\.\d*'

m = re.match(patt, data)

m.group()

'-12310.09'

data = '121+989i'

patt = r'\d+(\+\d*i)'   #简单的实部和虚部都是整数

m = re.match(patt, data)

m.group()

'121+989i'

data = 'y.1-a-9.a@t.w-0.9-3-c.com'

patt = r'[a-zA-Z]+([-\.]?\w+)+@((\w+-?\w*)+\.)+\w{2,3}'   #6~18个字符，可使用字母、数字、下划线，需以字母开头

m = re.match(patt, data)

m.group()

'y.1-a-9.a@t.w-0.9-3-c.com'

data = 'http://www.ba-i.du.com.cn http://ww.qq.com'

patt = r'http://((\w+[-\.])*\w+)'

m = re.match(patt, data).group()

n = re.findall(patt, data)

print(n)

data = type(.34)

print(data)

type(0)

<class 'float'>

import re

data = "type 'int' type 'float'"

patt = r'type \'(\w+)\''

m = re.findall(patt, data)

m

['int', 'float']

date = '10 11 12  09'

patt = '1\d'

m = re.findall(patt,date)

m

['10', '11', '12']

data = '1111-111111-11111'

data2 = '1111-1111-1111-1111'

patt = r'\d{4}-\d{4}(\d{2})?-\d{4}\d?(-\d{4})?'

m = re.match(patt, data)

m.group()

'1111-111111-11111'

import re

data = '1111-111111-11111'

data2 = '1111-1111-1111-1111'

patt = r'\d{4}-(\d{4}(\d{2})?)-(\d{4}\d?)(-\d{4})?'

m = re.match(patt, data2)

if m == None:

    print('Error')

elif len(m.group(1))==6 and len(m.group(3))==5:

    print('Yes, It is 465')

elif len(m.group(1))==4 and len(m.group(3))==4:

    print('Yes, it is 4444')

else:

    print('No')

​

#!/usr/bin/env python

#gendata.py

from random import randrange, choice

from string import ascii_lowercase as lc

#from sys import int

from time import ctime

​

tlds = ('com', 'edu', 'net', 'org', 'gov')

for i in range(randrange(5,11)):

    dtint = randrange(2**32)   #pick date

    dtstr = ctime(dtint)        #date string

    llen = randrange(4, 8)      #login is shorter

    login = ''.join(choice(lc) for j in range(llen))

    dlen = randrange(llen, 13)  #domain is longer

    dom = ''.join(choice(lc) for j in range(dlen))

    print('%s::%s@%s.%s::%d-%d-%d' % (dtstr, login,

              dom, choice(tlds), dtint, llen, dlen))

#!/usr/bin/env python

#gendata.py

from random import randrange, choice

from string import ascii_lowercase as lc

#from sys import int

from time import ctime

​

tlds = ('com', 'edu', 'net', 'org', 'gov')

f = open('redata.txt','w')

for i in range(randrange(5,11)):

    dtint = randrange(2**32)   #pick date

    dtstr = ctime(dtint)        #date string

    llen = randrange(4, 8)      #login is shorter

    login = ''.join(choice(lc) for j in range(llen))

    dlen = randrange(llen, 13)  #domain is longer

    dom = ''.join(choice(lc) for j in range(dlen)) 

    data = '%s::%s@%s.%s::%d-%d-%d\n' % (dtstr, login,

              dom, choice(tlds), dtint, llen, dlen)

    f.write(data)

    print('%s::%s@%s.%s::%d-%d-%d' % (dtstr, login,

              dom, choice(tlds), dtint, llen, dlen))

f.close()

#Fweekday = ['Mon','Tue','Wed','Thu','Fri','Sat','Sun']

import re

patt = r'^\w{3}\s'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'\s\w{3}\s'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'^\w{3}\s\w{3}\s\s?\d{1,2}\s\d{2}:\d{2}:\d{2}'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'^\w{3}\s\w{3}\s\s?\d{1,2}\s\d{2}:\d{2}:\d{2}'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'\w+@\w+\.\w{3}'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'\s\w{3}\s'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'(\d{4}):'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'\d{2}:\d{2}:\d{2}'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'@(\w+\.\w{3})'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'@(\w+)\.(\w{3})'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()

import re

patt = r'\w+@\w+\.\w{3}'

f = open('redata.txt','r')

for i in f:

    #print(i)

    l = re.sub(patt,'xx@yy.com',i)

    print(l)

f.close()

import re

patt = r'(\w{3})\s\s?(\d{1,2})\s\d{2}:\d{2}:\d{2}\s(\d{4})'

f = open('redata.txt','r')

for i in f:

    print(re.findall(patt, i.rstrip()))

f.close()