30-Python3 正则表达式

30-Python3 正则表达式

'''
re.match函数
'''
import re
print(re.match('www','www.runoob.com').span())
print(re.match('ww','www.runoob.com').span())
print(re.match('w','www.runoob.com').span())
print(re.match('com','www.runoob.com'))
 
line = 'Cats are smarter than dogs'
macthObj = re.match(r'(.*)are(.*?).*',line,re.M|re.I)
if macthObj:
    print('matchObj.group():',macthObj.group())
    print('matchObj.group(1):',macthObj.group(1))
    print('matchObj.group(2):',macthObj.group(2))
else:
    print('No match')
 
'''
re.search方法
'''
import re
print(re.search('www','www.runoob.com').span())
print(re.search('com','www.runoob.com').span())
 
line1 = 'Cats are smarter than dogs'
searchObj = re.search(r'(.*)are(.*?).*',line1,re.M|re.I)
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!')
 
'''
re.match和re.search的区别
'''
line2 = 'Cats are smarter than dogs'
matchObj = re.match(r'dogs',line2,re.M|re.I)
if matchObj:
    print('re.match:',matchObj.group())
else:
    print('no match1')
matchObj = re.search(r'dogs',line2,re.M|re.I)
if matchObj:
    print('re.search:',matchObj.group())
else:
    print('no match2')
'''
检索和替换
'''
phone = '2004-959-559 #这是一个电话号码'
##删除注释
num = re.sub(r'#.*$','',phone)
print('电话号码1：',num)
##移除非数字的内容
num = re.sub(r'\D','',phone)
print('电话号码2：',num)
 
'''
repl参数是一个函数
'''
 
#将匹配到到数字乘以2
def double(matched):
    value = int(matched.group('value'))
    return str(value*2)
 
s = 'QAA342RFDFD56FGFG'
print(re.sub('(?P<value>\d+)',double,s))
 
'''
compile函数
'''
pattern1 = re.compile(r'\d+')
m = pattern1.match('one12twothree34four')
m1 = pattern1.search('one12twothree34four')
print('m',m)
print('m1',m1)
 
m2 =pattern1.match('one12twothree34four',2,10)
print('m2',m2)
 
m3 =pattern1.match('one12twothree34four',3,10)
print('m3:',m3)
 
print('m3.group():',m3.group())
print('m3.start():',m3.start())
print('m3.end():',m3.end())
print('m3.span():',m3.span())
 
pattern2 = re.compile(r'([a-z]+)([a-z])',re.I) #re.I 表示忽略大小写
mm = pattern2.match('Hello World Wide Web')
print('mm:',mm)
 
print('mm.group(0):',mm.group(0))
print('mm.span(0):',mm.span(0))
print('mm.group(1):',mm.group(1))
print('mm.span(1):',mm.span(1))
print('mm.group(2):',mm.group(2))
print('mm.span(2):',mm.span(2))
print('mm.groups():',mm.groups())
# print('mm.group(3):',mm.group(3))
 
'''
findall
'''
# 在字符串中找到正则表达式所匹配的所有子串，并返回一个列表，如果没有找到匹配的，则返回空列表。
# 注意： match 和 search 是匹配一次 findall 匹配所有。
# 语法格式为：
# findall(string[, pos[, endpos]])
pattern3 = re.compile(r'\d+')
result1 = pattern3.findall('runoob 123 google 456')
result2 = pattern3.findall('run88oob123google456',0,10)
print('result1:',result1)
print('result2:',result2)
 
'''
re.finditer:找到正则表达式所匹配的所有子串，并把他们作为一个迭代器返回
'''
it = re.finditer(r'\d+','qaz12edc34edc4rfv56')
for match in it:
    print(match.group())
'''
re.split
'''
print('1:',re.split('\W+','runoob,runoob,runoob.'))
 
print('2:',re.split('(\W+)','runoob,runoob,runoob.'))
print('',re.split('\W+','runoob,runoob,runoob.',1))
 
'''
正则表达式对象
'''
 
'''
正则表达式修饰符-可选标志
'''
 
'''
正则表达式模式
'''
 
'''
正则表达式实例
'''