import re

text = "you are python"
match = re.search(‘are‘,text)

# 返回‘are‘第一个字符在text中的位置，注意是从0开始
print(match.start())

# 返回‘are‘最后一个字符在text中的位置，这里是从1开始
print(match.end())

4
7

import re

text = "you are SB"

# compile()函数会把一个表达式字符串转化为一个RegexObject
regexes = {re.compile(p)
           for p in [‘SB‘,‘NB‘,‘MB‘]
           }

for regex in regexes:
    if regex.search(text):
        print(‘seeking ‘ + regex.pattern + ‘ >> match‘)
    else:
        print(‘seeking ‘ + regex.pattern + ‘ >> not match‘)

seeking NB >> not match
seeking SB >> match
seeking MB >> not match

import re

text = "ab aa ab bb ab ba"

# 把text所有的‘ab‘组合都匹配出来
print(re.findall(‘ab‘,text))

[‘ab‘, ‘ab‘, ‘ab‘]

import re

text = "ab aa ab bb ab ba"

for match in re.finditer(‘ab‘,text):
    s = match.start()
    e = match.end()
    print(‘found {} at {} to {}‘.format(‘"ab"‘,str(s),str(e)))

found "ab" at 0 to 2
found "ab" at 6 to 8
found "ab" at 12 to 14

import re

def test_patterns(text,patterns = []):
    # pattern分别返回patterns各项的的第一个元素，desc分别返回patterns各项的的第二个元素
    # 本函数相当于把patterns第一项作为匹配条件来匹配text
    for pattern,desc in patterns:
        print(‘匹配方式：‘ + pattern, ‘说明：‘ + desc)
        print(‘文本:‘ + text)
        for match in re.finditer(pattern,text):
            s = match.start()
            e = match.end()
            print(‘found {} at {} to {}, result:{}‘.format(pattern,str(s),str(e),(text[s:e])))

# 匹配所有a开头，后面是1个b的

>>> test_patterns(‘a ab abb abbb ‘,[(‘ab‘,‘a followed by b‘)])

匹配方式：ab 说明：a followed by b
文本:a ab abb abbb 
found ab at 2 to 4, result:ab
found ab at 5 to 7, result:ab
found ab at 9 to 11, result:ab
>>>

# * 表示该模式会重复0次或多次（重复0次即意味着它不出现也能被匹配）
# 匹配a开头，后面为0个或多个b，也就是只要出现a就能匹配

>>> test_patterns(‘a ac ab abb abbb ‘,[(‘ab*‘,‘a followed by zero or more b‘)])

匹配方式：ab* 说明：a followed by zero or more b
文本:a ac ab abb abbb 
found ab* at 0 to 1, result:a
found ab* at 2 to 3, result:a
found ab* at 5 to 7, result:ab
found ab* at 8 to 11, result:abb
found ab* at 12 to 16, result:abbb
>>>

# + 表示该模式至少出现一次
# 匹配a开头，后面至少有1个b的

>>> test_patterns(‘a ab abb abbb ‘,[(‘ab+‘,‘a followed by one or more b‘)])
匹配方式：ab+ 说明：a followed by one or more b
文本:a ab abb abbb 
found ab+ at 2 to 4, result:ab
found ab+ at 5 to 8, result:abb
found ab+ at 9 to 13, result:abbb
>>> 

# ? 表示模式出现0次或1次
# 匹配a开头，后面为0个或1个b，也就是只要出现a就能匹配

>>> test_patterns(‘a ab abb abbb ‘,[(‘ab+‘,‘a followed by one or more b‘)])

匹配方式：ab+ 说明：a followed by one or more b
文本:a ab abb abbb 
found ab+ at 2 to 4, result:ab
found ab+ at 5 to 8, result:abb
found ab+ at 9 to 13, result:abbb
>>>

# 匹配a开头，后面3个b

>>> test_patterns(‘a ab abb abbb ‘,[(‘ab{3}‘,‘a followed by three b‘)])

匹配方式：ab{3} 说明：a followed by three b
文本:a ab abb abbb 
found ab{3} at 9 to 13, result:abbb
>>>

# 匹配a开头，后面2个或3个b

>>> test_patterns(‘a ab abb abbb ‘,[(‘ab{2,3}‘,‘a followed by two or three b‘)])

匹配方式：ab{2,3} 说明：a followed by two or three b
文本:a ab abb abbb 
found ab{2,3} at 5 to 8, result:abb
found ab{2,3} at 9 to 13, result:abbb
>>>

# 匹配所有a或b

>>> test_patterns(‘abca‘,[(‘[ab]‘,‘either a or b‘)])

匹配方式：[ab] 说明：either a or b
文本:abca
found [ab] at 0 to 1, result:a
found [ab] at 1 to 2, result:b
found [ab] at 3 to 4, result:a
>>>

# 匹配a开头，后面是a或b的

>>> test_patterns(‘a aa ab ac‘,[(‘a[ab]‘,‘a followed by a or b‘)])

匹配方式：a[ab] 说明：a followed by a or b
文本:a aa ab ac
found a[ab] at 2 to 4, result:aa
found a[ab] at 5 to 7, result:ab
>>>

# 匹配a开头，后面是1个或多个a或b的

>>> test_patterns(‘a aaaaa abbb accc‘,[(‘a[ab]+‘,‘a followed by 1 or more a or b‘)])

匹配方式：a[ab]+ 说明：a followed by 1 or more a or b
文本:a aaaaa abbb accc
found a[ab]+ at 2 to 7, result:aaaaa
found a[ab]+ at 8 to 12, result:abbb
>>>